diff --git a/.ipynb_checkpoints/train-mobilenetv2-checkpoint.ipynb b/.ipynb_checkpoints/train-mobilenetv2-checkpoint.ipynb
new file mode 100644
index 0000000..2341484
--- /dev/null
+++ b/.ipynb_checkpoints/train-mobilenetv2-checkpoint.ipynb
@@ -0,0 +1,1233 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Training + Testing Landslide Prediction"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Created: <b>Trong-An Bui</b> <br>\n",
+    "Organization: <b>ViP Lab - National Chi Nan University, Taiwan</b> <br/>\n",
+    "Email: trongan93@gmail.com <br/>\n",
+    "Project: <b>AI Cube Satellite</b> <br/>\n",
+    "Advisor: <b>Prof. Pei-Jun Lee</b>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "py 3.7.7\n",
+      "tf 2.2.0\n",
+      "keras 2.3.0-tf\n",
+      "mem 128555.12109375\n",
+      "cpu 40\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "['Fri Sep  4 02:44:42 2020       ',\n",
+       " '+-----------------------------------------------------------------------------+',\n",
+       " '| NVIDIA-SMI 440.100      Driver Version: 440.100      CUDA Version: 10.2     |',\n",
+       " '|-------------------------------+----------------------+----------------------+',\n",
+       " '| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |',\n",
+       " '| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |',\n",
+       " '|===============================+======================+======================|',\n",
+       " '|   0  Quadro RTX 4000     Off  | 00000000:1D:00.0 Off |                  N/A |',\n",
+       " '| 30%   35C    P8     8W / 125W |      0MiB /  7982MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '|   1  Quadro RTX 4000     Off  | 00000000:1E:00.0 Off |                  N/A |',\n",
+       " '| 30%   33C    P8     6W / 125W |      0MiB /  7982MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '|   2  Quadro RTX 4000     Off  | 00000000:1F:00.0 Off |                  N/A |',\n",
+       " '| 30%   31C    P8     4W / 125W |      0MiB /  7982MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '|   3  Quadro RTX 4000     Off  | 00000000:20:00.0 Off |                  N/A |',\n",
+       " '| 30%   33C    P8     9W / 125W |      0MiB /  7982MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '|   4  GeForce GTX 108...  Off  | 00000000:21:00.0 Off |                  N/A |',\n",
+       " '| 25%   32C    P8     8W / 250W |      0MiB / 11178MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '|   5  GeForce GTX 108...  Off  | 00000000:22:00.0 Off |                  N/A |',\n",
+       " '| 20%   24C    P8     9W / 250W |      0MiB / 11178MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '|   6  GeForce GTX 108...  Off  | 00000000:23:00.0 Off |                  N/A |',\n",
+       " '| 20%   32C    P8     9W / 250W |      0MiB / 11178MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '|   7  GeForce GTX 108...  Off  | 00000000:24:00.0 Off |                  N/A |',\n",
+       " '| 20%   29C    P8     8W / 250W |      0MiB / 11178MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '                                                                               ',\n",
+       " '+-----------------------------------------------------------------------------+',\n",
+       " '| Processes:                                                       GPU Memory |',\n",
+       " '|  GPU       PID   Type   Process name                             Usage      |',\n",
+       " '|=============================================================================|',\n",
+       " '|  No running processes found                                                 |',\n",
+       " '+-----------------------------------------------------------------------------+']"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import os\n",
+    "#os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"\"\n",
+    "#os.environ[\"AUTOGRAPH_VERBOSITY\"] = \"10\"\n",
+    "os.environ[\"TF_FORCE_GPU_ALLOW_GROWTH\"] = \"true\"\n",
+    "\n",
+    "from platform import python_version\n",
+    "import warnings\n",
+    "import time\n",
+    "import datetime as dt\n",
+    "from sklearn.metrics import classification_report, confusion_matrix\n",
+    "import multiprocessing as mp\n",
+    "import shutil\n",
+    "from imutils import paths\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "import matplotlib.image as mpimg\n",
+    "\n",
+    "import tensorflow as tf\n",
+    "from tensorflow.keras import backend as K\n",
+    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
+    "from tensorflow.keras.applications.mobilenet_v2 import MobileNetV2, preprocess_input, decode_predictions\n",
+    "from tensorflow.keras.models import *\n",
+    "from tensorflow.keras.layers import *\n",
+    "from tensorflow.keras.optimizers import *\n",
+    "from tensorflow.keras.utils import *\n",
+    "from tensorflow.keras.callbacks import *\n",
+    "from tensorflow.keras.initializers import *\n",
+    "\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import seaborn as sn\n",
+    "\n",
+    "from PIL import Image\n",
+    "import xml.etree.ElementTree as ET\n",
+    "import psutil\n",
+    "import random\n",
+    "\n",
+    "warnings.filterwarnings(\"ignore\")\n",
+    "%matplotlib inline\n",
+    "\n",
+    "print(\"py\", python_version())\n",
+    "print(\"tf\", tf.__version__)\n",
+    "print(\"keras\", tf.keras.__version__)\n",
+    "mem = psutil.virtual_memory()\n",
+    "print(\"mem\", mem.total/1024/1024)\n",
+    "cpu = mp.cpu_count()\n",
+    "print(\"cpu\", cpu)\n",
+    "\n",
+    "%system nvidia-smi\n",
+    "#%system rocm-smi"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Variables"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "epochs = 250\n",
+    "batch_size = 150\n",
+    "testsplit = .2\n",
+    "targetx = 224\n",
+    "targety = 224\n",
+    "learning_rate = 0.0001\n",
+    "classes = 2\n",
+    "seed = random.randint(1, 1000)\n",
+    "\n",
+    "data_dir = \"../LandslideDataset/\"\n",
+    "resized_dir = \"./img_data/resized/\"\n",
+    "test_dir = \"./img_data/test\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Crop images using provided annotations"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "%system rm -rf $resized_dir\n",
+    "%system mkdir $resized_dir\n",
+    "\n",
+    "\n",
+    "def crop_and_save_img(img_path, new_dir_path, original_ext_filter = 0):\n",
+    "#     print('trongan93:', new_dir_path)\n",
+    "    image = Image.open(img_path)\n",
+    "    image = image.resize((targetx,targety))\n",
+    "    image.save(new_dir_path)\n",
+    "\n",
+    "def resize_images(ext = 0):\n",
+    "    imgPaths = sorted(list(paths.list_images(data_dir)))\n",
+    "#     print('images len: ', len(imgPaths))\n",
+    "    \n",
+    "    labels_dir = os.listdir(data_dir)\n",
+    "    for label_dir in labels_dir:\n",
+    "        cropper_label_dir = resized_dir+label_dir\n",
+    "        if not os.path.exists(cropper_label_dir):\n",
+    "            os.makedirs(cropper_label_dir)\n",
+    "            print(\"sucessfull make dir for label: \", cropper_label_dir)\n",
+    "    \n",
+    "    \n",
+    "    total_images = 0\n",
+    "\n",
+    "    for imgPath in imgPaths:\n",
+    "#         print(imgPath)\n",
+    "        img_name_info = imgPath.split(os.path.sep)\n",
+    "        imgLabel = img_name_info[2]\n",
+    "#         print('img label: ', imgLabel)\n",
+    "        imgName = img_name_info[3]\n",
+    "#         print('img name: ', imgName)\n",
+    "        file_ext = os.path.splitext(imgName)[1]\n",
+    "#         print('img ext: ', file_ext)\n",
+    "        \n",
+    "        new_path = resized_dir + imgLabel + '/' + imgName\n",
+    "#         print(new_path)\n",
+    "        if ext == 0:\n",
+    "            crop_and_save_img(imgPath,new_path, original_ext_filter = 0)\n",
+    "        elif ext == 1:\n",
+    "            # TIF file\n",
+    "            if file_ext == '.TIF':\n",
+    "                crop_and_save_img(imgPath,new_path, original_ext_filter = 0)\n",
+    "            else:\n",
+    "                break\n",
+    "        elif ext == 2:\n",
+    "            # TIF file\n",
+    "            if file_ext == '.RAW':\n",
+    "                crop_and_save_img(imgPath,new_path, original_ext_filter = 0)\n",
+    "            else:\n",
+    "                break\n",
+    "                \n",
+    "        total_images += 1\n",
+    "        \n",
+    "#         annotations_dir_list = os.listdir(annotations_dir + breed)\n",
+    "#         img_list = [data_dir + breed + '/' + i for i in dir_list]\n",
+    "#         os.makedirs(cropped_dir + breed)\n",
+    "\n",
+    "#         for file in img_list:\n",
+    "#             annotation_path = annotations_dir + breed + '/' + os.path.basename(file[:-4])\n",
+    "#             newpath = cropped_dir + breed + '/' + os.path.basename(file)\n",
+    "#             save_cropped_img(file, annotation_path, newpath)\n",
+    "#             total_images += 1\n",
+    "    \n",
+    "    print(\"total images resized\", total_images)\n",
+    "\n",
+    "resize_images()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Keras image data readers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Found 2015 images belonging to 2 classes.\n",
+      "Found 502 images belonging to 2 classes.\n"
+     ]
+    }
+   ],
+   "source": [
+    "datagen = ImageDataGenerator(\n",
+    "        shear_range=0.1,\n",
+    "        zoom_range=0.1,\n",
+    "        brightness_range=[0.9,1.1],\n",
+    "        horizontal_flip=True,\n",
+    "        validation_split=testsplit,\n",
+    "        preprocessing_function=preprocess_input\n",
+    ")\n",
+    "\n",
+    "train_generator = datagen.flow_from_directory(\n",
+    "        resized_dir,\n",
+    "        target_size=(targetx, targety),\n",
+    "        batch_size=batch_size,\n",
+    "        class_mode='categorical',\n",
+    "        shuffle=True,\n",
+    "        seed=seed,\n",
+    "        subset=\"training\"\n",
+    ")\n",
+    "\n",
+    "test_generator = datagen.flow_from_directory(\n",
+    "        resized_dir,\n",
+    "        target_size=(targetx, targety),\n",
+    "        batch_size=batch_size,\n",
+    "        class_mode='categorical',\n",
+    "        shuffle=False,\n",
+    "        seed=seed,\n",
+    "        subset=\"validation\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Sample image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "./img_data/resized/Positive/3843713_landsat_7_rgb.tif\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.image.AxesImage at 0x7f91b4bdd890>"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "img = train_generator.filepaths[np.random.random_integers(low=0, high=train_generator.samples)]\n",
+    "print(img)\n",
+    "img = mpimg.imread(img)\n",
+    "plt.imshow(img)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### GPU configuration"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "physical_devices = tf.config.experimental.list_physical_devices('GPU') \n",
+    "for physical_device in physical_devices: \n",
+    "    tf.config.experimental.set_memory_growth(physical_device, True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "INFO:tensorflow:Using MirroredStrategy with devices ('/job:localhost/replica:0/task:0/device:GPU:0', '/job:localhost/replica:0/task:0/device:GPU:1', '/job:localhost/replica:0/task:0/device:GPU:2', '/job:localhost/replica:0/task:0/device:GPU:3', '/job:localhost/replica:0/task:0/device:GPU:4', '/job:localhost/replica:0/task:0/device:GPU:5', '/job:localhost/replica:0/task:0/device:GPU:6', '/job:localhost/replica:0/task:0/device:GPU:7')\n",
+      "Number of devices: 8\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Create a MirroredStrategy.\n",
+    "strategy = tf.distribute.MirroredStrategy()\n",
+    "print('Number of devices: {}'.format(strategy.num_replicas_in_sync))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Keras callbacks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:`period` argument is deprecated. Please use `save_freq` to specify the frequency in number of batches seen.\n",
+      "WARNING:tensorflow:`batch_size` is no longer needed in the `TensorBoard` Callback and will be ignored in TensorFlow 2.0.\n"
+     ]
+    }
+   ],
+   "source": [
+    "checkpoint = ModelCheckpoint('landslide_classifier.h5',\n",
+    "                             monitor='val_accuracy',\n",
+    "                             save_best_only=True,\n",
+    "                             verbose=1,\n",
+    "                             mode='auto',\n",
+    "                             save_weights_only=False,\n",
+    "                             period=1)\n",
+    "\n",
+    "#https://github.com/keras-team/keras/issues/3358\n",
+    "tensorboard = TensorBoard(log_dir=\"./logs-\"+dt.datetime.now().strftime(\"%m%d%Y%H%M%S\"),\n",
+    "                            histogram_freq=0,\n",
+    "                            batch_size=batch_size,\n",
+    "                            write_graph=False,\n",
+    "                            update_freq='epoch')\n",
+    "\n",
+    "def epoch_end(epoch, logs):\n",
+    "    message = \"End of epoch \"+str(epoch)+\". Learning rate: \"+str(K.eval(model.optimizer.lr))\n",
+    "    os.system('echo '+message)\n",
+    "\n",
+    "def epoch_begin(epoch, logs):\n",
+    "    print(\"Learning rate: \", K.eval(model.optimizer.lr))\n",
+    "    \n",
+    "def train_begin(logs):\n",
+    "    os.system(\"echo Beginning training\")\n",
+    "\n",
+    "earlystop = EarlyStopping(monitor='val_accuracy',\n",
+    "                          min_delta=.0001,\n",
+    "                          patience=20,\n",
+    "                          verbose=1,\n",
+    "                          mode='auto',\n",
+    "                          baseline=None,\n",
+    "                          restore_best_weights=True)\n",
+    "\n",
+    "reducelr = ReduceLROnPlateau(monitor='val_accuracy',\n",
+    "                             factor=np.sqrt(.1),\n",
+    "                             patience=5,\n",
+    "                             verbose=1,\n",
+    "                             mode='auto',\n",
+    "                             min_delta=.0001,\n",
+    "                             cooldown=0,\n",
+    "                             min_lr=0.0000001)\n",
+    "\n",
+    "lambdacb = LambdaCallback(on_epoch_begin=epoch_begin,\n",
+    "                          on_epoch_end=epoch_end,\n",
+    "                          on_batch_begin=None,\n",
+    "                          on_batch_end=None,\n",
+    "                          on_train_begin=train_begin,\n",
+    "                          on_train_end=None)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Define new top layers and compile model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "Model: \"model\"\n",
+      "__________________________________________________________________________________________________\n",
+      "Layer (type)                    Output Shape         Param #     Connected to                     \n",
+      "==================================================================================================\n",
+      "input_1 (InputLayer)            [(None, 224, 224, 3) 0                                            \n",
+      "__________________________________________________________________________________________________\n",
+      "Conv1_pad (ZeroPadding2D)       (None, 225, 225, 3)  0           input_1[0][0]                    \n",
+      "__________________________________________________________________________________________________\n",
+      "Conv1 (Conv2D)                  (None, 112, 112, 32) 864         Conv1_pad[0][0]                  \n",
+      "__________________________________________________________________________________________________\n",
+      "bn_Conv1 (BatchNormalization)   (None, 112, 112, 32) 128         Conv1[0][0]                      \n",
+      "__________________________________________________________________________________________________\n",
+      "Conv1_relu (ReLU)               (None, 112, 112, 32) 0           bn_Conv1[0][0]                   \n",
+      "__________________________________________________________________________________________________\n",
+      "expanded_conv_depthwise (Depthw (None, 112, 112, 32) 288         Conv1_relu[0][0]                 \n",
+      "__________________________________________________________________________________________________\n",
+      "expanded_conv_depthwise_BN (Bat (None, 112, 112, 32) 128         expanded_conv_depthwise[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "expanded_conv_depthwise_relu (R (None, 112, 112, 32) 0           expanded_conv_depthwise_BN[0][0] \n",
+      "__________________________________________________________________________________________________\n",
+      "expanded_conv_project (Conv2D)  (None, 112, 112, 16) 512         expanded_conv_depthwise_relu[0][0\n",
+      "__________________________________________________________________________________________________\n",
+      "expanded_conv_project_BN (Batch (None, 112, 112, 16) 64          expanded_conv_project[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_expand (Conv2D)         (None, 112, 112, 96) 1536        expanded_conv_project_BN[0][0]   \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_expand_BN (BatchNormali (None, 112, 112, 96) 384         block_1_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_expand_relu (ReLU)      (None, 112, 112, 96) 0           block_1_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_pad (ZeroPadding2D)     (None, 113, 113, 96) 0           block_1_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_depthwise (DepthwiseCon (None, 56, 56, 96)   864         block_1_pad[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_depthwise_BN (BatchNorm (None, 56, 56, 96)   384         block_1_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_depthwise_relu (ReLU)   (None, 56, 56, 96)   0           block_1_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_project (Conv2D)        (None, 56, 56, 24)   2304        block_1_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_project_BN (BatchNormal (None, 56, 56, 24)   96          block_1_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_expand (Conv2D)         (None, 56, 56, 144)  3456        block_1_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_expand_BN (BatchNormali (None, 56, 56, 144)  576         block_2_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_expand_relu (ReLU)      (None, 56, 56, 144)  0           block_2_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_depthwise (DepthwiseCon (None, 56, 56, 144)  1296        block_2_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_depthwise_BN (BatchNorm (None, 56, 56, 144)  576         block_2_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_depthwise_relu (ReLU)   (None, 56, 56, 144)  0           block_2_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_project (Conv2D)        (None, 56, 56, 24)   3456        block_2_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_project_BN (BatchNormal (None, 56, 56, 24)   96          block_2_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_add (Add)               (None, 56, 56, 24)   0           block_1_project_BN[0][0]         \n",
+      "                                                                 block_2_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_expand (Conv2D)         (None, 56, 56, 144)  3456        block_2_add[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_expand_BN (BatchNormali (None, 56, 56, 144)  576         block_3_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_expand_relu (ReLU)      (None, 56, 56, 144)  0           block_3_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_pad (ZeroPadding2D)     (None, 57, 57, 144)  0           block_3_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_depthwise (DepthwiseCon (None, 28, 28, 144)  1296        block_3_pad[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_depthwise_BN (BatchNorm (None, 28, 28, 144)  576         block_3_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_depthwise_relu (ReLU)   (None, 28, 28, 144)  0           block_3_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_project (Conv2D)        (None, 28, 28, 32)   4608        block_3_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_project_BN (BatchNormal (None, 28, 28, 32)   128         block_3_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_expand (Conv2D)         (None, 28, 28, 192)  6144        block_3_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_expand_BN (BatchNormali (None, 28, 28, 192)  768         block_4_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_expand_relu (ReLU)      (None, 28, 28, 192)  0           block_4_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_depthwise (DepthwiseCon (None, 28, 28, 192)  1728        block_4_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_depthwise_BN (BatchNorm (None, 28, 28, 192)  768         block_4_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_depthwise_relu (ReLU)   (None, 28, 28, 192)  0           block_4_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_project (Conv2D)        (None, 28, 28, 32)   6144        block_4_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_project_BN (BatchNormal (None, 28, 28, 32)   128         block_4_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_add (Add)               (None, 28, 28, 32)   0           block_3_project_BN[0][0]         \n",
+      "                                                                 block_4_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_expand (Conv2D)         (None, 28, 28, 192)  6144        block_4_add[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_expand_BN (BatchNormali (None, 28, 28, 192)  768         block_5_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_expand_relu (ReLU)      (None, 28, 28, 192)  0           block_5_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_depthwise (DepthwiseCon (None, 28, 28, 192)  1728        block_5_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_depthwise_BN (BatchNorm (None, 28, 28, 192)  768         block_5_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_depthwise_relu (ReLU)   (None, 28, 28, 192)  0           block_5_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_project (Conv2D)        (None, 28, 28, 32)   6144        block_5_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_project_BN (BatchNormal (None, 28, 28, 32)   128         block_5_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_add (Add)               (None, 28, 28, 32)   0           block_4_add[0][0]                \n",
+      "                                                                 block_5_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_expand (Conv2D)         (None, 28, 28, 192)  6144        block_5_add[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_expand_BN (BatchNormali (None, 28, 28, 192)  768         block_6_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_expand_relu (ReLU)      (None, 28, 28, 192)  0           block_6_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_pad (ZeroPadding2D)     (None, 29, 29, 192)  0           block_6_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_depthwise (DepthwiseCon (None, 14, 14, 192)  1728        block_6_pad[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_depthwise_BN (BatchNorm (None, 14, 14, 192)  768         block_6_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_depthwise_relu (ReLU)   (None, 14, 14, 192)  0           block_6_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_project (Conv2D)        (None, 14, 14, 64)   12288       block_6_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_project_BN (BatchNormal (None, 14, 14, 64)   256         block_6_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_expand (Conv2D)         (None, 14, 14, 384)  24576       block_6_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_expand_BN (BatchNormali (None, 14, 14, 384)  1536        block_7_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_expand_relu (ReLU)      (None, 14, 14, 384)  0           block_7_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_depthwise (DepthwiseCon (None, 14, 14, 384)  3456        block_7_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_depthwise_BN (BatchNorm (None, 14, 14, 384)  1536        block_7_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_depthwise_relu (ReLU)   (None, 14, 14, 384)  0           block_7_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_project (Conv2D)        (None, 14, 14, 64)   24576       block_7_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_project_BN (BatchNormal (None, 14, 14, 64)   256         block_7_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_add (Add)               (None, 14, 14, 64)   0           block_6_project_BN[0][0]         \n",
+      "                                                                 block_7_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_expand (Conv2D)         (None, 14, 14, 384)  24576       block_7_add[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_expand_BN (BatchNormali (None, 14, 14, 384)  1536        block_8_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_expand_relu (ReLU)      (None, 14, 14, 384)  0           block_8_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_depthwise (DepthwiseCon (None, 14, 14, 384)  3456        block_8_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_depthwise_BN (BatchNorm (None, 14, 14, 384)  1536        block_8_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_depthwise_relu (ReLU)   (None, 14, 14, 384)  0           block_8_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_project (Conv2D)        (None, 14, 14, 64)   24576       block_8_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_project_BN (BatchNormal (None, 14, 14, 64)   256         block_8_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_add (Add)               (None, 14, 14, 64)   0           block_7_add[0][0]                \n",
+      "                                                                 block_8_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_expand (Conv2D)         (None, 14, 14, 384)  24576       block_8_add[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_expand_BN (BatchNormali (None, 14, 14, 384)  1536        block_9_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_expand_relu (ReLU)      (None, 14, 14, 384)  0           block_9_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_depthwise (DepthwiseCon (None, 14, 14, 384)  3456        block_9_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_depthwise_BN (BatchNorm (None, 14, 14, 384)  1536        block_9_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_depthwise_relu (ReLU)   (None, 14, 14, 384)  0           block_9_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_project (Conv2D)        (None, 14, 14, 64)   24576       block_9_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_project_BN (BatchNormal (None, 14, 14, 64)   256         block_9_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_add (Add)               (None, 14, 14, 64)   0           block_8_add[0][0]                \n",
+      "                                                                 block_9_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_expand (Conv2D)        (None, 14, 14, 384)  24576       block_9_add[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_expand_BN (BatchNormal (None, 14, 14, 384)  1536        block_10_expand[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_expand_relu (ReLU)     (None, 14, 14, 384)  0           block_10_expand_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_depthwise (DepthwiseCo (None, 14, 14, 384)  3456        block_10_expand_relu[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_depthwise_BN (BatchNor (None, 14, 14, 384)  1536        block_10_depthwise[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_depthwise_relu (ReLU)  (None, 14, 14, 384)  0           block_10_depthwise_BN[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_project (Conv2D)       (None, 14, 14, 96)   36864       block_10_depthwise_relu[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_project_BN (BatchNorma (None, 14, 14, 96)   384         block_10_project[0][0]           \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_expand (Conv2D)        (None, 14, 14, 576)  55296       block_10_project_BN[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_expand_BN (BatchNormal (None, 14, 14, 576)  2304        block_11_expand[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_expand_relu (ReLU)     (None, 14, 14, 576)  0           block_11_expand_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_depthwise (DepthwiseCo (None, 14, 14, 576)  5184        block_11_expand_relu[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_depthwise_BN (BatchNor (None, 14, 14, 576)  2304        block_11_depthwise[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_depthwise_relu (ReLU)  (None, 14, 14, 576)  0           block_11_depthwise_BN[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_project (Conv2D)       (None, 14, 14, 96)   55296       block_11_depthwise_relu[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_project_BN (BatchNorma (None, 14, 14, 96)   384         block_11_project[0][0]           \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_add (Add)              (None, 14, 14, 96)   0           block_10_project_BN[0][0]        \n",
+      "                                                                 block_11_project_BN[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_expand (Conv2D)        (None, 14, 14, 576)  55296       block_11_add[0][0]               \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_expand_BN (BatchNormal (None, 14, 14, 576)  2304        block_12_expand[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_expand_relu (ReLU)     (None, 14, 14, 576)  0           block_12_expand_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_depthwise (DepthwiseCo (None, 14, 14, 576)  5184        block_12_expand_relu[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_depthwise_BN (BatchNor (None, 14, 14, 576)  2304        block_12_depthwise[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_depthwise_relu (ReLU)  (None, 14, 14, 576)  0           block_12_depthwise_BN[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_project (Conv2D)       (None, 14, 14, 96)   55296       block_12_depthwise_relu[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_project_BN (BatchNorma (None, 14, 14, 96)   384         block_12_project[0][0]           \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_add (Add)              (None, 14, 14, 96)   0           block_11_add[0][0]               \n",
+      "                                                                 block_12_project_BN[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_expand (Conv2D)        (None, 14, 14, 576)  55296       block_12_add[0][0]               \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_expand_BN (BatchNormal (None, 14, 14, 576)  2304        block_13_expand[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_expand_relu (ReLU)     (None, 14, 14, 576)  0           block_13_expand_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_pad (ZeroPadding2D)    (None, 15, 15, 576)  0           block_13_expand_relu[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_depthwise (DepthwiseCo (None, 7, 7, 576)    5184        block_13_pad[0][0]               \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_depthwise_BN (BatchNor (None, 7, 7, 576)    2304        block_13_depthwise[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_depthwise_relu (ReLU)  (None, 7, 7, 576)    0           block_13_depthwise_BN[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_project (Conv2D)       (None, 7, 7, 160)    92160       block_13_depthwise_relu[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_project_BN (BatchNorma (None, 7, 7, 160)    640         block_13_project[0][0]           \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_expand (Conv2D)        (None, 7, 7, 960)    153600      block_13_project_BN[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_expand_BN (BatchNormal (None, 7, 7, 960)    3840        block_14_expand[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_expand_relu (ReLU)     (None, 7, 7, 960)    0           block_14_expand_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_depthwise (DepthwiseCo (None, 7, 7, 960)    8640        block_14_expand_relu[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_depthwise_BN (BatchNor (None, 7, 7, 960)    3840        block_14_depthwise[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_depthwise_relu (ReLU)  (None, 7, 7, 960)    0           block_14_depthwise_BN[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_project (Conv2D)       (None, 7, 7, 160)    153600      block_14_depthwise_relu[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_project_BN (BatchNorma (None, 7, 7, 160)    640         block_14_project[0][0]           \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_add (Add)              (None, 7, 7, 160)    0           block_13_project_BN[0][0]        \n",
+      "                                                                 block_14_project_BN[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_expand (Conv2D)        (None, 7, 7, 960)    153600      block_14_add[0][0]               \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_expand_BN (BatchNormal (None, 7, 7, 960)    3840        block_15_expand[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_expand_relu (ReLU)     (None, 7, 7, 960)    0           block_15_expand_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_depthwise (DepthwiseCo (None, 7, 7, 960)    8640        block_15_expand_relu[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_depthwise_BN (BatchNor (None, 7, 7, 960)    3840        block_15_depthwise[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_depthwise_relu (ReLU)  (None, 7, 7, 960)    0           block_15_depthwise_BN[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_project (Conv2D)       (None, 7, 7, 160)    153600      block_15_depthwise_relu[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_project_BN (BatchNorma (None, 7, 7, 160)    640         block_15_project[0][0]           \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_add (Add)              (None, 7, 7, 160)    0           block_14_add[0][0]               \n",
+      "                                                                 block_15_project_BN[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_expand (Conv2D)        (None, 7, 7, 960)    153600      block_15_add[0][0]               \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_expand_BN (BatchNormal (None, 7, 7, 960)    3840        block_16_expand[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_expand_relu (ReLU)     (None, 7, 7, 960)    0           block_16_expand_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_depthwise (DepthwiseCo (None, 7, 7, 960)    8640        block_16_expand_relu[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_depthwise_BN (BatchNor (None, 7, 7, 960)    3840        block_16_depthwise[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_depthwise_relu (ReLU)  (None, 7, 7, 960)    0           block_16_depthwise_BN[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_project (Conv2D)       (None, 7, 7, 320)    307200      block_16_depthwise_relu[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_project_BN (BatchNorma (None, 7, 7, 320)    1280        block_16_project[0][0]           \n",
+      "__________________________________________________________________________________________________\n",
+      "Conv_1 (Conv2D)                 (None, 7, 7, 1280)   409600      block_16_project_BN[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "Conv_1_bn (BatchNormalization)  (None, 7, 7, 1280)   5120        Conv_1[0][0]                     \n",
+      "__________________________________________________________________________________________________\n",
+      "out_relu (ReLU)                 (None, 7, 7, 1280)   0           Conv_1_bn[0][0]                  \n",
+      "__________________________________________________________________________________________________\n",
+      "global_average_pooling2d (Globa (None, 1280)         0           out_relu[0][0]                   \n",
+      "__________________________________________________________________________________________________\n",
+      "batch_normalization (BatchNorma (None, 1280)         5120        global_average_pooling2d[0][0]   \n",
+      "__________________________________________________________________________________________________\n",
+      "dense (Dense)                   (None, 1280)         1639680     batch_normalization[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "batch_normalization_1 (BatchNor (None, 1280)         5120        dense[0][0]                      \n",
+      "__________________________________________________________________________________________________\n",
+      "dense_1 (Dense)                 (None, 2)            2562        batch_normalization_1[0][0]      \n",
+      "==================================================================================================\n",
+      "Total params: 3,910,466\n",
+      "Trainable params: 3,871,234\n",
+      "Non-trainable params: 39,232\n",
+      "__________________________________________________________________________________________________\n"
+     ]
+    }
+   ],
+   "source": [
+    "with strategy.scope():\n",
+    "    base_model = MobileNetV2(include_top=False, weights='imagenet', input_shape=(targetx, targety, 3))\n",
+    "    # base_model = EfficientNetB0(include_top=False, weights='imagenet', input_shape=(targetx, targety, 3))\n",
+    "\n",
+    "    x = base_model.output\n",
+    "    x = GlobalAveragePooling2D()(x)\n",
+    "    # x = Dropout(rate = .2)(x)\n",
+    "    x = BatchNormalization()(x)\n",
+    "    x = Dense(1280, activation='relu',  kernel_initializer=glorot_uniform(seed), bias_initializer='zeros')(x)\n",
+    "    # x = Dropout(rate = .2)(x)\n",
+    "    x = BatchNormalization()(x)\n",
+    "    predictions = Dense(classes, activation='softmax', kernel_initializer='random_uniform', bias_initializer='zeros')(x)\n",
+    "\n",
+    "    model = Model(inputs=base_model.input, outputs=predictions)\n",
+    "\n",
+    "    optimizer = Adam(lr=learning_rate)\n",
+    "    # optimizer = RMSprop(lr=learning_rate)\n",
+    "\n",
+    "    loss = \"categorical_crossentropy\"\n",
+    "    # loss = \"kullback_leibler_divergence\"\n",
+    "\n",
+    "    for layer in model.layers:\n",
+    "        layer.trainable = True\n",
+    "    # for layer in model.layers[-2:]:\n",
+    "    #     layer.trainable = True\n",
+    "\n",
+    "    model.compile(optimizer=optimizer,\n",
+    "                  loss=loss,\n",
+    "                  metrics=[\"accuracy\"])\n",
+    "\n",
+    "    model.summary()\n",
+    "    # for i, layer in enumerate(model.layers):\n",
+    "    #     print(i, layer.name, layer.trainable)"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "with strategy.scope():\n",
+    "    base_model = MobileNetV2(include_top=False, weights='imagenet', input_shape=(targetx, targety, 3))\n",
+    "\n",
+    "    x = base_model.output\n",
+    "    x = GlobalAveragePooling2D()(x)\n",
+    "    # x = Dropout(rate = .2)(x)\n",
+    "    x = BatchNormalization()(x)\n",
+    "    x = Dense(1280, activation='relu',  kernel_initializer=glorot_uniform(seed), bias_initializer='zeros')(x)\n",
+    "    # x = Dropout(rate = .2)(x)\n",
+    "    x = BatchNormalization()(x)\n",
+    "    predictions = Dense(classes, activation='softmax', kernel_initializer='random_uniform', bias_initializer='zeros')(x)\n",
+    "\n",
+    "    model = Model(inputs=base_model.input, outputs=predictions)\n",
+    "\n",
+    "    optimizer = Adam(lr=learning_rate)\n",
+    "    # optimizer = RMSprop(lr=learning_rate)\n",
+    "\n",
+    "    loss = \"categorical_crossentropy\"\n",
+    "    # loss = \"kullback_leibler_divergence\"\n",
+    "\n",
+    "    for layer in model.layers:\n",
+    "        layer.trainable = True\n",
+    "    # for layer in model.layers[-2:]:\n",
+    "    #     layer.trainable = True\n",
+    "\n",
+    "    model.compile(optimizer=optimizer,\n",
+    "                  loss=loss,\n",
+    "                  metrics=[\"accuracy\"])\n",
+    "\n",
+    "    model.summary()\n",
+    "    # for i, layer in enumerate(model.layers):\n",
+    "    #     print(i, layer.name, layer.trainable)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Fit model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From <timed exec>:6: Model.fit_generator (from tensorflow.python.keras.engine.training) is deprecated and will be removed in a future version.\n",
+      "Instructions for updating:\n",
+      "Please use Model.fit, which supports generators.\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 1/250\n",
+      "INFO:tensorflow:batch_all_reduce: 164 all-reduces with algorithm = nccl, num_packs = 1\n",
+      "INFO:tensorflow:batch_all_reduce: 164 all-reduces with algorithm = nccl, num_packs = 1\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.5027 - loss: 0.8569\n",
+      "Epoch 00001: val_accuracy improved from -inf to 0.50398, saving model to landslide_classifier.h5\n",
+      "14/14 [==============================] - 49s 3s/step - accuracy: 0.5027 - loss: 0.8569 - val_accuracy: 0.5040 - val_loss: 0.7772 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 2/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.5638 - loss: 0.7553\n",
+      "Epoch 00002: val_accuracy improved from 0.50398 to 0.53785, saving model to landslide_classifier.h5\n",
+      "14/14 [==============================] - 38s 3s/step - accuracy: 0.5638 - loss: 0.7553 - val_accuracy: 0.5378 - val_loss: 0.7356 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 3/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.6149 - loss: 0.6962\n",
+      "Epoch 00003: val_accuracy did not improve from 0.53785\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.6149 - loss: 0.6962 - val_accuracy: 0.5359 - val_loss: 0.7441 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 4/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.6566 - loss: 0.6314\n",
+      "Epoch 00004: val_accuracy improved from 0.53785 to 0.55578, saving model to landslide_classifier.h5\n",
+      "14/14 [==============================] - 38s 3s/step - accuracy: 0.6566 - loss: 0.6314 - val_accuracy: 0.5558 - val_loss: 0.7152 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 5/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.6526 - loss: 0.6359\n",
+      "Epoch 00005: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.6526 - loss: 0.6359 - val_accuracy: 0.5398 - val_loss: 0.7142 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 6/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.6774 - loss: 0.6009\n",
+      "Epoch 00006: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.6774 - loss: 0.6009 - val_accuracy: 0.5339 - val_loss: 0.7319 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 7/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.6804 - loss: 0.5988\n",
+      "Epoch 00007: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.6804 - loss: 0.5988 - val_accuracy: 0.5378 - val_loss: 0.7520 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 8/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7017 - loss: 0.5779\n",
+      "Epoch 00008: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7017 - loss: 0.5779 - val_accuracy: 0.5120 - val_loss: 0.7925 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 9/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7112 - loss: 0.5569\n",
+      "Epoch 00009: ReduceLROnPlateau reducing learning rate to 3.1622775802825264e-05.\n",
+      "\n",
+      "Epoch 00009: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7112 - loss: 0.5569 - val_accuracy: 0.5100 - val_loss: 0.8326 - lr: 1.0000e-04\n",
+      "Learning rate:  3.1622774e-05\n",
+      "Epoch 10/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7270 - loss: 0.5282\n",
+      "Epoch 00010: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7270 - loss: 0.5282 - val_accuracy: 0.5159 - val_loss: 0.8136 - lr: 3.1623e-05\n",
+      "Learning rate:  3.1622774e-05\n",
+      "Epoch 11/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7236 - loss: 0.5335\n",
+      "Epoch 00011: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7236 - loss: 0.5335 - val_accuracy: 0.5020 - val_loss: 0.8296 - lr: 3.1623e-05\n",
+      "Learning rate:  3.1622774e-05\n",
+      "Epoch 12/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7280 - loss: 0.5409\n",
+      "Epoch 00012: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7280 - loss: 0.5409 - val_accuracy: 0.5299 - val_loss: 0.8433 - lr: 3.1623e-05\n",
+      "Learning rate:  3.1622774e-05\n",
+      "Epoch 13/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7504 - loss: 0.5148\n",
+      "Epoch 00013: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7504 - loss: 0.5148 - val_accuracy: 0.5319 - val_loss: 0.8690 - lr: 3.1623e-05\n",
+      "Learning rate:  3.1622774e-05\n",
+      "Epoch 14/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7449 - loss: 0.5103\n",
+      "Epoch 00014: ReduceLROnPlateau reducing learning rate to 9.999999259090306e-06.\n",
+      "\n",
+      "Epoch 00014: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7449 - loss: 0.5103 - val_accuracy: 0.5359 - val_loss: 0.9017 - lr: 3.1623e-05\n",
+      "Learning rate:  9.999999e-06\n",
+      "Epoch 15/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7672 - loss: 0.4831\n",
+      "Epoch 00015: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7672 - loss: 0.4831 - val_accuracy: 0.5279 - val_loss: 0.9036 - lr: 1.0000e-05\n",
+      "Learning rate:  9.999999e-06\n",
+      "Epoch 16/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7538 - loss: 0.4952\n",
+      "Epoch 00016: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7538 - loss: 0.4952 - val_accuracy: 0.5120 - val_loss: 0.9364 - lr: 1.0000e-05\n",
+      "Learning rate:  9.999999e-06\n",
+      "Epoch 17/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7623 - loss: 0.4870\n",
+      "Epoch 00017: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7623 - loss: 0.4870 - val_accuracy: 0.5378 - val_loss: 0.9247 - lr: 1.0000e-05\n",
+      "Learning rate:  9.999999e-06\n",
+      "Epoch 18/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7350 - loss: 0.5125\n",
+      "Epoch 00018: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7350 - loss: 0.5125 - val_accuracy: 0.5418 - val_loss: 0.9386 - lr: 1.0000e-05\n",
+      "Learning rate:  9.999999e-06\n",
+      "Epoch 19/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7717 - loss: 0.4804\n",
+      "Epoch 00019: ReduceLROnPlateau reducing learning rate to 3.162277292675049e-06.\n",
+      "\n",
+      "Epoch 00019: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7717 - loss: 0.4804 - val_accuracy: 0.5339 - val_loss: 0.9490 - lr: 1.0000e-05\n",
+      "Learning rate:  3.1622774e-06\n",
+      "Epoch 20/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7772 - loss: 0.4741\n",
+      "Epoch 00020: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7772 - loss: 0.4741 - val_accuracy: 0.5219 - val_loss: 0.9684 - lr: 3.1623e-06\n",
+      "Learning rate:  3.1622774e-06\n",
+      "Epoch 21/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7628 - loss: 0.4934"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "\n",
+    "params = model.fit_generator(generator=train_generator, \n",
+    "                                steps_per_epoch=len(train_generator), \n",
+    "                                validation_data=test_generator, \n",
+    "                                validation_steps=len(test_generator),\n",
+    "                                epochs=epochs,\n",
+    "                                callbacks=[reducelr, earlystop, lambdacb, tensorboard, checkpoint])"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "%%time\n",
+    "params = model.fit(generator=train_generator, \n",
+    "                                steps_per_epoch=len(train_generator), \n",
+    "                                validation_data=test_generator, \n",
+    "                                validation_steps=len(test_generator),\n",
+    "                                epochs=epochs,\n",
+    "                                callbacks=[reducelr, earlystop, lambdacb, tensorboard, checkpoint])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Training and test loss/accuracy graphs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# plt.subplot(2, 1, 1)\n",
+    "plt.title('Training and test accuracy')\n",
+    "plt.plot(params.epoch, params.history['accuracy'], label='Training accuracy')\n",
+    "plt.plot(params.epoch, params.history['val_accuracy'], label='Test accuracy')\n",
+    "plt.legend()\n",
+    "plt.show()\n",
+    "\n",
+    "# plt.subplot(2, 1, 2)\n",
+    "plt.title('Training and test loss')\n",
+    "plt.plot(params.epoch, params.history['loss'], label='Training loss')\n",
+    "plt.plot(params.epoch, params.history['val_loss'], label='Test loss')\n",
+    "plt.legend()\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Sample prediction"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Randomly test an image from the test set\n",
+    "\n",
+    "# model.load_weights('dog_breed_classifier.h5')\n",
+    "\n",
+    "imageno=np.random.random_integers(low=0, high=test_generator.samples)\n",
+    "print('predict with test number: ', imageno)\n",
+    "\n",
+    "name = test_generator.filepaths[imageno]\n",
+    "print(name)\n",
+    "plt.imshow(mpimg.imread(name))\n",
+    "\n",
+    "img = Image.open(test_generator.filepaths[imageno]).resize((targetx, targety))\n",
+    "probabilities = model.predict(preprocess_input(np.expand_dims(img, axis=0)))\n",
+    "breed_list = tuple(zip(test_generator.class_indices.values(), test_generator.class_indices.keys()))\n",
+    "\n",
+    "for i in probabilities[0].argsort()[-5:][::-1]: \n",
+    "    print(probabilities[0][i], \"  :  \" , breed_list[i])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Sample for paper test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# path for landslide \n",
+    "#./data/reized/WithLandslide/25_94_Large_cropped_6.TIF\n",
+    "# ./data/reized/WithLandslide/44_-123_Large_cropped_4.TIF\n",
+    "# ./imgtest/27.770733_85.868467_VERY_LARGE_cropped_LC08_L1TP_141041_20130915_20170502_01_T1.TIF\n",
+    "# ./imgtest/27.770733_85.868467_VERY_LARGE_cropped_LC08_L1TP_141041_20140918_20170419_01_T1.TIF\n",
+    "img_test = Image.open(test_dir + \"27.770733_85.868467_VERY_LARGE_cropped_LC08_L1TP_141041_20140918_20170419_01_T1.TIF\").resize((targetx, targety))\n",
+    "plt.imshow(img_test,origin='lower')\n",
+    "probabilities = model.predict(preprocess_input(np.expand_dims(img, axis=0)))\n",
+    "breed_list = tuple(zip(test_generator.class_indices.values(), test_generator.class_indices.keys()))\n",
+    "\n",
+    "for i in probabilities[0].argsort()[-5:][::-1]: \n",
+    "    print(probabilities[0][i], \"  :  \" , breed_list[i])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Classification report"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_generator.reset()\n",
+    "predictions = model.predict_generator(test_generator, steps=len(test_generator))\n",
+    "y = np.argmax(predictions, axis=1)\n",
+    "\n",
+    "print('Classification Report')\n",
+    "cr = classification_report(y_true=test_generator.classes, y_pred=y, target_names=test_generator.class_indices)\n",
+    "print(cr)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Confusion matrix"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print('Confusion Matrix')\n",
+    "cm = confusion_matrix(test_generator.classes, y)\n",
+    "df = pd.DataFrame(cm, columns=test_generator.class_indices)\n",
+    "plt.figure(figsize=(80,80))\n",
+    "sn.heatmap(df, annot=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Reference: \n",
+    "## Transfer learning with Keras and MobileNet V2\n",
+    "#### https://www.kaggle.com/devang/transfer-learning-with-keras-and-mobilenet-v2/"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "viplab-gpu",
+   "language": "python",
+   "name": "viplab-gpu"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/train-mobilenetv2.ipynb b/train-mobilenetv2.ipynb
new file mode 100644
index 0000000..142dc51
--- /dev/null
+++ b/train-mobilenetv2.ipynb
@@ -0,0 +1,1375 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Training + Testing Landslide Prediction"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Created: <b>Trong-An Bui</b> <br>\n",
+    "Organization: <b>ViP Lab - National Chi Nan University, Taiwan</b> <br/>\n",
+    "Email: trongan93@gmail.com <br/>\n",
+    "Project: <b>AI Cube Satellite</b> <br/>\n",
+    "Advisor: <b>Prof. Pei-Jun Lee</b>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "py 3.7.7\n",
+      "tf 2.2.0\n",
+      "keras 2.3.0-tf\n",
+      "mem 128555.12109375\n",
+      "cpu 40\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "['Fri Sep  4 02:44:42 2020       ',\n",
+       " '+-----------------------------------------------------------------------------+',\n",
+       " '| NVIDIA-SMI 440.100      Driver Version: 440.100      CUDA Version: 10.2     |',\n",
+       " '|-------------------------------+----------------------+----------------------+',\n",
+       " '| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |',\n",
+       " '| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |',\n",
+       " '|===============================+======================+======================|',\n",
+       " '|   0  Quadro RTX 4000     Off  | 00000000:1D:00.0 Off |                  N/A |',\n",
+       " '| 30%   35C    P8     8W / 125W |      0MiB /  7982MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '|   1  Quadro RTX 4000     Off  | 00000000:1E:00.0 Off |                  N/A |',\n",
+       " '| 30%   33C    P8     6W / 125W |      0MiB /  7982MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '|   2  Quadro RTX 4000     Off  | 00000000:1F:00.0 Off |                  N/A |',\n",
+       " '| 30%   31C    P8     4W / 125W |      0MiB /  7982MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '|   3  Quadro RTX 4000     Off  | 00000000:20:00.0 Off |                  N/A |',\n",
+       " '| 30%   33C    P8     9W / 125W |      0MiB /  7982MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '|   4  GeForce GTX 108...  Off  | 00000000:21:00.0 Off |                  N/A |',\n",
+       " '| 25%   32C    P8     8W / 250W |      0MiB / 11178MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '|   5  GeForce GTX 108...  Off  | 00000000:22:00.0 Off |                  N/A |',\n",
+       " '| 20%   24C    P8     9W / 250W |      0MiB / 11178MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '|   6  GeForce GTX 108...  Off  | 00000000:23:00.0 Off |                  N/A |',\n",
+       " '| 20%   32C    P8     9W / 250W |      0MiB / 11178MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '|   7  GeForce GTX 108...  Off  | 00000000:24:00.0 Off |                  N/A |',\n",
+       " '| 20%   29C    P8     8W / 250W |      0MiB / 11178MiB |      0%      Default |',\n",
+       " '+-------------------------------+----------------------+----------------------+',\n",
+       " '                                                                               ',\n",
+       " '+-----------------------------------------------------------------------------+',\n",
+       " '| Processes:                                                       GPU Memory |',\n",
+       " '|  GPU       PID   Type   Process name                             Usage      |',\n",
+       " '|=============================================================================|',\n",
+       " '|  No running processes found                                                 |',\n",
+       " '+-----------------------------------------------------------------------------+']"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import os\n",
+    "#os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"\"\n",
+    "#os.environ[\"AUTOGRAPH_VERBOSITY\"] = \"10\"\n",
+    "os.environ[\"TF_FORCE_GPU_ALLOW_GROWTH\"] = \"true\"\n",
+    "\n",
+    "from platform import python_version\n",
+    "import warnings\n",
+    "import time\n",
+    "import datetime as dt\n",
+    "from sklearn.metrics import classification_report, confusion_matrix\n",
+    "import multiprocessing as mp\n",
+    "import shutil\n",
+    "from imutils import paths\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "import matplotlib.image as mpimg\n",
+    "\n",
+    "import tensorflow as tf\n",
+    "from tensorflow.keras import backend as K\n",
+    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
+    "from tensorflow.keras.applications.mobilenet_v2 import MobileNetV2, preprocess_input, decode_predictions\n",
+    "from tensorflow.keras.models import *\n",
+    "from tensorflow.keras.layers import *\n",
+    "from tensorflow.keras.optimizers import *\n",
+    "from tensorflow.keras.utils import *\n",
+    "from tensorflow.keras.callbacks import *\n",
+    "from tensorflow.keras.initializers import *\n",
+    "\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import seaborn as sn\n",
+    "\n",
+    "from PIL import Image\n",
+    "import xml.etree.ElementTree as ET\n",
+    "import psutil\n",
+    "import random\n",
+    "\n",
+    "warnings.filterwarnings(\"ignore\")\n",
+    "%matplotlib inline\n",
+    "\n",
+    "print(\"py\", python_version())\n",
+    "print(\"tf\", tf.__version__)\n",
+    "print(\"keras\", tf.keras.__version__)\n",
+    "mem = psutil.virtual_memory()\n",
+    "print(\"mem\", mem.total/1024/1024)\n",
+    "cpu = mp.cpu_count()\n",
+    "print(\"cpu\", cpu)\n",
+    "\n",
+    "%system nvidia-smi\n",
+    "#%system rocm-smi"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Variables"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "epochs = 250\n",
+    "batch_size = 150\n",
+    "testsplit = .2\n",
+    "targetx = 224\n",
+    "targety = 224\n",
+    "learning_rate = 0.0001\n",
+    "classes = 2\n",
+    "seed = random.randint(1, 1000)\n",
+    "\n",
+    "data_dir = \"../LandslideDataset/\"\n",
+    "resized_dir = \"./img_data/resized/\"\n",
+    "test_dir = \"./img_data/test/\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Crop images using provided annotations"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "%system rm -rf $resized_dir\n",
+    "%system mkdir $resized_dir\n",
+    "\n",
+    "\n",
+    "def crop_and_save_img(img_path, new_dir_path, original_ext_filter = 0):\n",
+    "#     print('trongan93:', new_dir_path)\n",
+    "    image = Image.open(img_path)\n",
+    "    image = image.resize((targetx,targety))\n",
+    "    image.save(new_dir_path)\n",
+    "\n",
+    "def resize_images(ext = 0):\n",
+    "    imgPaths = sorted(list(paths.list_images(data_dir)))\n",
+    "#     print('images len: ', len(imgPaths))\n",
+    "    \n",
+    "    labels_dir = os.listdir(data_dir)\n",
+    "    for label_dir in labels_dir:\n",
+    "        cropper_label_dir = resized_dir+label_dir\n",
+    "        if not os.path.exists(cropper_label_dir):\n",
+    "            os.makedirs(cropper_label_dir)\n",
+    "            print(\"sucessfull make dir for label: \", cropper_label_dir)\n",
+    "    \n",
+    "    \n",
+    "    total_images = 0\n",
+    "\n",
+    "    for imgPath in imgPaths:\n",
+    "#         print(imgPath)\n",
+    "        img_name_info = imgPath.split(os.path.sep)\n",
+    "        imgLabel = img_name_info[2]\n",
+    "#         print('img label: ', imgLabel)\n",
+    "        imgName = img_name_info[3]\n",
+    "#         print('img name: ', imgName)\n",
+    "        file_ext = os.path.splitext(imgName)[1]\n",
+    "#         print('img ext: ', file_ext)\n",
+    "        \n",
+    "        new_path = resized_dir + imgLabel + '/' + imgName\n",
+    "#         print(new_path)\n",
+    "        if ext == 0:\n",
+    "            crop_and_save_img(imgPath,new_path, original_ext_filter = 0)\n",
+    "        elif ext == 1:\n",
+    "            # TIF file\n",
+    "            if file_ext == '.TIF':\n",
+    "                crop_and_save_img(imgPath,new_path, original_ext_filter = 0)\n",
+    "            else:\n",
+    "                break\n",
+    "        elif ext == 2:\n",
+    "            # TIF file\n",
+    "            if file_ext == '.RAW':\n",
+    "                crop_and_save_img(imgPath,new_path, original_ext_filter = 0)\n",
+    "            else:\n",
+    "                break\n",
+    "                \n",
+    "        total_images += 1\n",
+    "        \n",
+    "#         annotations_dir_list = os.listdir(annotations_dir + breed)\n",
+    "#         img_list = [data_dir + breed + '/' + i for i in dir_list]\n",
+    "#         os.makedirs(cropped_dir + breed)\n",
+    "\n",
+    "#         for file in img_list:\n",
+    "#             annotation_path = annotations_dir + breed + '/' + os.path.basename(file[:-4])\n",
+    "#             newpath = cropped_dir + breed + '/' + os.path.basename(file)\n",
+    "#             save_cropped_img(file, annotation_path, newpath)\n",
+    "#             total_images += 1\n",
+    "    \n",
+    "    print(\"total images resized\", total_images)\n",
+    "\n",
+    "resize_images()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Keras image data readers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Found 2015 images belonging to 2 classes.\n",
+      "Found 502 images belonging to 2 classes.\n"
+     ]
+    }
+   ],
+   "source": [
+    "datagen = ImageDataGenerator(\n",
+    "        shear_range=0.1,\n",
+    "        zoom_range=0.1,\n",
+    "        brightness_range=[0.9,1.1],\n",
+    "        horizontal_flip=True,\n",
+    "        validation_split=testsplit,\n",
+    "        preprocessing_function=preprocess_input\n",
+    ")\n",
+    "\n",
+    "train_generator = datagen.flow_from_directory(\n",
+    "        resized_dir,\n",
+    "        target_size=(targetx, targety),\n",
+    "        batch_size=batch_size,\n",
+    "        class_mode='categorical',\n",
+    "        shuffle=True,\n",
+    "        seed=seed,\n",
+    "        subset=\"training\"\n",
+    ")\n",
+    "\n",
+    "test_generator = datagen.flow_from_directory(\n",
+    "        resized_dir,\n",
+    "        target_size=(targetx, targety),\n",
+    "        batch_size=batch_size,\n",
+    "        class_mode='categorical',\n",
+    "        shuffle=False,\n",
+    "        seed=seed,\n",
+    "        subset=\"validation\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Sample image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "./img_data/resized/Positive/3843713_landsat_7_rgb.tif\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.image.AxesImage at 0x7f91b4bdd890>"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "img = train_generator.filepaths[np.random.random_integers(low=0, high=train_generator.samples)]\n",
+    "print(img)\n",
+    "img = mpimg.imread(img)\n",
+    "plt.imshow(img)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### GPU configuration"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "physical_devices = tf.config.experimental.list_physical_devices('GPU') \n",
+    "for physical_device in physical_devices: \n",
+    "    tf.config.experimental.set_memory_growth(physical_device, True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "INFO:tensorflow:Using MirroredStrategy with devices ('/job:localhost/replica:0/task:0/device:GPU:0', '/job:localhost/replica:0/task:0/device:GPU:1', '/job:localhost/replica:0/task:0/device:GPU:2', '/job:localhost/replica:0/task:0/device:GPU:3', '/job:localhost/replica:0/task:0/device:GPU:4', '/job:localhost/replica:0/task:0/device:GPU:5', '/job:localhost/replica:0/task:0/device:GPU:6', '/job:localhost/replica:0/task:0/device:GPU:7')\n",
+      "Number of devices: 8\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Create a MirroredStrategy.\n",
+    "strategy = tf.distribute.MirroredStrategy()\n",
+    "print('Number of devices: {}'.format(strategy.num_replicas_in_sync))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Keras callbacks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:`period` argument is deprecated. Please use `save_freq` to specify the frequency in number of batches seen.\n",
+      "WARNING:tensorflow:`batch_size` is no longer needed in the `TensorBoard` Callback and will be ignored in TensorFlow 2.0.\n"
+     ]
+    }
+   ],
+   "source": [
+    "checkpoint = ModelCheckpoint('landslide_classifier.h5',\n",
+    "                             monitor='val_accuracy',\n",
+    "                             save_best_only=True,\n",
+    "                             verbose=1,\n",
+    "                             mode='auto',\n",
+    "                             save_weights_only=False,\n",
+    "                             period=1)\n",
+    "\n",
+    "#https://github.com/keras-team/keras/issues/3358\n",
+    "tensorboard = TensorBoard(log_dir=\"./logs-\"+dt.datetime.now().strftime(\"%m%d%Y%H%M%S\"),\n",
+    "                            histogram_freq=0,\n",
+    "                            batch_size=batch_size,\n",
+    "                            write_graph=False,\n",
+    "                            update_freq='epoch')\n",
+    "\n",
+    "def epoch_end(epoch, logs):\n",
+    "    message = \"End of epoch \"+str(epoch)+\". Learning rate: \"+str(K.eval(model.optimizer.lr))\n",
+    "    os.system('echo '+message)\n",
+    "\n",
+    "def epoch_begin(epoch, logs):\n",
+    "    print(\"Learning rate: \", K.eval(model.optimizer.lr))\n",
+    "    \n",
+    "def train_begin(logs):\n",
+    "    os.system(\"echo Beginning training\")\n",
+    "\n",
+    "earlystop = EarlyStopping(monitor='val_accuracy',\n",
+    "                          min_delta=.0001,\n",
+    "                          patience=20,\n",
+    "                          verbose=1,\n",
+    "                          mode='auto',\n",
+    "                          baseline=None,\n",
+    "                          restore_best_weights=True)\n",
+    "\n",
+    "reducelr = ReduceLROnPlateau(monitor='val_accuracy',\n",
+    "                             factor=np.sqrt(.1),\n",
+    "                             patience=5,\n",
+    "                             verbose=1,\n",
+    "                             mode='auto',\n",
+    "                             min_delta=.0001,\n",
+    "                             cooldown=0,\n",
+    "                             min_lr=0.0000001)\n",
+    "\n",
+    "lambdacb = LambdaCallback(on_epoch_begin=epoch_begin,\n",
+    "                          on_epoch_end=epoch_end,\n",
+    "                          on_batch_begin=None,\n",
+    "                          on_batch_end=None,\n",
+    "                          on_train_begin=train_begin,\n",
+    "                          on_train_end=None)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Define new top layers and compile model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).\n",
+      "Model: \"model\"\n",
+      "__________________________________________________________________________________________________\n",
+      "Layer (type)                    Output Shape         Param #     Connected to                     \n",
+      "==================================================================================================\n",
+      "input_1 (InputLayer)            [(None, 224, 224, 3) 0                                            \n",
+      "__________________________________________________________________________________________________\n",
+      "Conv1_pad (ZeroPadding2D)       (None, 225, 225, 3)  0           input_1[0][0]                    \n",
+      "__________________________________________________________________________________________________\n",
+      "Conv1 (Conv2D)                  (None, 112, 112, 32) 864         Conv1_pad[0][0]                  \n",
+      "__________________________________________________________________________________________________\n",
+      "bn_Conv1 (BatchNormalization)   (None, 112, 112, 32) 128         Conv1[0][0]                      \n",
+      "__________________________________________________________________________________________________\n",
+      "Conv1_relu (ReLU)               (None, 112, 112, 32) 0           bn_Conv1[0][0]                   \n",
+      "__________________________________________________________________________________________________\n",
+      "expanded_conv_depthwise (Depthw (None, 112, 112, 32) 288         Conv1_relu[0][0]                 \n",
+      "__________________________________________________________________________________________________\n",
+      "expanded_conv_depthwise_BN (Bat (None, 112, 112, 32) 128         expanded_conv_depthwise[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "expanded_conv_depthwise_relu (R (None, 112, 112, 32) 0           expanded_conv_depthwise_BN[0][0] \n",
+      "__________________________________________________________________________________________________\n",
+      "expanded_conv_project (Conv2D)  (None, 112, 112, 16) 512         expanded_conv_depthwise_relu[0][0\n",
+      "__________________________________________________________________________________________________\n",
+      "expanded_conv_project_BN (Batch (None, 112, 112, 16) 64          expanded_conv_project[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_expand (Conv2D)         (None, 112, 112, 96) 1536        expanded_conv_project_BN[0][0]   \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_expand_BN (BatchNormali (None, 112, 112, 96) 384         block_1_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_expand_relu (ReLU)      (None, 112, 112, 96) 0           block_1_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_pad (ZeroPadding2D)     (None, 113, 113, 96) 0           block_1_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_depthwise (DepthwiseCon (None, 56, 56, 96)   864         block_1_pad[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_depthwise_BN (BatchNorm (None, 56, 56, 96)   384         block_1_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_depthwise_relu (ReLU)   (None, 56, 56, 96)   0           block_1_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_project (Conv2D)        (None, 56, 56, 24)   2304        block_1_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_1_project_BN (BatchNormal (None, 56, 56, 24)   96          block_1_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_expand (Conv2D)         (None, 56, 56, 144)  3456        block_1_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_expand_BN (BatchNormali (None, 56, 56, 144)  576         block_2_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_expand_relu (ReLU)      (None, 56, 56, 144)  0           block_2_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_depthwise (DepthwiseCon (None, 56, 56, 144)  1296        block_2_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_depthwise_BN (BatchNorm (None, 56, 56, 144)  576         block_2_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_depthwise_relu (ReLU)   (None, 56, 56, 144)  0           block_2_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_project (Conv2D)        (None, 56, 56, 24)   3456        block_2_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_project_BN (BatchNormal (None, 56, 56, 24)   96          block_2_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_2_add (Add)               (None, 56, 56, 24)   0           block_1_project_BN[0][0]         \n",
+      "                                                                 block_2_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_expand (Conv2D)         (None, 56, 56, 144)  3456        block_2_add[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_expand_BN (BatchNormali (None, 56, 56, 144)  576         block_3_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_expand_relu (ReLU)      (None, 56, 56, 144)  0           block_3_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_pad (ZeroPadding2D)     (None, 57, 57, 144)  0           block_3_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_depthwise (DepthwiseCon (None, 28, 28, 144)  1296        block_3_pad[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_depthwise_BN (BatchNorm (None, 28, 28, 144)  576         block_3_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_depthwise_relu (ReLU)   (None, 28, 28, 144)  0           block_3_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_project (Conv2D)        (None, 28, 28, 32)   4608        block_3_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_3_project_BN (BatchNormal (None, 28, 28, 32)   128         block_3_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_expand (Conv2D)         (None, 28, 28, 192)  6144        block_3_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_expand_BN (BatchNormali (None, 28, 28, 192)  768         block_4_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_expand_relu (ReLU)      (None, 28, 28, 192)  0           block_4_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_depthwise (DepthwiseCon (None, 28, 28, 192)  1728        block_4_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_depthwise_BN (BatchNorm (None, 28, 28, 192)  768         block_4_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_depthwise_relu (ReLU)   (None, 28, 28, 192)  0           block_4_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_project (Conv2D)        (None, 28, 28, 32)   6144        block_4_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_project_BN (BatchNormal (None, 28, 28, 32)   128         block_4_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_4_add (Add)               (None, 28, 28, 32)   0           block_3_project_BN[0][0]         \n",
+      "                                                                 block_4_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_expand (Conv2D)         (None, 28, 28, 192)  6144        block_4_add[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_expand_BN (BatchNormali (None, 28, 28, 192)  768         block_5_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_expand_relu (ReLU)      (None, 28, 28, 192)  0           block_5_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_depthwise (DepthwiseCon (None, 28, 28, 192)  1728        block_5_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_depthwise_BN (BatchNorm (None, 28, 28, 192)  768         block_5_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_depthwise_relu (ReLU)   (None, 28, 28, 192)  0           block_5_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_project (Conv2D)        (None, 28, 28, 32)   6144        block_5_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_project_BN (BatchNormal (None, 28, 28, 32)   128         block_5_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_5_add (Add)               (None, 28, 28, 32)   0           block_4_add[0][0]                \n",
+      "                                                                 block_5_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_expand (Conv2D)         (None, 28, 28, 192)  6144        block_5_add[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_expand_BN (BatchNormali (None, 28, 28, 192)  768         block_6_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_expand_relu (ReLU)      (None, 28, 28, 192)  0           block_6_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_pad (ZeroPadding2D)     (None, 29, 29, 192)  0           block_6_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_depthwise (DepthwiseCon (None, 14, 14, 192)  1728        block_6_pad[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_depthwise_BN (BatchNorm (None, 14, 14, 192)  768         block_6_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_depthwise_relu (ReLU)   (None, 14, 14, 192)  0           block_6_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_project (Conv2D)        (None, 14, 14, 64)   12288       block_6_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_6_project_BN (BatchNormal (None, 14, 14, 64)   256         block_6_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_expand (Conv2D)         (None, 14, 14, 384)  24576       block_6_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_expand_BN (BatchNormali (None, 14, 14, 384)  1536        block_7_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_expand_relu (ReLU)      (None, 14, 14, 384)  0           block_7_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_depthwise (DepthwiseCon (None, 14, 14, 384)  3456        block_7_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_depthwise_BN (BatchNorm (None, 14, 14, 384)  1536        block_7_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_depthwise_relu (ReLU)   (None, 14, 14, 384)  0           block_7_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_project (Conv2D)        (None, 14, 14, 64)   24576       block_7_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_project_BN (BatchNormal (None, 14, 14, 64)   256         block_7_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_7_add (Add)               (None, 14, 14, 64)   0           block_6_project_BN[0][0]         \n",
+      "                                                                 block_7_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_expand (Conv2D)         (None, 14, 14, 384)  24576       block_7_add[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_expand_BN (BatchNormali (None, 14, 14, 384)  1536        block_8_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_expand_relu (ReLU)      (None, 14, 14, 384)  0           block_8_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_depthwise (DepthwiseCon (None, 14, 14, 384)  3456        block_8_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_depthwise_BN (BatchNorm (None, 14, 14, 384)  1536        block_8_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_depthwise_relu (ReLU)   (None, 14, 14, 384)  0           block_8_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_project (Conv2D)        (None, 14, 14, 64)   24576       block_8_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_project_BN (BatchNormal (None, 14, 14, 64)   256         block_8_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_8_add (Add)               (None, 14, 14, 64)   0           block_7_add[0][0]                \n",
+      "                                                                 block_8_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_expand (Conv2D)         (None, 14, 14, 384)  24576       block_8_add[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_expand_BN (BatchNormali (None, 14, 14, 384)  1536        block_9_expand[0][0]             \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_expand_relu (ReLU)      (None, 14, 14, 384)  0           block_9_expand_BN[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_depthwise (DepthwiseCon (None, 14, 14, 384)  3456        block_9_expand_relu[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_depthwise_BN (BatchNorm (None, 14, 14, 384)  1536        block_9_depthwise[0][0]          \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_depthwise_relu (ReLU)   (None, 14, 14, 384)  0           block_9_depthwise_BN[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_project (Conv2D)        (None, 14, 14, 64)   24576       block_9_depthwise_relu[0][0]     \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_project_BN (BatchNormal (None, 14, 14, 64)   256         block_9_project[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_9_add (Add)               (None, 14, 14, 64)   0           block_8_add[0][0]                \n",
+      "                                                                 block_9_project_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_expand (Conv2D)        (None, 14, 14, 384)  24576       block_9_add[0][0]                \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_expand_BN (BatchNormal (None, 14, 14, 384)  1536        block_10_expand[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_expand_relu (ReLU)     (None, 14, 14, 384)  0           block_10_expand_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_depthwise (DepthwiseCo (None, 14, 14, 384)  3456        block_10_expand_relu[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_depthwise_BN (BatchNor (None, 14, 14, 384)  1536        block_10_depthwise[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_depthwise_relu (ReLU)  (None, 14, 14, 384)  0           block_10_depthwise_BN[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_project (Conv2D)       (None, 14, 14, 96)   36864       block_10_depthwise_relu[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "block_10_project_BN (BatchNorma (None, 14, 14, 96)   384         block_10_project[0][0]           \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_expand (Conv2D)        (None, 14, 14, 576)  55296       block_10_project_BN[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_expand_BN (BatchNormal (None, 14, 14, 576)  2304        block_11_expand[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_expand_relu (ReLU)     (None, 14, 14, 576)  0           block_11_expand_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_depthwise (DepthwiseCo (None, 14, 14, 576)  5184        block_11_expand_relu[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_depthwise_BN (BatchNor (None, 14, 14, 576)  2304        block_11_depthwise[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_depthwise_relu (ReLU)  (None, 14, 14, 576)  0           block_11_depthwise_BN[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_project (Conv2D)       (None, 14, 14, 96)   55296       block_11_depthwise_relu[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_project_BN (BatchNorma (None, 14, 14, 96)   384         block_11_project[0][0]           \n",
+      "__________________________________________________________________________________________________\n",
+      "block_11_add (Add)              (None, 14, 14, 96)   0           block_10_project_BN[0][0]        \n",
+      "                                                                 block_11_project_BN[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_expand (Conv2D)        (None, 14, 14, 576)  55296       block_11_add[0][0]               \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_expand_BN (BatchNormal (None, 14, 14, 576)  2304        block_12_expand[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_expand_relu (ReLU)     (None, 14, 14, 576)  0           block_12_expand_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_depthwise (DepthwiseCo (None, 14, 14, 576)  5184        block_12_expand_relu[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_depthwise_BN (BatchNor (None, 14, 14, 576)  2304        block_12_depthwise[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_depthwise_relu (ReLU)  (None, 14, 14, 576)  0           block_12_depthwise_BN[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_project (Conv2D)       (None, 14, 14, 96)   55296       block_12_depthwise_relu[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_project_BN (BatchNorma (None, 14, 14, 96)   384         block_12_project[0][0]           \n",
+      "__________________________________________________________________________________________________\n",
+      "block_12_add (Add)              (None, 14, 14, 96)   0           block_11_add[0][0]               \n",
+      "                                                                 block_12_project_BN[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_expand (Conv2D)        (None, 14, 14, 576)  55296       block_12_add[0][0]               \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_expand_BN (BatchNormal (None, 14, 14, 576)  2304        block_13_expand[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_expand_relu (ReLU)     (None, 14, 14, 576)  0           block_13_expand_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_pad (ZeroPadding2D)    (None, 15, 15, 576)  0           block_13_expand_relu[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_depthwise (DepthwiseCo (None, 7, 7, 576)    5184        block_13_pad[0][0]               \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_depthwise_BN (BatchNor (None, 7, 7, 576)    2304        block_13_depthwise[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_depthwise_relu (ReLU)  (None, 7, 7, 576)    0           block_13_depthwise_BN[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_project (Conv2D)       (None, 7, 7, 160)    92160       block_13_depthwise_relu[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "block_13_project_BN (BatchNorma (None, 7, 7, 160)    640         block_13_project[0][0]           \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_expand (Conv2D)        (None, 7, 7, 960)    153600      block_13_project_BN[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_expand_BN (BatchNormal (None, 7, 7, 960)    3840        block_14_expand[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_expand_relu (ReLU)     (None, 7, 7, 960)    0           block_14_expand_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_depthwise (DepthwiseCo (None, 7, 7, 960)    8640        block_14_expand_relu[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_depthwise_BN (BatchNor (None, 7, 7, 960)    3840        block_14_depthwise[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_depthwise_relu (ReLU)  (None, 7, 7, 960)    0           block_14_depthwise_BN[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_project (Conv2D)       (None, 7, 7, 160)    153600      block_14_depthwise_relu[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_project_BN (BatchNorma (None, 7, 7, 160)    640         block_14_project[0][0]           \n",
+      "__________________________________________________________________________________________________\n",
+      "block_14_add (Add)              (None, 7, 7, 160)    0           block_13_project_BN[0][0]        \n",
+      "                                                                 block_14_project_BN[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_expand (Conv2D)        (None, 7, 7, 960)    153600      block_14_add[0][0]               \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_expand_BN (BatchNormal (None, 7, 7, 960)    3840        block_15_expand[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_expand_relu (ReLU)     (None, 7, 7, 960)    0           block_15_expand_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_depthwise (DepthwiseCo (None, 7, 7, 960)    8640        block_15_expand_relu[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_depthwise_BN (BatchNor (None, 7, 7, 960)    3840        block_15_depthwise[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_depthwise_relu (ReLU)  (None, 7, 7, 960)    0           block_15_depthwise_BN[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_project (Conv2D)       (None, 7, 7, 160)    153600      block_15_depthwise_relu[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_project_BN (BatchNorma (None, 7, 7, 160)    640         block_15_project[0][0]           \n",
+      "__________________________________________________________________________________________________\n",
+      "block_15_add (Add)              (None, 7, 7, 160)    0           block_14_add[0][0]               \n",
+      "                                                                 block_15_project_BN[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_expand (Conv2D)        (None, 7, 7, 960)    153600      block_15_add[0][0]               \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_expand_BN (BatchNormal (None, 7, 7, 960)    3840        block_16_expand[0][0]            \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_expand_relu (ReLU)     (None, 7, 7, 960)    0           block_16_expand_BN[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_depthwise (DepthwiseCo (None, 7, 7, 960)    8640        block_16_expand_relu[0][0]       \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_depthwise_BN (BatchNor (None, 7, 7, 960)    3840        block_16_depthwise[0][0]         \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_depthwise_relu (ReLU)  (None, 7, 7, 960)    0           block_16_depthwise_BN[0][0]      \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_project (Conv2D)       (None, 7, 7, 320)    307200      block_16_depthwise_relu[0][0]    \n",
+      "__________________________________________________________________________________________________\n",
+      "block_16_project_BN (BatchNorma (None, 7, 7, 320)    1280        block_16_project[0][0]           \n",
+      "__________________________________________________________________________________________________\n",
+      "Conv_1 (Conv2D)                 (None, 7, 7, 1280)   409600      block_16_project_BN[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "Conv_1_bn (BatchNormalization)  (None, 7, 7, 1280)   5120        Conv_1[0][0]                     \n",
+      "__________________________________________________________________________________________________\n",
+      "out_relu (ReLU)                 (None, 7, 7, 1280)   0           Conv_1_bn[0][0]                  \n",
+      "__________________________________________________________________________________________________\n",
+      "global_average_pooling2d (Globa (None, 1280)         0           out_relu[0][0]                   \n",
+      "__________________________________________________________________________________________________\n",
+      "batch_normalization (BatchNorma (None, 1280)         5120        global_average_pooling2d[0][0]   \n",
+      "__________________________________________________________________________________________________\n",
+      "dense (Dense)                   (None, 1280)         1639680     batch_normalization[0][0]        \n",
+      "__________________________________________________________________________________________________\n",
+      "batch_normalization_1 (BatchNor (None, 1280)         5120        dense[0][0]                      \n",
+      "__________________________________________________________________________________________________\n",
+      "dense_1 (Dense)                 (None, 2)            2562        batch_normalization_1[0][0]      \n",
+      "==================================================================================================\n",
+      "Total params: 3,910,466\n",
+      "Trainable params: 3,871,234\n",
+      "Non-trainable params: 39,232\n",
+      "__________________________________________________________________________________________________\n"
+     ]
+    }
+   ],
+   "source": [
+    "with strategy.scope():\n",
+    "    base_model = MobileNetV2(include_top=False, weights='imagenet', input_shape=(targetx, targety, 3))\n",
+    "    # base_model = EfficientNetB0(include_top=False, weights='imagenet', input_shape=(targetx, targety, 3))\n",
+    "\n",
+    "    x = base_model.output\n",
+    "    x = GlobalAveragePooling2D()(x)\n",
+    "    # x = Dropout(rate = .2)(x)\n",
+    "    x = BatchNormalization()(x)\n",
+    "    x = Dense(1280, activation='relu',  kernel_initializer=glorot_uniform(seed), bias_initializer='zeros')(x)\n",
+    "    # x = Dropout(rate = .2)(x)\n",
+    "    x = BatchNormalization()(x)\n",
+    "    predictions = Dense(classes, activation='softmax', kernel_initializer='random_uniform', bias_initializer='zeros')(x)\n",
+    "\n",
+    "    model = Model(inputs=base_model.input, outputs=predictions)\n",
+    "\n",
+    "    optimizer = Adam(lr=learning_rate)\n",
+    "    # optimizer = RMSprop(lr=learning_rate)\n",
+    "\n",
+    "    loss = \"categorical_crossentropy\"\n",
+    "    # loss = \"kullback_leibler_divergence\"\n",
+    "\n",
+    "    for layer in model.layers:\n",
+    "        layer.trainable = True\n",
+    "    # for layer in model.layers[-2:]:\n",
+    "    #     layer.trainable = True\n",
+    "\n",
+    "    model.compile(optimizer=optimizer,\n",
+    "                  loss=loss,\n",
+    "                  metrics=[\"accuracy\"])\n",
+    "\n",
+    "    model.summary()\n",
+    "    # for i, layer in enumerate(model.layers):\n",
+    "    #     print(i, layer.name, layer.trainable)"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "with strategy.scope():\n",
+    "    base_model = MobileNetV2(include_top=False, weights='imagenet', input_shape=(targetx, targety, 3))\n",
+    "\n",
+    "    x = base_model.output\n",
+    "    x = GlobalAveragePooling2D()(x)\n",
+    "    # x = Dropout(rate = .2)(x)\n",
+    "    x = BatchNormalization()(x)\n",
+    "    x = Dense(1280, activation='relu',  kernel_initializer=glorot_uniform(seed), bias_initializer='zeros')(x)\n",
+    "    # x = Dropout(rate = .2)(x)\n",
+    "    x = BatchNormalization()(x)\n",
+    "    predictions = Dense(classes, activation='softmax', kernel_initializer='random_uniform', bias_initializer='zeros')(x)\n",
+    "\n",
+    "    model = Model(inputs=base_model.input, outputs=predictions)\n",
+    "\n",
+    "    optimizer = Adam(lr=learning_rate)\n",
+    "    # optimizer = RMSprop(lr=learning_rate)\n",
+    "\n",
+    "    loss = \"categorical_crossentropy\"\n",
+    "    # loss = \"kullback_leibler_divergence\"\n",
+    "\n",
+    "    for layer in model.layers:\n",
+    "        layer.trainable = True\n",
+    "    # for layer in model.layers[-2:]:\n",
+    "    #     layer.trainable = True\n",
+    "\n",
+    "    model.compile(optimizer=optimizer,\n",
+    "                  loss=loss,\n",
+    "                  metrics=[\"accuracy\"])\n",
+    "\n",
+    "    model.summary()\n",
+    "    # for i, layer in enumerate(model.layers):\n",
+    "    #     print(i, layer.name, layer.trainable)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Fit model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From <timed exec>:6: Model.fit_generator (from tensorflow.python.keras.engine.training) is deprecated and will be removed in a future version.\n",
+      "Instructions for updating:\n",
+      "Please use Model.fit, which supports generators.\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 1/250\n",
+      "INFO:tensorflow:batch_all_reduce: 164 all-reduces with algorithm = nccl, num_packs = 1\n",
+      "INFO:tensorflow:batch_all_reduce: 164 all-reduces with algorithm = nccl, num_packs = 1\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.5027 - loss: 0.8569\n",
+      "Epoch 00001: val_accuracy improved from -inf to 0.50398, saving model to landslide_classifier.h5\n",
+      "14/14 [==============================] - 49s 3s/step - accuracy: 0.5027 - loss: 0.8569 - val_accuracy: 0.5040 - val_loss: 0.7772 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 2/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.5638 - loss: 0.7553\n",
+      "Epoch 00002: val_accuracy improved from 0.50398 to 0.53785, saving model to landslide_classifier.h5\n",
+      "14/14 [==============================] - 38s 3s/step - accuracy: 0.5638 - loss: 0.7553 - val_accuracy: 0.5378 - val_loss: 0.7356 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 3/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.6149 - loss: 0.6962\n",
+      "Epoch 00003: val_accuracy did not improve from 0.53785\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.6149 - loss: 0.6962 - val_accuracy: 0.5359 - val_loss: 0.7441 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 4/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.6566 - loss: 0.6314\n",
+      "Epoch 00004: val_accuracy improved from 0.53785 to 0.55578, saving model to landslide_classifier.h5\n",
+      "14/14 [==============================] - 38s 3s/step - accuracy: 0.6566 - loss: 0.6314 - val_accuracy: 0.5558 - val_loss: 0.7152 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 5/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.6526 - loss: 0.6359\n",
+      "Epoch 00005: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.6526 - loss: 0.6359 - val_accuracy: 0.5398 - val_loss: 0.7142 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 6/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.6774 - loss: 0.6009\n",
+      "Epoch 00006: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.6774 - loss: 0.6009 - val_accuracy: 0.5339 - val_loss: 0.7319 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 7/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.6804 - loss: 0.5988\n",
+      "Epoch 00007: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.6804 - loss: 0.5988 - val_accuracy: 0.5378 - val_loss: 0.7520 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 8/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7017 - loss: 0.5779\n",
+      "Epoch 00008: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7017 - loss: 0.5779 - val_accuracy: 0.5120 - val_loss: 0.7925 - lr: 1.0000e-04\n",
+      "Learning rate:  1e-04\n",
+      "Epoch 9/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7112 - loss: 0.5569\n",
+      "Epoch 00009: ReduceLROnPlateau reducing learning rate to 3.1622775802825264e-05.\n",
+      "\n",
+      "Epoch 00009: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7112 - loss: 0.5569 - val_accuracy: 0.5100 - val_loss: 0.8326 - lr: 1.0000e-04\n",
+      "Learning rate:  3.1622774e-05\n",
+      "Epoch 10/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7270 - loss: 0.5282\n",
+      "Epoch 00010: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7270 - loss: 0.5282 - val_accuracy: 0.5159 - val_loss: 0.8136 - lr: 3.1623e-05\n",
+      "Learning rate:  3.1622774e-05\n",
+      "Epoch 11/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7236 - loss: 0.5335\n",
+      "Epoch 00011: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7236 - loss: 0.5335 - val_accuracy: 0.5020 - val_loss: 0.8296 - lr: 3.1623e-05\n",
+      "Learning rate:  3.1622774e-05\n",
+      "Epoch 12/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7280 - loss: 0.5409\n",
+      "Epoch 00012: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7280 - loss: 0.5409 - val_accuracy: 0.5299 - val_loss: 0.8433 - lr: 3.1623e-05\n",
+      "Learning rate:  3.1622774e-05\n",
+      "Epoch 13/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7504 - loss: 0.5148\n",
+      "Epoch 00013: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7504 - loss: 0.5148 - val_accuracy: 0.5319 - val_loss: 0.8690 - lr: 3.1623e-05\n",
+      "Learning rate:  3.1622774e-05\n",
+      "Epoch 14/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7449 - loss: 0.5103\n",
+      "Epoch 00014: ReduceLROnPlateau reducing learning rate to 9.999999259090306e-06.\n",
+      "\n",
+      "Epoch 00014: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7449 - loss: 0.5103 - val_accuracy: 0.5359 - val_loss: 0.9017 - lr: 3.1623e-05\n",
+      "Learning rate:  9.999999e-06\n",
+      "Epoch 15/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7672 - loss: 0.4831\n",
+      "Epoch 00015: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7672 - loss: 0.4831 - val_accuracy: 0.5279 - val_loss: 0.9036 - lr: 1.0000e-05\n",
+      "Learning rate:  9.999999e-06\n",
+      "Epoch 16/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7538 - loss: 0.4952\n",
+      "Epoch 00016: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7538 - loss: 0.4952 - val_accuracy: 0.5120 - val_loss: 0.9364 - lr: 1.0000e-05\n",
+      "Learning rate:  9.999999e-06\n",
+      "Epoch 17/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7623 - loss: 0.4870\n",
+      "Epoch 00017: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7623 - loss: 0.4870 - val_accuracy: 0.5378 - val_loss: 0.9247 - lr: 1.0000e-05\n",
+      "Learning rate:  9.999999e-06\n",
+      "Epoch 18/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7350 - loss: 0.5125\n",
+      "Epoch 00018: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7350 - loss: 0.5125 - val_accuracy: 0.5418 - val_loss: 0.9386 - lr: 1.0000e-05\n",
+      "Learning rate:  9.999999e-06\n",
+      "Epoch 19/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7717 - loss: 0.4804\n",
+      "Epoch 00019: ReduceLROnPlateau reducing learning rate to 3.162277292675049e-06.\n",
+      "\n",
+      "Epoch 00019: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7717 - loss: 0.4804 - val_accuracy: 0.5339 - val_loss: 0.9490 - lr: 1.0000e-05\n",
+      "Learning rate:  3.1622774e-06\n",
+      "Epoch 20/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7772 - loss: 0.4741\n",
+      "Epoch 00020: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7772 - loss: 0.4741 - val_accuracy: 0.5219 - val_loss: 0.9684 - lr: 3.1623e-06\n",
+      "Learning rate:  3.1622774e-06\n",
+      "Epoch 21/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7628 - loss: 0.4934\n",
+      "Epoch 00021: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7628 - loss: 0.4934 - val_accuracy: 0.5219 - val_loss: 0.9629 - lr: 3.1623e-06\n",
+      "Learning rate:  3.1622774e-06\n",
+      "Epoch 22/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7737 - loss: 0.4792\n",
+      "Epoch 00022: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7737 - loss: 0.4792 - val_accuracy: 0.5438 - val_loss: 0.9646 - lr: 3.1623e-06\n",
+      "Learning rate:  3.1622774e-06\n",
+      "Epoch 23/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7826 - loss: 0.4708\n",
+      "Epoch 00023: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 37s 3s/step - accuracy: 0.7826 - loss: 0.4708 - val_accuracy: 0.5199 - val_loss: 0.9883 - lr: 3.1623e-06\n",
+      "Learning rate:  3.1622774e-06\n",
+      "Epoch 24/250\n",
+      "14/14 [==============================] - ETA: 0s - accuracy: 0.7692 - loss: 0.4834\n",
+      "Epoch 00024: ReduceLROnPlateau reducing learning rate to 9.999999115286567e-07.\n",
+      "Restoring model weights from the end of the best epoch.\n",
+      "\n",
+      "Epoch 00024: val_accuracy did not improve from 0.55578\n",
+      "14/14 [==============================] - 38s 3s/step - accuracy: 0.7692 - loss: 0.4834 - val_accuracy: 0.5159 - val_loss: 0.9976 - lr: 3.1623e-06\n",
+      "Epoch 00024: early stopping\n",
+      "CPU times: user 24min 23s, sys: 1min 57s, total: 26min 21s\n",
+      "Wall time: 16min 38s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "\n",
+    "params = model.fit_generator(generator=train_generator, \n",
+    "                                steps_per_epoch=len(train_generator), \n",
+    "                                validation_data=test_generator, \n",
+    "                                validation_steps=len(test_generator),\n",
+    "                                epochs=epochs,\n",
+    "                                callbacks=[reducelr, earlystop, lambdacb, tensorboard, checkpoint])"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "%%time\n",
+    "params = model.fit(generator=train_generator, \n",
+    "                                steps_per_epoch=len(train_generator), \n",
+    "                                validation_data=test_generator, \n",
+    "                                validation_steps=len(test_generator),\n",
+    "                                epochs=epochs,\n",
+    "                                callbacks=[reducelr, earlystop, lambdacb, tensorboard, checkpoint])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Training and test loss/accuracy graphs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAEICAYAAABRSj9aAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+j8jraAAAgAElEQVR4nOzdd1zVZfvA8c/NFsEBggv3xoEg7kzNWVlpWmlqWqkts6ye9tN+Wr+nzMZjaZq21DItLS1HmnuAYu6FA3AhyBKZ5/79cR/tiKCMA4dxvV8vXnC+61znC1zne+7vfV+30lojhBCi/HJydABCCCGKlyR6IYQo5yTRCyFEOSeJXgghyjlJ9EIIUc5JohdCiHJOEr0oNKXUMqXUGHtv60hKqWNKqb6OjkMIe3JxdACiZCmlUmweegLpQLb18UNa6+/yeyyt9c3FsW1ppZSaDURrrV8u4nEaAkcBV611VtEjE+LaJNFXMFprr0s/K6WOAeO01itzbqeUcpEkVHHJ7798kaYbAYBSqpdSKlop9ZxS6jTwlVKqulLqV6VUrFLqvPXnAJt91iilxll/HquUWq+U+q9126NKqZsLuW0jpdRapVSyUmqlUuozpdS3ecSdnxjfVEptsB5vuVKqhs360Uqp40qpOKXUS9c4PxOAkcCzSqkUpdQS6/I6SqmfrM9/VCk1yWafTkqpMKVUklLqjFLqQ+uqtdbvCdZjdc3l+ToppTYppRKUUqeUUp8qpdxs1rdWSq1QSsVbj/2idbmzUupFpdQR6+sNV0rVU0o1VEpppZSLzTFy/k42KKWmKKXigNeUUk2UUn9az805pdR3SqlqNvvXU0ottL72uEsxWmNqa7Odv1IqVSnll9f5FcVLEr2wVQvwARoAEzB/H19ZH9cHLgKfXmP/zsABoAbwPjBTKaUKse33wFbAF3gNGH2N58xPjPcC9wP+gBvwDIBSKhCYZj1+HevzBZALrfV04Dvgfa21l9b6NqWUE7AE2AnUBfoATyqlBlh3mwpM1VpXAZoAP1iX32j9Xs16rE25PGU2MNl6frpaj/2oNW5vYCXwuzXupsAq635PASOAW4AqwANAam6vKRedgUigJvAfQAHvWJ+jFVAP8/tAKeUM/AocBxpaX/88rXUGMA8YZXPcEcAqrXVsPuMQ9qa1lq8K+gUcA/paf+4FZAAe19i+PXDe5vEaTNMPwFjgsM06T0ADtQqyLSZZZwGeNuu/Bb7N52vKLcaXbR4/Cvxu/fkVTHK6tK6y9Rz0zePYs4G3bB53Bk7k2OYF4Cvrz2uB14EaObZpaH29LgX4XT0JLLL+PALYkcd2B4A7cll+1XPm8js5cZ0YBl96XsybT2xur+HSeQGU9XEYcLej/94r8pe00QtbsVrrtEsPlFKewBRgIFDduthbKeWstc7OZf/Tl37QWqdaL9C9ctnuWtvWAOK11rZXoVGYq8mr5DPG0za7pNrEVMd67EtxXLA2W+RXA6COUirBZpkzsM7684PAG8B+pdRR4HWt9a/5ObBSqjnwIRCKeSN0AcKtq+sBR/LY9VrrrifK9oFSqibmU0kPwBvz6em8zfMc17m042uttyilUoFeSqlTmE8ciwsZk7ADaboRtnKWMn0aaAF01qb54VKTQ17NMfZwCvCxJvBLck3yVkWJ8ZTtsa3P6XuN7XOenyjgqNa6ms2Xt9b6FgCt9SGt9QhMk9F7wAKlVOVcjpObacB+oJn1db1o85qigMZ57BeFaSbK6YL1u+15rZVjm5xxvW1d1tYaw6gcMdS3bfPPYY51+9HAAtsLCFHyJNGLa/HGtHknKKV8gFeL+wm11scxH/Vfs97Y6wrcVkwxLgAGKaVusN7ofINr/0+c4coEuxVIVuYGdiXrjdA2SqmOAEqpUUopP621Bbh01W/BNHlYyDtZX3pdSUCKUqol8IjNul+B2kqpJ5VS7kopb6VUZ+u6L4E3lVLNlNFOKeWrTft4DDDKGucD5P6GkDOGFCBRKVUX+FeO134KeFcpVVkp5aGU6m6z/ltgCCbZf32d5xHFTBK9uJaPgErAOWAz5uZfSRiJaQOOA94C5mP6++em0DFqrfcAj2Fu/p7CNEtEX2OXmUCgtSfMz9amoUGY+wJHrTF8CVS1bj8Q2KPM2IWpwHCt9UVrs9R/gA3WY3XJ5bmewdxETgZmYM7BpbiTgX6YN8DTwCGgt3X1h5ibvssxbxQzMecHYDwmWccBrYGN1zlFrwMhQCLwG7DQJoZs6/M3xbTHRwP32KyPArZjPhGsQzjUpZslQpRaSqn5wH6tdbF/ohD2o5SaBZzURRxgJopOEr0odaxNH/GYq+T+wM9AV631DocGJvJNmdG/EUCw1vqoY6MR0nQjSqNamK5/KcDHwCOS5MsOpdSbwG7g/yTJlw5yRS+EEOWcXNELIUQ5V+oGTNWoUUM3bNjQ0WEIIUSZEh4efk5rnWs9oVKX6Bs2bEhYWJijwxBCiDJFKXU8r3XSdCOEEOWcJHohhCjnJNELIUQ5V+ra6HOTmZlJdHQ0aWlSF6m88/DwICAgAFdXV0eHIkS5USYSfXR0NN7e3jRs2JC857EQZZ3Wmri4OKKjo2nUqJGjwxGi3CgTTTdpaWn4+vpKki/nlFL4+vrKJzch7KxMJHpAknwFIb9nIeyvzCR6IYQoCy6kZ7EgPJq9J5McHcplZaKN3tHi4uLo06cPAKdPn8bZ2Rk/PzMAbevWrbi5ueW5b1hYGF9//TUff/zxNZ+jW7dubNx4vfLgQojSKiE1g9kbjzF74zESUjNxcVI83b8FE25sjLOTYz+pSqLPB19fXyIiIgB47bXX8PLy4plnnrm8PisrCxeX3E9laGgooaGh132Ospjks7OzcXZ2dnQYQjjUmaQ0vlwXyXdbTpCakU2/wJqM7daQ77ec4L3f9/PXwbNMuac9tatWuv7Biok03RTS2LFjefjhh+ncuTPPPvssW7dupWvXrgQHB9OtWzcOHDgAwJo1axg0aBBg3iQeeOABevXqRePGja+4yvfy8rq8fa9evRg2bBgtW7Zk5MiRXKowunTpUlq2bEmHDh2YNGnS5ePaOnbsGD169CAkJISQkJAr3kDee+892rZtS1BQEM8//zwAhw8fpm/fvgQFBRESEsKRI0euiBlg4sSJzJ49GzAlKp577jlCQkL48ccfmTFjBh07diQoKIihQ4eSmmrm9D5z5gxDhgwhKCiIoKAgNm7cyCuvvMJHH310+bgvvfQSU6dOLfLvQghHOBGXyouLdtHjvdXMXH+U/oE1+ePJG5lxXyjdm9bg03uDeX9YO/6OTmTgR+tYtuuUw2Itc1f0ry/ZY/e2r8A6VXj1ttYF3i86OpqNGzfi7OxMUlIS69atw8XFhZUrV/Liiy/y008/XbXP/v37Wb16NcnJybRo0YJHHnnkqj7jO3bsYM+ePdSpU4fu3buzYcMGQkNDeeihh1i7di2NGjVixIgRucbk7+/PihUr8PDw4NChQ4wYMYKwsDCWLVvGL7/8wpYtW/D09CQ+Ph6AkSNH8vzzzzNkyBDS0tKwWCxERUVd83X7+vqyfft2wDRrjR8/HoCXX36ZmTNn8vjjjzNp0iR69uzJokWLyM7OJiUlhTp16nDnnXfy5JNPYrFYmDdvHlu3bi3weRcVV1a2hYioBFYfOIuXuyvjejTC1blkr1f3n05i2pojLNl5EhcnJ+4KDeChG5tQ39fziu2UUtwdWo9ODX14Yt4OHvluO3eHBvDqba2p7F6yqbfMJfrS5K677rrcdJGYmMiYMWM4dOgQSikyMzNz3efWW2/F3d0dd3d3/P39OXPmDAEBAVds06lTp8vL2rdvz7Fjx/Dy8qJx48aX+5ePGDGC6dOnX3X8zMxMJk6cSEREBM7Ozhw8eBCAlStXcv/99+Ppaf4YfXx8SE5OJiYmhiFDhgBmsFJ+3HPP5alB2b17Ny+//DIJCQmkpKQwYMAAAP7880++/trMCe3s7EzVqlWpWrUqvr6+7NixgzNnzhAcHIyvr2++nlNUXPEXMvjr4Fn+3B/L2oOxJF7MxNlJkW3RrNp3hk/vDaFW1fz97RbF9hPn+d/qw6zcd5bKbs6M69GYcTc0wr/KtZ+7YY3KLHikG1NXHuKzNYfZejSeqcODCapXrdhjvqTMJfrCXHkXl8qVK1/++d///je9e/dm0aJFHDt2jF69euW6j7u7++WfnZ2dycrKKtQ2eZkyZQo1a9Zk586dWCyWfCdvWy4uLlgslsuPc/Zrt33dY8eO5eeffyYoKIjZs2ezZs2aax573LhxzJ49m9OnT/PAAw8UODZR/lksmr2nkvhz/1lWHzhLRFQCWkMNLzf6tqrJTS39uaFZDf46GMvzP/3NrR+vY+rwYG5oVsPusWit2XA4js9WH2ZTZBzVPF2Z3Lc5Y7o1oJpn3p0wcnJ1duKZAS3o0awGk+dHMHTaRib3a87DPZuUyI1aaaO3k8TEROrWrQtwuT3bnlq0aEFkZCTHjh0DYP78+XnGUbt2bZycnPjmm2/Izs4GoF+/fnz11VeX29Dj4+Px9vYmICCAn3/+GYD09HRSU1Np0KABe/fuJT09nYSEBFatWpVnXMnJydSuXZvMzEy+++67y8v79OnDtGnTAHPTNjExEYAhQ4bw+++/s23btstX/0Ikp2WybNcp/vXjTjq/s4pBn6xnysqDWDQ82ac5iyd2Z+uLffng7iBubVebqpVcuT2oDosndsenshujZ23h41WHsFjsN2Pe4bMpjPlqG6NmbiHyXAov39qKDc/dxBN9mxUoydvq3NiXZU/cyIA2tfi/Pw5w74zNnEy4aLeY81LmruhLq2effZYxY8bw1ltvceutt9r9+JUqVeJ///sfAwcOpHLlynTs2DHX7R599FGGDh3K119/fXlbgIEDBxIREUFoaChubm7ccsstvP3223zzzTc89NBDvPLKK7i6uvLjjz/SuHFj7r77btq0aUOjRo0IDg7OM64333yTzp074+fnR+fOnUlOTgZg6tSpTJgwgZkzZ+Ls7My0adPo2rUrbm5u9O7dm2rVqkmPHYHWmhcW7mJBeDRZFk0VDxdubO5H7xb+9GzhRw0v92vu39Tfm18mdufFhbv4cMVBwo+f56N72lO9cuESMUDixUw+XnWIORuPUcnNmZdvbcXorg1wd7HP32tVT1c+HRFM7xb+vPrLbgZ+tJZ37mzHre1q2+X4uSl1c8aGhobqnBOP7Nu3j1atWjkootIjJSUFLy8vtNY89thjNGvWjMmTJzs6rAKxWCyXe+w0a9Ys123k911xrDsUy+iZW7kzpC7DO9YnpH41XApxc1VrzfdbT/D64r3U8HLjs5EhBNevXqBjZFs0P4RF8d8/DhCfmsHwjvV4un+L677ZFMXxuAs8MS+CiKgE7uoQwKu3t8arkDdqlVLhWutc+3JL000ZMmPGDNq3b0/r1q1JTEzkoYcecnRIBbJ3716aNm1Knz598kzyouLQWvPB8oPUqerBO3e2pVMjn0IleTA9XEZ2bsBPj3TDyUlx9xebmLPxGPm9kN12LJ7bP13PCwt30divMksm3sA7d7Yr1iQP0MC3Mj8+3JVJNzXlp+3R3PPFJrs2P10iV/Si1JHfd96+2nAUF2cnRnaqj5ODR1sW1Z/7z/DA7DDeubMtIzrVt9txE1IzePqHnazaf5ZB7Wrz7tB2eV4ln0y4yLvL9rN450lqV/XghVtacVu72g6pubT1aDxxKenc3LZwTTjXuqKXNnohyohvNx/n9SV7AVix9wz/Hdbuul37SiutNR+uOEh9H0+GdQi4/g4FUM3TjRn3hfL52iP8948D7D2VxOejOtC8pvflbdIys5m+NpJpa45g0ZpJNzXl4V5N8HRzXErs1Min2I4tTTdClAHrD53j1cV76N3CjzcHt2Hr0TgGTl3Hyr1nHB1aofyx5wy7Y5KY1KdZsQx4cnJSPNqrKd+N60LSxSzu+HQDi3ZEo7Vm2a5T9P3wLz5ccZBeLfxY+VRPnurfwqFJvriV31cmRDlxJDaFR78Lp6mfFx+PCMbbw5WujX2YNDeCcV+HMapLfV66JZBKbvbrxWSxaOIuZODnbf82aotFM2XFQRrXqMzg9nXsfnxbXZv4snTSDUycu4PJ83fyyZ+HiYy9QIua3nw/vjPdmti/731pJFf0QpRi5y9k8ODsbbg6O/HlmFC8PUy5jKb+3ix6rBvjezTi280nuO3T9ew5mVjk50vLzOb7LSfoN+UvOr+9kg2HzxX5mDkt3X2KA2eSeaJvs0LffC0I/yoefD+uMw/3bMLFjGzevKM1v026ocIkeZCbsflSlDLFYAqVubm50a1bt2KPtTxw9O+7tMjIsjB65hZ2nEhg7oTOdGiQexvu+kPneOqHCBJSM3l2YAse6N6owDdqz6Wk882m43y7+ThxFzJoU7cKyWlZZGRZ+P3JG6layT5z+GZbNAM+WosCfn/yRoeX7y1P5GZsEV2vTPH1rFmzBi8vL4cneikrXHZorfn3z7vZcjSej+5pn2eSB7ihWQ1+f/JGnvvpb976bR9/HYzlv3cFUTMfN2oPn01m5vqj/LQ9howsC31a+jOuR2O6NPbh7+hE7py2kdeX7OHDu9vb5XUt3hnD4bMp/G9kiCT5EiRNN4UUHh5Oz5496dChAwMGDODUKVOC9OOPPyYwMJB27doxfPhwjh07xueff86UKVNo374969atu+I4eZU3zs7O5plnnqFNmza0a9eOTz75BIBt27bRrVs3goKC6NSpE8nJycyePZuJEydePuagQYMu15zx8vLi6aefJigoiE2bNvHGG2/QsWNH2rRpw4QJEy73M86tXPF99913uTwCmEqXv/zyS7GdU/GPL9cdZX5YFI/f1JTBwXWvu71PZTemj+7A20Pasu1YPAM/WsvyPadz3VZrzcbD57j/q630/XAtC7fHMDQkgJVP9WTm2I50bWLmZw6qV42JvZuycHsMv+8ueondrGwLU1ceolXtKgxsXavIxxP5V/au6Jc9D6d32feYtdrCze/me3OtNY8//ji//PILfn5+zJ8/n5deeolZs2bx7rvvcvToUdzd3UlISKBatWo8/PDDeX4KaNmyZa7ljadPn86xY8eIiIjAxcWF+Ph4MjIyuOeee5g/fz4dO3YkKSmJSpWuPZnBhQsX6Ny5Mx988AEAgYGBvPLKKwCMHj2aX3/9ldtuuy3XcsUPPvggU6ZMYfDgwSQmJrJx40bmzJlTgBMrCmPF3jO8vWwft7StxeS+zfO9n1KKezvXp1MjUxZ3wjfh3Nu5Pv++1dyozcy28OvfJ/ly3VH2nEzCt7IbT/ZtxuguDfDNY2DQxJua8uf+s7ywcBchDarj71347pwLt8dwLC6VGfeFlvkxAGVN2Uv0pUB6ejq7d++mX79+gLn6rl3bDHJo164dI0eOZPDgwQwePPi6x8qrvPHKlSt5+OGHL89c5ePjw65du6hdu/blOjdVqlS57vGdnZ0ZOnTo5cerV6/m/fffJzU1lfj4eFq3bk2vXr1yLVfcs2dPHn30UWJjY/npp58YOnRonjNpCfvYezKJJ+btoG3dqnxwV/tCJcSm/l4sfLQbHy4/yBdrI9kcGcftQXWYtzWK00lpNPGrzDt3tmVIcF08XK/dlOfq7MSUe4K49eP1vLhwFzPuCy3UYKKMLAtTVx0iKKAqfVv5F3h/UTT5+q9VSg0EpgLOwJda63dzrJ8C9LY+9AT8tdbVrOuygUuX4Ce01rcXKeICXHkXF601rVu3ZtOmTVet++2331i7di1LlizhP//5D7t2XfvTR37LG1/LtcoKe3h4XG6XT0tL49FHHyUsLIx69erx2muvXVWCOKf77ruPb7/9lnnz5vHVV18VODaRf2eT0xg3ZxtVPFz58r7QInWXdHdx5oVbWnFjcz+e+iGCj1YeomtjX96+sw29mvsX6A2kqb83zw1syRu/7uWHsCju6VjwUaw/hEURk3CR/wxp45BRpxXdddvolVLOwGfAzUAgMEIpFWi7jdZ6sta6vda6PfAJsNBm9cVL64qc5EsJd3d3YmNjLyf6zMxM9uzZc3l2pt69e/Pee++RmJhISkoK3t7el6s65pRXeeN+/frxxRdfXK5FHx8fT4sWLTh16hTbtm0DTIngrKwsGjZsSERExOXnz2vWpktJvUaNGqSkpLBgwQKAPMsVg6k3f2n6v8DAwFyOKuwhLTOb8V+Hcz41ky/HhNptxGv3pjVY9XQv1v6rN3MndOGmljUL9SlhbLeGdG3syxtL9hIVn1qgfdMys/n0z8N0aFCdns39CvzcoujyczO2E3BYax2ptc4A5gF3XGP7EcBcewRXWjk5ObFgwQKee+45goKCaN++PRs3biQ7O5tRo0bRtm1bgoODmTRpEtWqVeO2225j0aJFud6MffbZZ3nhhRcIDg6+YoKRcePGUb9+fdq1a0dQUBDff/89bm5uzJ8/n8cff5ygoCD69etHWloa3bt3p1GjRgQGBjJp0iRCQkJyjbtatWqMHz+eNm3aMGDAgCtKHX/zzTd8/PHHtGvXjm7dunH6tLmRV7NmTVq1asX9999fDGeyfNh/Oon7Zm3lv38cIPx4PNkFLEqlteaZH3fyd3QCHw1vT5u6Ve0an5e7y1XT3BWUk5Piv3cH4aQUT/+ws0Cvce7WE5xOSuPpfs3lat5BrtuPXik1DBiotR5nfTwa6Ky1npjLtg2AzUCA1jrbuiwLiACygHe11j/nst8EYAJA/fr1Oxw/fvyK9dKv2nFSU1Np27Yt27dvp2pV+yagvJSl33dscjqDP9tAQmoGaVkWsi2aap6u9LTWVL+xuR8+16mNPmXFQaauOsRzA1vySK8mJRR54SwIj+aZH3fy0i2tGH9j4+tufzEjmx7vr6apf2XmTehaAhFWXCXZj344sOBSkrdqoLWOUUo1Bv5USu3SWh+x3UlrPR2YDmbAlJ1jEoW0cuVKHnzwQSZPnlxiSb4sScvMZsI3YcRdSOfHh7pR39eTdYdiWb0/lr8OnuWXiJMoBcH1qtG7hT+9W/rTuk6VK65qF+88ydRVhxjWIYCHe14/cTra0JC6rNh7mv/74wA3NvejRS3va27/zeZjnEtJZ9qo3D9lipKRn0QfA9SzeRxgXZab4cBjtgu01jHW75FKqTVAMHDk6l1FadO3b19yfroShtaaZxf8zY4TCXw+KoS2AeaNcFC7OgxqVweLRbMrJpE/959lzYGzfLDiIB+sOIi/tzu9WpirfW8PV575cSedGvrw9pC2ZaJZQynF20PaMuCjtUyeH8HPj3XHzSX3FuCU9Cw+/yuSHs1q0LFh8VVmFNeXn0S/DWimlGqESfDDgXtzbqSUaglUBzbZLKsOpGqt05VSNYDuwPuFCVRrXSb+EUTRlLaSHHn55M/DLN55kn8NaMHANlfXD3dyMgOOgupVY3K/5sQmp/PXwVhWHzjLst2n+SEsGoD6Pp58PrpDnsmyNPL1cuftIW2Z8E04H686xDMDWuS63ZyNx4i/kMHT/XNfL0rOdRO91jpLKTUR+APTvXKW1nqPUuoNIExrvdi66XBgnr7yP7UV8IVSyoK58fuu1npvQYP08PAgLi4OX19fSfblmNaauLi4y/34S6tf/z7JhysOcmdIXR7NZ5u6n7c7wzoEMKxDAJnZFrYfP8+myDjuaF/3um34pVH/1rW4q0MA/1tzmJta+ROSY9q+pLRMpq+NpE9Lf9rXq+agKMUlZaKoWWZmJtHR0dft8y3KPg8PDwICAnB1tU8RLXuLiErgni820bZuVb4b39luE0aXRclpmQz8aB2uzoqlT/S4op77pRvMvz5+g917EYnclfmiZq6urjRq1MjRYYgK7mTCRcZ/HYZ/FXe+GN2hQid5AG8PVz64O4gRMzbzztL9vDm4DWCm8pu1/igDW9eSJF9KlJ2GQSEc6EJ6Fg/OCSMtI5uZYzrmWRumounS2JcHuzfim83H+etgLADT10aSkpHF5H75r9MjipckeiGuw2LRPDk/ggOnk/jk3uAr5h4V8MyAFjTz9+LZBTs5EpvC7I3HGNSuznW7XoqSI4leiOt474/9rNh7hlcGBdKrhRTkysnD1ZkP725PXEoGQz7bQFpmNk/2bebosIQNSfRCXMMPYVF88Vcko7rUZ0y3ho4Op9RqG1CVSX2akZSWxeDgujTx83J0SMJGmbgZK4QjbI6M46VFu+jRrAav3tZauvZex6O9muBT2Y1b2l49rkA4liR6IXJx7NwFHv42nPo+nnx6bwiuJTCJdVnn4uzEqC4NHB2GyIX89QqRQ+LFTB6cY0pBzxzT0W4TYwvhKJLohbCRlW1h4vfbORGfyuejOtCwRmVHhyREkUnTjSgTdpw4T5ZF07KWN94e9rvCzrZo9p1KYtuxeOvXeWKT03l/WDu6NPa12/MI4UiS6EWpZrFo/rv8AP9b80/B03o+lQisXYVW1q/A2lUIqF4pXzdL0zKz2RmVcDmpbz9+nuR0M+FL3WqV6N7El/6ta8kNRVGuSKIXpdbFjGwmz4/g9z2nGdGpHv0Da7H3VBJ7TyWx72QSy/ee4VKpJm8PF1rVqkJgnSq0qu1Nq9pVaF7Tm/QsC+HHTVLfdjSev6MTycg28+s2r+nF7e3r0KmRD6ENfahbrZIDX60QxUcSvSiVziSlMW5OGLtPJvLyra148IZGKKXo3fKfAUupGVkcOJ1sEv+pJPadSuaHsChSM8y8N85OCovWaA0uToq2AVUZ270hHRv6ENqgOtXLYNVIIQpDEr0odfacTGTcnDASL2YyY3QofQNr5rqdp5sLwfWrE2xTItdi0ZyIT2Wf9crf1dmJ0IbVCa5XnUpuFbsImai4JNGLUmXF3jM8MW8HVSu5suDhbgTWqVKg/Z2cFA1rVKZhjcrcLO3sQgCS6EUpobVmxrpI3lm2n7Z1q/LlfaH4VyndE5AIUVZIohcOl5Fl4ZVfdjNvWxS3tK3FB3e1l2YWIexIEr1wqMTUTB7+NpxNkXFM7N2Up/o1x8lJasoIYU+S6IXDHD13gQdnbyPqfCof3BXE0A4Bjg5JiHJJEr1wiM2RcTz8bTgK+G5cF8g6QI0AACAASURBVDo18nF0SEKUW5LoRYn7ISyKlxbtor6PJ7PGdqSBr9STEaI4SaIXJWZLZBwfrTzEpsg4bmhag89GhkhlSCFKgCR6Uey2Ho3no5UH2XgkDj9vd14ZFMjorg2kxrsQJUQSvSg2246ZBL/hcBw1vNz596BARnauj4erdJ0UoiRJohd2F3Ysno9WHmL94XPU8HLn5VtbMbJzA+kbL4SDSKIXdhN+PJ4pKy4leDdJ8EKUEvlK9EqpgcBUwBn4Umv9bo71U4De1oeegL/Wupp13RjgZeu6t7TWc+wRuCg9wo+f56OVB1l36By+ld146ZZWjOxSH083uY4QojS47n+iUsoZ+AzoB0QD25RSi7XWey9to7WebLP940Cw9Wcf4FUgFNBAuHXf83Z9FcIhTsSl8tLPuy4n+BdvacmoLg0kwQtRyuTnP7ITcFhrHQmglJoH3AHszWP7EZjkDjAAWKG1jrfuuwIYCMwtStDC8c6lpDNq5hYSUjN44eaWjO4qCV6I0io//5l1gSibx9FA59w2VEo1ABoBf15j37q57DcBmABQv379fIQkHCk1I4sHZ2/jbHIac8d3uaIevBCi9LF3R+bhwAKtdXZBdtJaT9dah2qtQ/38/OwckrCnrGwLk+buYFdMIp+MCJEkL0QZkJ9EHwPUs3kcYF2Wm+Fc2SxTkH1FKae15rUle1i57yyv396afnnM/CSEKF3yk+i3Ac2UUo2UUm6YZL4450ZKqZZAdWCTzeI/gP5KqepKqepAf+syUQZN++sI324+wcM9mzC6a0NHhyOEyKfrttFrrbOUUhMxCdoZmKW13qOUegMI01pfSvrDgXlaa22zb7xS6k3MmwXAG5duzIqy5ZeIGN7//QC3B9Xh2QEtHB2OEKIAlE1eLhVCQ0N1WFiYo8MQNjYeOceYWVvp0KA6cx7ohLuLDIASorRRSoVrrUNzWydVpcQ1HTidzENfh9OoRmW+GB0qSV6IMkgSvcjT6cQ0xn61FU93Z766v5OUFBaijJIRLiJXyWmZjP1qK8lpWcx/qAt1q1VydEhCiEKSK3pxlYwsC498u53DZ1OYNiqE1nWqOjokIUQRyBW9uILWmucX/s36w+f4v2Ht6NFMBrAJUdbJFb24wocrDrJwewxP9WvOXaH1rr+DEKLUk0QvLpu79QSf/HmY4R3r8fhNTR0djhDCTqTppgLTWnM2OZ3DZ1PYGZ3AB8sP0rO5H28OboNSytHhCSHsRBJ9BZCVbeF4fCqHz6ZwJDbF+v0CkWdTSE7PurxdSP1qfDYyRCbtFqKckURfDm2JjGPtoViOnL3A4dgUjsddIDP7nxHQNau409TfiyEhdWnq70UTPy+a+nvh7+0uV/JClEOS6MuZLZFx3PvlFgAa+HrSxM+LfoE1Lyfzxn6VqeIhA5+EqEgk0Zcj51LSeXzuDur7ePLLxO6S0IUQgPS6KTeyLZon50WQeDGTz+4NkSQvhLhMrujLiU/+PMT6w+d4b2hbAutUcXQ4QohSRK7oy4ENh88xddUh7gyuy90yyEkIkYMk+jLuTFIaT8zbQVM/L94aIv3fhRBXk6abMiwr28Ljc3dwIT2bueND8HSTX6cQ4mqSGcqwD1ccZOvReKbcE0Szmt6ODkcIUUpJ000ZtXr/Wf635ggjOtVjSHCAo8MRQpRikujLoJiEi0z+IYJWtavw6m2tHR2OEKKUk0RfxmRkWZj4/XaysjWf3RuMh6vM4SqEuDZpoy9j3v99PztOJPDpvcE09vNydDhCiDJArujLkN93n+bL9UcZ07UBg9rVcXQ4QogyQhJ9GXEiLpV/LdhJu4CqvHhrK0eHI4QoQ6TppoQcPpvMlBWHaOrvRft61QiqVw2fym752jctM5tHvw9HAZ/dG4K7i7TLCyHyTxJ9CflwxUGW7znD0t0abS0NX9/Hk6B61QgKqEr7etVoXacqldyuTuL/+W0fu2OSmD66A/V8PEs4ciFEWSeJvgSciEvl992neahnEx7r3ZTdMYlERCWwMyqB8GPxLNl5EgBnJ0WLmt4E1atGsPWqf//pJL7ZfJzxPRrRv3UtB78SIURZlK9Er5QaCEwFnIEvtdbv5rLN3cBrgAZ2aq3vtS7PBnZZNzuhtb7dDnGXKbM2HMXZSTG2W0O83F3o0tiXLo19L68/m5TGzuhEdkYlsDM6gV//PsncrScurw+pX41nB7Z0ROhCiHLguoleKeUMfAb0A6KBbUqpxVrrvTbbNANeALprrc8rpfxtDnFRa93eznGXGQmpGczfFsVtQXWoWcUj1238q3jQL9CDfoE1AbBYNMfiLrAzOoFDZ1IY062hzOMqhCi0/FzRdwIOa60jAZRS84A7gL0224wHPtNanwfQWp+1d6Bl1XdbTnAxM5vxPRrnex8nJ0VjPy/pJy+EsIv8XCbWBaJsHkdbl9lqDjRXSm1QSm22NvVc4qGUCrMuH5zbEyilJli3CYuNjS3QCyjN0rOymbPxGD2a1aBVbZkMRAjhGPZqD3ABmgG9gBHADKVUNeu6BlrrUOBe4COlVJOcO2utp2utQ7XWoX5+fnYKyfEWR5zkbHI64wpwNS+EEPaWn0QfA9hOWxRgXWYrGlistc7UWh8FDmISP1rrGOv3SGANEFzEmMsErTUz1x+lRU1vbmxWw9HhCCEqsPwk+m1AM6VUI6WUGzAcWJxjm58xV/MopWpgmnIilVLVlVLuNsu7c2Xbfrm17tA59p9OZlyPRjLrkxDCoa57M1ZrnaWUmgj8geleOUtrvUcp9QYQprVebF3XXym1F8gG/qW1jlNKdQO+UEpZMG8q79r21inPZqyLxN/bndvbS00aIYRj5asfvdZ6KbA0x7JXbH7WwFPWL9ttNgJtix5m2bLvVBLrDp3jXwNaSLkCIYTDSefsYvDluqNUcnVmZOf6jg5FCCEk0dvbmaQ0Fu+M4Z6O9ajmmb+iZUIIUZwk0dvZ7I3HyLZoHujeyNGhCCEEIIneri6kZ/Hd5uMMbFOL+r5SZVIIUTpIorejH8KiSErLkgFSQohSRRK9nWRbNLM2HKVDg+qE1K/u6HCEEOIySfR28see00TFXyxQ8TIhhCgJkujtQGvN9LWRNPD1vFxqWAghSgtJ9HYQfvw8EVEJjLuhEc5OUu5ACFG6SKK3gxnrIqnm6cqwDvWuv7EQQpQwSfRFdPTcBZbvPcOozg1yndhbCCEcTRJ9Ec1afxRXJyfu69bA0aEIIUSuJNEXwfkLGfwYHsXg4Dr4e+c+H6wQQjiaJPoi+HbzcdIyLTJASghRqkmiL6S0zGzmbDpOrxZ+NK/p7ehwhBAiT5LoC2lxxEnOpaTLACkhRKknib4QtNbMWBdJYO0qdGvi6+hwhBDimiTRF8Kag7EcOpvC+BtlPlghROknib4Qvtl0nJpV3BnUTuaDFUKUfpLoCyg2OZ2/DsYyNCQAV2c5fUKI0k8yVQEt3nmSbIvmzpC6jg5FCCHyRRJ9AS3cHk1QQFWa+kuXSiFE2SCJvgD2n05iz8kk7gwJcHQoQgiRb5LoC2DR9hhcnBS3BclNWCFE2SGJPp+ysi0s2hFD75b++FR2c3Q4QgiRb5Lo82nDkTjOJqczVG7CCiHKmHwleqXUQKXUAaXUYaXU83lsc7dSaq9Sao9S6nub5WOUUoesX2PsFXhJW7g9mqqVXOnd0t/RoQghRIG4XG8DpZQz8BnQD4gGtimlFmut99ps0wx4AeiutT6vlPK3LvcBXgVCAQ2EW/c9b/+XUnyS0zL5Y89phnUIwN1FJhcRQpQt+bmi7wQc1lpHaq0zgHnAHTm2GQ98dimBa63PWpcPAFZoreOt61YAA+0TeslZtvs0aZkW6W0jhCiT8pPo6wJRNo+jrctsNQeaK6U2KKU2K6UGFmBflFITlFJhSqmw2NjY/EdfQhZuj6ZRjcoE16vm6FCEEKLA7HUz1gVoBvQCRgAzlFL5zopa6+la61Ctdaifn5+dQrKP6POpbI6M587gulLATAhRJuUn0ccA9WweB1iX2YoGFmutM7XWR4GDmMSfn31LtZ93mHCHSG8bIUQZlZ9Evw1oppRqpJRyA4YDi3Ns8zPmah6lVA1MU04k8AfQXylVXSlVHehvXVYmaK1ZuD2GLo19CKju6ehwhBCiUK7b60ZrnaWUmohJ0M7ALK31HqXUG0CY1nox/yT0vUA28C+tdRyAUupNzJsFwBta6/jieCHFISIqgchzF3i4VxNHhyKEEIV23UQPoLVeCizNsewVm5818JT1K+e+s4BZRQvTMX7aHo2HqxM3t6nl6FCEEKLQZGRsHtKzslmy8xQDWtfC28PV0eEIIUShSaLPw+r9Z0m8mCl954UQZZ4k+jz8tD0Gf293usvk30KIMk4SfS7iL2Swev9ZBgfXxUWmCxRClHGSxXKxZOdJsmS6QCFEOSGJPhcLt0cTWLsKLWtVcXQoQghRZJLoczh8Npmd0YlyNS+EKDck0eewcHsMzk6K29vLdIFCiPJBEr0Ni0WzaEcMNzargb+3h6PDEUIIu5BEb2NTZBynEtOk77wQolyRRG/jp+3ReHu40C+wpqNDEUIIu5FEb3UhPYvfd59mULvaeLjKdIFCiPJDEr3VH3tOk5qRLc02QohyRxK91cLtMdTzqURog+qODkUIIexKEj1wKvEiG46c487gAJkuUAhR7kiiB37ecRKtkUFSQohyqcInejNdYDShDarTwLeyo8MRQgi7q/CJfndMEofOpshNWCFEuVXhE/1P26Nxc3Hi1ra1HR2KEEIUiwqd6LMtml//PkWflv5U9ZTpAoUQ5VOFTvQRUQmcS0lnoEz+LYQoxyp0ol+x9wwuTopeLfwdHYoQQhSbCp7oT9O5sQ9VK0mzjRCi/KqwiT4yNoUjsRfo10oKmAkhyrcKm+hX7D0DQN+SqlQZEw6/PAZJp0rm+YQQwsrF0QE4ysp9ZwisXYWA6p7F/2Snd8M3QyAtEQ7/CffOg9pBxf+8QghBPq/olVIDlVIHlFKHlVLP57J+rFIqVikVYf0aZ7Mu22b5YnsGX1hxKemEHz9fMnXnzx2GbwaDa2UYMQ+UE8y6GfYvLf7nFkII8nFFr5RyBj4D+gHRwDal1GKt9d4cm87XWk/M5RAXtdbtix6q/azafxaLpvgTfUIUfH0HaA33/QJ+zaFOMMwdAfPuhf5vQteJIIXUhBDFKD9X9J2Aw1rrSK11BjAPuKN4wypeK/aeoU5VD1rXqVJ8T5Jy1iT59GQYvdAkeQDvWjD2Nwi8HZa/DL8+CdmZxReHEKLCy0+irwtE2TyOti7LaahS6m+l1AKlVD2b5R5KqTCl1Gal1ODcnkApNcG6TVhsbGz+oy+EixnZrDsUS9/AmsVXkvjiedMmn3wKRv54dXu8mycMmw09nobw2fDtULOPEEIUA3v1ulkCNNRatwNWAHNs1jXQWocC9wIfKaWa5NxZaz1dax2qtQ718/OzU0i523D4HGmZluJrtklPhm+HwbmDMPw7qN859+2cnKDPKzB4GhzfCDP7Q3xk8cQkhKjQ8pPoYwDbK/QA67LLtNZxWut068MvgQ4262Ks3yOBNUBwEeItshV7z+Dt7kLnRr72P3hmmml7P7kDhn0FTW66/j7t7zXt9xdiYUYfk/SFEMKO8pPotwHNlFKNlFJuwHDgit4zSinb0o+3A/usy6srpdytP9cAugM5b+KWmGyLZtX+M/Rs4Yebi52HEGRnwo9j4ehaGPw/aDUo//s27A7jVoGnj2nX3znPvrEJIQpHazi9CyzZjo6kSK6b7bTWWcBE4A9MAv9Ba71HKfWGUup262aTlFJ7lFI7gUnAWOvyVkCYdflq4N1ceuuUmIio85xLybB/s40lGxY9DAeXwS3/haDhBT+GbxN4cAXU6wyLHoJVb4LFYt84hRAFs34KfH6D6ThRhuVrwJTWeimwNMeyV2x+fgF4IZf9NgJtixij3SwvjiJmWsNvT8HuBdDnVeg0vvDH8vSBUQvN8db9F+KPmDZ810r2i1cIe0pPhpMRZuR3TBic3Q8Nb4BOE6BmoKOjK5o9i2DV6+BdBzb/D+p2gLbDHB1VoVSokbEr956hS2Nf+xUx0xpW/Nv0nLnhKejxVNGP6eIGt38CNZrBilch4QT0fR3qdwXnCvXrEqVNdiac3WtN6uEQHQ6x+wFt1ldvBL5NYedcCP8KGvYwFz4tbi17f7tR22DhQ1CvC4xaAN/dBYsfB/9WULO1o6MrsDJ29gvvUhGz+7o2vHJFVgbo7MJdNa/9L2z8BDqONz1o7EUp6P4E+DQxzThzBoGnL7S4GVrdDo16gquH/Z4PzHlQCpylkqewOn8cordBzHaT2E/thKyLZl0lHwgIhdaDzZVu3Q7mEylAajxs/xq2zYQf7oMqAdDxAQgZA5VrOO715Nf5YzB3OFSpA8O/B3dvuGs2fHEjzB8F41dDpWqOjrJAlNba0TFcITQ0VIeFhdn9uF/8dYR3lu1n/XO9/6lvk50Jn/eA2H3gUc38YqvUAe/auX/39P1nFOvmz+H356DdcNO84lRM9eHSU+DwSti3BA4th/QkcPOCZv3NDd9m/c0fYkFobbpyXroyiwmHU3+DT2MYvwrcZJL0Ci9sFvw62fzs4mHGglxK6HU7QPWG1x/RbcmGg7/Dli/g6F/g7A5thpqr/Lohxf4SCuViAszsZwY8jltpPllfcmIzzL4VmvaF4XOL73++kJRS4dau7FevqyiJfti0jaRmZLP0iR7/LNwyHZb9Czo9ZK7qk05B8klIOml+0eQ4N85uJul7+ZsrnZaD4K45JfexNCvd9OrZtwQOLDVdMp3doXEvaHUbtLgFKufSbfTCOZuP22Hme1qCWefqCbXbmz/o7V9DyGjTdCSKR8aFf9q0z+wxV8VBwwv+Zl2czuyB6b2hQVfTbFizddE/6cUegK3TIWIuZF6AgI7m/y7wDtNcWRpkZcB3Q+H4Jhi9CBr1uHqbLV/Asmeh90vQ89mSj/EaKnyiP5eSTsf/rGTSTc2Y3M9aiiAtEaa2h1ptTT/2nFcn2ZmQcsYm+Z+CpBgz2jXpFPg0gls/ABd3u8aab5ZsiNoC+341iT/xhCmY1qA7tLzVrL+U3BOOm32UE/gHmqupS1dmfq3+eaNa+ZrpZXDXbGg9xDGvqzzJzjJt2JduVMZsN23c2tqbytMXUuPAvYoZT9FxPNRo6tiYM1Jhxk0mrkc2gpedBzCmJZpkv3W66WxQ2R9C7zev3d7PVRBaw+KJsONbGPw5tB+R93YLJ8CuH82o92b9SjbOa6jwif6HsCieXfA3vz5+A23qVjULV7wKG6bCQ2uhdju7Pl+J0xpO//1P0o/dZ5ZXrX9lUq/T/trNMtmZMGuAqbj5yHqoVr9k4i8PtIbEaGtCDzdJ/eQOyEw16z2qXdn0UbeDaa+ODoOtX8Cen8GSCU36mB4rzfo7pmng18mm2WbUQmjap/iex2KByD/Np+pDy8GjCvR/C4JHO6bI37oPTQ+bG5+Fm1669rYZqWYke2IUTFhjLvpKgQqf6Md/HcaemEQ2PH+TqW9z/jh82tG0Fw6ZZtfnKhXOHwOXSuBdiPEC8UfNfYuagTB2adnrLVFcMi7k8enupPmecMI0pYFpTqvd7sqk7tP42gks+YzpvRU2C1JOmzbwjuMheCRUql4SrxD2LoYfRkO3SaayakmJPQBLnoQTG01PndummnElJWXPIjPYsc0wGPpl/t5o4iNhei9zMfTAclO/ysEqdKK/mJFN8JvLuTu0Hm/c0cYs/GmcufJ9fDtUza0+WwX394+wcBz0fA56v+joaEpWYgxsn2O+2zbVpSdeva17VahS29y3qVrX3Ouo2wFqtil8u3N2JuxbDFtnwIlN5h5Ku7ut/dKLsVtfYjRM626uTh9YXvLt5hYL7Pgalr8CWWmm/bvbpOKPI2qbucFaJ9g04RakN9vB5fD93dDuHhjyucPLjV8r0Zf7y7X1OYuYxYSb9rUez0iSz0u7u+DIn7D2/6DRjWYATEWQnWm61Z3ZDV61TBL3bWrOQW49sdy97B+Ds6v5pNlmqOnOuHWGKYkRPhsa3ACdJ9i/X7olG34aD5YsGDrTMTdHnZygw1hoPtDc7PzzTdj9k+kYEJBr7iq6nN0oC9pluXl/6PU8rHnHxFiUwZLFrNxf0T+7YCfLdp0m/N/9cHNW5t373EGYtKN09XQobdKT4Yue5urq4fX/9JEuz9a8a/5ph39vbmiXFqnxsOMb2PalaSKqEwIj5pq5DexhzXuw5m0Y8kXhyncUh/1L4benzSeqThOgz7/t+/96rW6UBWGxwLwRpgv02KV5V6stAde6oi9dHUHtLNuiWbXvLL1a+psiZgeWwvEN0OsFSfLX4+4Nw2aaf4TFj5ubjeXZyQjzCabdPaUryYN5k+3+BEyKgDu/NG3aM/qYYltFdXwT/PWued2lJckDtLwFHtsCHceZHjqfdYEDv9vn2FkZ5l5E/FG459vCJ3kwn0SGfAFV65nBYcln7BOjnZXrRB8RdZ64C9YiZtmZsOIVqNHcjNAT11cnGPq+Cvt/NTcJy6usdPj5UfCsATe/5+ho8ubkbJrVHvjddNGcNRAO/lH44108DwvHQ7UGphhfaeNRBW79Lzy43Fx4zL0HfrzfOsalkLSG3yab8Si3f5J7X/mCqlTNvGGkJZqbuqVwxrhynegvFTHr2dzPtHHGHYZ+b0pPkoLo8pjp8vfHi3DGYYVHi9df78HZPeYfv6R6uBRF7XYw/k9z/2DucNg8reCfuLSGxZNM08iwmSapllb1Oplu0L1fMhcdn4aawX2F+ZS5forpK3/js3n3lS+MWm3M38+JjbD83/Y7rp2U64y34lIRM5Vq2l4b9oDmAxwdVtni5GR6FEzrBj89aBJMeaqmGRNu/vmDR5mba2VFldpw/1IzeOf35+HcIbj5/fxfxGyfY3r39H3d9BQq7VzcTE+cwMGw5AnTnLj67YINWNTaDB5sM6x4epO1u8uMo9gyzdycLUWVLsttoj8Sm0Jk7AXGdG1o/pFT48yADAd3gSqTvPxNsv92qKnLfesHjo7IPjLTYNEjpgztgLcdHU3BuVWGu78xA302fATnj5pRzR5Vr71f7AFY9rwpndFtUgkEakd+zWHsbxDxHRxbV/D9Ww8x9+iKKw/0f8vUjfplounN1KCrab93cN4pt4l+5V5zU2RAQCbM+Z8pPlanvYOjKsOa9oWuE2HTp9C4d8Fm0CqtVv8Hzh0wdU2ulxxLKycn6Pe6acb59UkzYvPe+WbAVW4y02DBA+ZNYsgXpa4wV744OZmaTCGjHR3J1ZxdzZvtzL6waIJZVtnfZvBciPkq4SbCcpvoV+w9Q2DtKtQK+z/zbnpT2Z4hplTo8yocW29qgtQJLtvjEE5sMSWmO9yfv7l9S7uQ0VC9AcwfbXrkDP8+965+K14x4wTu/dF+3TPFlbxrwsRwc55tK8QeXPbPNr5NbZJ/qGnjL8a6WeWyH/2lImZvdcpi5M77zKQgfV+1U4QVXNwRUyKhTjCMWWx6ghSnzDRT4vbIapOQ7dGOnpFqpoezZJrCXeWpq+25w/D9XWZk7x2fmXbjSw4sMzdvuzwKA99xXIwVVVriP7X9Y7ab9vwUa3dMJ1dTYLHJTWbMQCFUuJGxf+47i9aaO85OM13mbpjs6JDKD98mpo3+54dNIaie/7L/c6Qnm0JX+3413zNSTOXNLdNML6C+rxVt9OaqN0zlxDFLyleSB1P9ctwqM0HGwnGmp1mv5yH5tOlCWqutOX+i5HlUhSa9zReYm8NJMTZX/dvN76sYlMtEv2LfGe723oPXqU2mf3Bp7jpWFgUNNyUS1rxjygPYYzTghTgzoG3fEohcA9npUNnPlAJodZuZNP3Pt2DzZ6YGzLBZhasaeGy9ecPoNMHEXh55+pj7DkueNIOh4g7DhbNmlPOwrxxXWltcSSmoGmC+Au8o3qcqb003FzOy6fjmUlZ7voiflzs8ukmmxysOaUnwRQ8zlLxOe6hS11oHprbpxXLpe2W/vG/4JUabq/b9v5oRy9piSiu3us3c7K3X+eqmob2LzT0CrU2/5daD8x9zeorpJqqc4JEN5X8mLa1h/YfmEwzA7Z+WzhuYwi4qVNPN+sPnGGxZhV/6CRgyV5J8cfGoYm74/fWeSdhHVpv2Rp195XZOLuYNwPZNwM3TfCI4ucNs49cKejxtEnytdtfuihZ4u5nWbsED8OMYOPqg6RqZn4JUK62Trd+/rPwneTDnscfTZrKZc4fMWAFRIZW7K/p/z9/Ik3vvoXqDtjjd/5vD+69WKJZsMzz9Us32ZGvddts67smnTJt73VBz1d7ytsLNqpSdaa5UN34MNdvCXV9du2ZJ5Br4+g7TRXTAfwr9EoUorSrMFX22RdNw/wx8VRIMkMFRJc7J2Vy1V6kN1+p5mZVR9FK4zq5mcoyGPWDRQ6bS5qApEHTP1dumJZkBLL7NpJutqJDK4GiJvO3Zt4eRliVE17ut9M4yL+xb77x5f1NGuXaQGaDy82NmNihby18ynywGTytf5RuEyKdylejV6v+ggKqD3nB0KKIkVa1rukre+C8zNH7GTXDWOm/uoZWmAFa3SVCvo2PjFMJB8pXolVIDlVIHlFKHlVLP57J+rFIqVikVYf0aZ7NujFLqkPWr+OoDnztM63PLWF7lTrxrNi62pxGllLOLaZYZvchM1DG9N2z5whS/8mtV8aZEFMLGddvolVLOwGdAPyAa2KaUWqy1zlmzdr7WemKOfX2AV4FQQAPh1n3P2yV6GydUHV7OeJaBobfZ+9CiLGnS2zTlLBxvpqRTzjDie+k7Liq0/NyM7QQc1lpHAiil5gF3APkpTj4AWKG1jrfuuwIYCMwtXLh5q+/ryVtPP0mVSuXq/rIoDO+a5sp+6wwzGrFOsKMjEsKh8pMVuhwNxwAAA+RJREFU6wJRNo+jgdyGQg5VSt0IHAQma62j8tj3qv4YSqkJwASA+vXr5y/yXNT39Sz0vqKccXKGLg87OgohSgV73YxdAjTUWrcDVgBzCrKz1nq61jpUax3q5+dnp5CEEEJA/hJ9DFDP5nGAddllWus4rXW69eGXQIf87iuEEKJ45SfRbwOaKaUaKaXcgOHAYtsNlFK1bR7eDlj7tvEH0F8pVV0pVR3ob10mhBCihFy3jV5rnaWUmohJ0M7ALK31HqXUG0CY1noxMEkpdTuQBcQDY637xiul3sS8WQC8cenGrBBCiJJR7mrdCCFERXStWjflamSsEEKIq0miF0KIck4SvRBClHOlro1eKRULHC/CIWoA5+wUTlkm58GQ82DIeTDK83looLXOdSBSqUv0RaWUCsvrhkRFIufBkPNgyHkwKup5kKYbIYQo5yTRCyFEOVceE/10RwdQSsh5MOQ8GHIejAp5HspdG70QQogrlccreiGEEDYk0QshRDlXbhL99ea1rSiUUseUUrusc/dWqKJBSqlZSqmzSqndNst8lFIrrHMWr7BWUS3X8jgPrymlYmzmdb7FkTGWBKVUPaXUaqXUXqXUHqXUE9blFe5volwkept5bW8GAoERSqlAx0blUL211u0rYH/h2ZipKm09D6zSWjcDVlkfl3ezufo8AEyx/l2011ovLeGYHCELeFprHQh0AR6z5oUK9zdRLhI9NvPaaq0zgEvz2ooKRGu9FlMm29Yd/DPj2RxgcIkG5QB5nIcKR2t9Smu93fpzMmaejLpUwL+J8pLo8zU3bQWhgeVKqXDrXLwVXU2t9Snrz6eBmo4MxsEmKqX+tjbtlPvmCltKqYZAMLCF/2/vflUiiKI4jn9PMKmvYNAXEPOGfQWLdaPBYraYjIrNIEYVBP++go+gYLWI7Ea7+zPcu+wirjYHzv19ygwzLFyGw4/hcHdOgzWRJehtqidpg9LG2qkD2w1Q2Uvc6n7iE2ANWAfegcNul/N/ImIJuAZ2JX3M3mulJrIEvWfTVpLe6nEE3FLaWi0bTkZd1uOo4/V0QtJQ0qekMXBKI3UREQuUkD+XdFMvN1cTWYL+z7m2LYiIxYhYnpxTZvQ+//6r9B6AQT0fAPcdrqUz3+Y6b9JAXUREAGfAi6SjmVvN1USaf8bW7WLHTOfaHnS8pH8XEauUt3go84AvWnoOEXEJ9Cmfoh0C+8AdcAWsUD5/vZV9bvGc59CntG0EvALbM33qlCKiBzwCT8C4Xt6j9OnbqoksQW9mZj/L0roxM7M5HPRmZsk56M3MknPQm5kl56A3M0vOQW9mlpyD3swsuS8j1KHBPhOsbQAAAABJRU5ErkJggg==\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# plt.subplot(2, 1, 1)\n",
+    "plt.title('Training and test accuracy')\n",
+    "plt.plot(params.epoch, params.history['accuracy'], label='Training accuracy')\n",
+    "plt.plot(params.epoch, params.history['val_accuracy'], label='Test accuracy')\n",
+    "plt.legend()\n",
+    "plt.show()\n",
+    "\n",
+    "# plt.subplot(2, 1, 2)\n",
+    "plt.title('Training and test loss')\n",
+    "plt.plot(params.epoch, params.history['loss'], label='Training loss')\n",
+    "plt.plot(params.epoch, params.history['val_loss'], label='Test loss')\n",
+    "plt.legend()\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Sample prediction"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "predict with test number:  92\n",
+      "./img_data/resized/Negative/3838087_landsat_7_rgb.tif\n",
+      "0.5856288   :   (0, 'Negative')\n",
+      "0.41437116   :   (1, 'Positive')\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Randomly test an image from the test set\n",
+    "\n",
+    "# model.load_weights('dog_breed_classifier.h5')\n",
+    "\n",
+    "imageno=np.random.random_integers(low=0, high=test_generator.samples)\n",
+    "print('predict with test number: ', imageno)\n",
+    "\n",
+    "name = test_generator.filepaths[imageno]\n",
+    "print(name)\n",
+    "plt.imshow(mpimg.imread(name))\n",
+    "\n",
+    "img = Image.open(test_generator.filepaths[imageno]).resize((targetx, targety))\n",
+    "probabilities = model.predict(preprocess_input(np.expand_dims(img, axis=0)))\n",
+    "breed_list = tuple(zip(test_generator.class_indices.values(), test_generator.class_indices.keys()))\n",
+    "\n",
+    "for i in probabilities[0].argsort()[-5:][::-1]: \n",
+    "    print(probabilities[0][i], \"  :  \" , breed_list[i])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Sample for paper test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.5856288   :   (0, 'Negative')\n",
+      "0.41437116   :   (1, 'Positive')\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# path for landslide \n",
+    "#./data/reized/WithLandslide/25_94_Large_cropped_6.TIF\n",
+    "# ./data/reized/WithLandslide/44_-123_Large_cropped_4.TIF\n",
+    "# ./imgtest/27.770733_85.868467_VERY_LARGE_cropped_LC08_L1TP_141041_20130915_20170502_01_T1.TIF\n",
+    "# ./imgtest/27.770733_85.868467_VERY_LARGE_cropped_LC08_L1TP_141041_20140918_20170419_01_T1.TIF\n",
+    "img_test = Image.open(test_dir + \"27.770733_85.868467_VERY_LARGE_cropped_LC08_L1TP_141041_20140918_20170419_01_T1.TIF\").resize((targetx, targety))\n",
+    "plt.imshow(img_test,origin='lower')\n",
+    "probabilities = model.predict(preprocess_input(np.expand_dims(img, axis=0)))\n",
+    "breed_list = tuple(zip(test_generator.class_indices.values(), test_generator.class_indices.keys()))\n",
+    "\n",
+    "for i in probabilities[0].argsort()[-5:][::-1]: \n",
+    "    print(probabilities[0][i], \"  :  \" , breed_list[i])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Classification report"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From <ipython-input-14-6c336b480794>:2: Model.predict_generator (from tensorflow.python.keras.engine.training) is deprecated and will be removed in a future version.\n",
+      "Instructions for updating:\n",
+      "Please use Model.predict, which supports generators.\n",
+      "Classification Report\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "    Negative       0.56      0.56      0.56       252\n",
+      "    Positive       0.56      0.56      0.56       250\n",
+      "\n",
+      "    accuracy                           0.56       502\n",
+      "   macro avg       0.56      0.56      0.56       502\n",
+      "weighted avg       0.56      0.56      0.56       502\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "test_generator.reset()\n",
+    "predictions = model.predict_generator(test_generator, steps=len(test_generator))\n",
+    "y = np.argmax(predictions, axis=1)\n",
+    "\n",
+    "print('Classification Report')\n",
+    "cr = classification_report(y_true=test_generator.classes, y_pred=y, target_names=test_generator.class_indices)\n",
+    "print(cr)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Confusion matrix"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Confusion Matrix\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x7f8d7a5e6c50>"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 5760x5760 with 2 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "print('Confusion Matrix')\n",
+    "cm = confusion_matrix(test_generator.classes, y)\n",
+    "df = pd.DataFrame(cm, columns=test_generator.class_indices)\n",
+    "plt.figure(figsize=(80,80))\n",
+    "sn.heatmap(df, annot=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Reference: \n",
+    "## Transfer learning with Keras and MobileNet V2\n",
+    "#### https://www.kaggle.com/devang/transfer-learning-with-keras-and-mobilenet-v2/"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "viplab-gpu",
+   "language": "python",
+   "name": "viplab-gpu"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}