diff --git a/tutorials/EEG_test.ipynb b/tutorials/EEG_test.ipynb
index 33b1984..c3fb0e2 100644
--- a/tutorials/EEG_test.ipynb
+++ b/tutorials/EEG_test.ipynb
@@ -1,26 +1,28 @@
 {
  "cells": [
   {
-   "metadata": {},
    "cell_type": "markdown",
+   "id": "f4666ce8cbcbde16",
+   "metadata": {},
    "source": [
     "# 1. Baseline\n",
     "classify for math and relax in synchronized_brainwave_dataset data"
-   ],
-   "id": "f4666ce8cbcbde16"
+   ]
   },
   {
+   "cell_type": "code",
+   "id": "bfa03c740f88b2cf",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T16:06:14.850086Z",
-     "start_time": "2024-06-27T16:06:14.842922Z"
+     "end_time": "2024-06-29T15:09:15.763595Z",
+     "start_time": "2024-06-29T15:09:10.626692Z"
     }
    },
-   "cell_type": "code",
    "source": [
     "import numpy as np\n",
     "import pandas as pd\n",
     "import tensorflow as tf\n",
+    "import matplotlib.pyplot as plt\n",
     "from sklearn.model_selection import train_test_split\n",
     "from sklearn.preprocessing import LabelEncoder\n",
     "from tensorflow.keras.models import Sequential\n",
@@ -28,23 +30,27 @@
     "from tensorflow import keras\n",
     "import tsgm\n",
     "from tsgm.models.architectures.zoo import zoo  \n",
+    "from tensorflow.keras.utils import to_categorical\n",
     "import ast\n",
     "%matplotlib inline"
    ],
-   "id": "bfa03c740f88b2cf",
    "outputs": [],
-   "execution_count": 131
+   "execution_count": 1
   },
   {
+   "cell_type": "code",
+   "id": "5f881b19b73f321e",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T14:13:01.605634Z",
-     "start_time": "2024-06-27T14:13:00.884414Z"
+     "end_time": "2024-06-29T15:09:16.505307Z",
+     "start_time": "2024-06-29T15:09:15.764563Z"
     }
    },
-   "cell_type": "code",
-   "source": "X, y = tsgm.utils.get_synchronized_brainwave_dataset()",
-   "id": "5f881b19b73f321e",
+   "source": [
+    "X, y = tsgm.utils.get_synchronized_brainwave_dataset()\n",
+    "print('feature shape in total data:',X.shape)\n",
+    "print('label shape in total data:',y.shape)"
+   ],
    "outputs": [
     {
      "name": "stderr",
@@ -52,79 +58,42 @@
      "text": [
       "INFO:utils:File exist\n"
      ]
-    }
-   ],
-   "execution_count": 68
-  },
-  {
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-06-27T12:22:25.067208Z",
-     "start_time": "2024-06-27T12:22:25.062306Z"
-    }
-   },
-   "cell_type": "code",
-   "source": "X.shape",
-   "id": "dcc46df65a801df9",
-   "outputs": [
+    },
     {
-     "data": {
-      "text/plain": [
-       "(30013, 12)"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "feature shape in total data: (30013, 12)\n",
+      "label shape in total data: (30013,)\n"
+     ]
     }
    ],
-   "execution_count": 3
+   "execution_count": 2
   },
   {
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-06-27T12:22:27.924038Z",
-     "start_time": "2024-06-27T12:22:27.920191Z"
-    }
-   },
    "cell_type": "code",
-   "source": "y.shape",
-   "id": "900328101a606991",
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "(30013,)"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "execution_count": 4
-  },
-  {
+   "id": "a380d2f85b0a7235",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T14:13:04.386050Z",
-     "start_time": "2024-06-27T14:13:03.650020Z"
+     "end_time": "2024-06-29T15:09:17.235969Z",
+     "start_time": "2024-06-29T15:09:16.506146Z"
     }
    },
-   "cell_type": "code",
-   "source": "df = pd.read_csv(\"../data/synchronized_brainwave_dataset.csv\")",
-   "id": "a380d2f85b0a7235",
+   "source": [
+    "df = pd.read_csv(\"../data/synchronized_brainwave_dataset.csv\")"
+   ],
    "outputs": [],
-   "execution_count": 69
+   "execution_count": 3
   },
   {
+   "cell_type": "code",
+   "id": "c4a62977f983c13e",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T14:13:04.405794Z",
-     "start_time": "2024-06-27T14:13:04.390517Z"
+     "end_time": "2024-06-29T15:09:17.253091Z",
+     "start_time": "2024-06-29T15:09:17.237400Z"
     }
    },
-   "cell_type": "code",
    "source": [
     "# we want to classify label 'relax' and 'math'\n",
     "relax = df[df.label == 'relax']\n",
@@ -141,56 +110,60 @@
     "          (df.label == 'math11') |\n",
     "          (df.label == 'math12') ]\n",
     "\n",
-    "print(len(relax))\n",
-    "print(len(math))"
+    "print('length of relax data:',len(relax))\n",
+    "print('length of math data',len(math))"
    ],
-   "id": "c4a62977f983c13e",
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "934\n",
-      "936\n"
+      "length of relax data: 934\n",
+      "length of math data 936\n"
      ]
     }
    ],
-   "execution_count": 70
+   "execution_count": 4
   },
   {
+   "cell_type": "code",
+   "id": "4f7830db118c92f8",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T14:13:07.562480Z",
-     "start_time": "2024-06-27T14:13:07.557639Z"
+     "end_time": "2024-06-29T15:09:17.256317Z",
+     "start_time": "2024-06-29T15:09:17.253958Z"
     }
    },
-   "cell_type": "code",
-   "source": "relax_math = pd.concat([relax, math], axis=0)",
-   "id": "4f7830db118c92f8",
+   "source": [
+    "relax_math = pd.concat([relax, math], axis=0)"
+   ],
    "outputs": [],
-   "execution_count": 71
+   "execution_count": 5
   },
   {
+   "cell_type": "code",
+   "id": "8ec9a86b566b3d04",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T14:13:16.681813Z",
-     "start_time": "2024-06-27T14:13:15.701182Z"
+     "end_time": "2024-06-29T15:09:18.385911Z",
+     "start_time": "2024-06-29T15:09:17.256958Z"
     }
    },
-   "cell_type": "code",
-   "source": "relax_math['raw_values'] = relax_math['raw_values'].apply(ast.literal_eval)\n",
-   "id": "8ec9a86b566b3d04",
+   "source": [
+    "relax_math['raw_values'] = relax_math['raw_values'].apply(ast.literal_eval)"
+   ],
    "outputs": [],
-   "execution_count": 72
+   "execution_count": 6
   },
   {
+   "cell_type": "code",
+   "id": "ce5226398f21e70e",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T14:13:20.237134Z",
-     "start_time": "2024-06-27T14:13:20.195199Z"
+     "end_time": "2024-06-29T15:09:18.414664Z",
+     "start_time": "2024-06-29T15:09:18.386726Z"
     }
    },
-   "cell_type": "code",
    "source": [
     "# A signal values over 128 indicate that the headset was placed incorrectly.\n",
     "relax_math = relax_math[relax_math['signal_quality'] < 128]\n",
@@ -206,142 +179,124 @@
     "label_encoder = LabelEncoder()\n",
     "relax_math['label'] = label_encoder.fit_transform(relax_math['label'])\n",
     "\n",
-    "features_matrix = np.stack(relax_math['raw_values'].values)\n"
+    "features_matrix = np.stack(relax_math['raw_values'].values)"
    ],
-   "id": "ce5226398f21e70e",
    "outputs": [],
-   "execution_count": 73
+   "execution_count": 7
   },
   {
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-06-27T14:13:52.254759Z",
-     "start_time": "2024-06-27T14:13:52.249268Z"
-    }
-   },
    "cell_type": "code",
-   "source": "# relax_math['label']",
-   "id": "4b2d5582ccec0bfb",
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "13274    1\n",
-       "13275    1\n",
-       "13276    1\n",
-       "13277    1\n",
-       "13278    1\n",
-       "        ..\n",
-       "23828    0\n",
-       "23829    0\n",
-       "23830    0\n",
-       "23831    0\n",
-       "23832    0\n",
-       "Name: label, Length: 1870, dtype: int64"
-      ]
-     },
-     "execution_count": 74,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "execution_count": 74
-  },
-  {
+   "id": "144eb81613c4c5ee",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T14:14:52.758126Z",
-     "start_time": "2024-06-27T14:14:52.736563Z"
+     "end_time": "2024-06-29T15:09:18.425759Z",
+     "start_time": "2024-06-29T15:09:18.415508Z"
     }
    },
-   "cell_type": "code",
    "source": [
-    "X = relax_math['raw_values']\n",
+    "# we choose column 'raw_values' as our feature for label\n",
+    "X = features_matrix\n",
     "y = relax_math['label']"
    ],
-   "id": "144eb81613c4c5ee",
    "outputs": [],
-   "execution_count": 75
+   "execution_count": 8
   },
   {
+   "cell_type": "code",
+   "id": "49fdd39e1fb6aa41",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T14:25:40.980508Z",
-     "start_time": "2024-06-27T14:25:40.977671Z"
+     "end_time": "2024-06-29T15:09:18.428971Z",
+     "start_time": "2024-06-29T15:09:18.426759Z"
     }
    },
-   "cell_type": "code",
    "source": [
-    "print(relax_math.shape)\n",
-    "print(X.shape)\n",
-    "print(y.shape)\n",
-    "print(X.index)\n",
-    "print(X[13274].shape)"
+    "# print('data shape:', relax_math.shape)\n",
+    "print('feature shape:', X.shape)\n",
+    "print('label shape:', y.shape)\n",
+    "# print(X.head())"
    ],
-   "id": "49fdd39e1fb6aa41",
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "(1870, 13)\n",
-      "(1870,)\n",
-      "(1870,)\n",
-      "Index([13274, 13275, 13276, 13277, 13278, 13279, 13280, 13281, 13282, 13283,\n",
-      "       ...\n",
-      "       23823, 23824, 23825, 23826, 23827, 23828, 23829, 23830, 23831, 23832],\n",
-      "      dtype='int64', length=1870)\n",
-      "(512,)\n"
+      "feature shape: (1870, 512)\n",
+      "label shape: (1870,)\n"
      ]
     }
    ],
-   "execution_count": 87
+   "execution_count": 9
   },
   {
+   "cell_type": "code",
+   "id": "894e15a5f35baa30",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T15:56:35.890089Z",
-     "start_time": "2024-06-27T15:56:35.886829Z"
+     "end_time": "2024-06-29T15:09:18.433229Z",
+     "start_time": "2024-06-29T15:09:18.431536Z"
     }
    },
+   "source": [
+    "# features_matrix"
+   ],
+   "outputs": [],
+   "execution_count": 10
+  },
+  {
    "cell_type": "code",
-   "source": "features_matrix",
-   "id": "894e15a5f35baa30",
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array([[285., 241., 200., ...,  32.,  23.,  21.],\n",
-       "       [-12., -60., -70., ...,  20.,  19.,  -7.],\n",
-       "       [ 37.,  43.,  42., ...,  18.,  13.,  35.],\n",
-       "       ...,\n",
-       "       [106., 108.,  91., ...,  28.,  42.,  49.],\n",
-       "       [ 48.,  37.,  18., ...,  49.,  42.,  26.],\n",
-       "       [ 96.,  75.,  64., ...,  71.,  86.,  92.]])"
-      ]
-     },
-     "execution_count": 127,
-     "metadata": {},
-     "output_type": "execute_result"
+   "id": "9e386478eab9c192",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-06-29T15:09:18.437819Z",
+     "start_time": "2024-06-29T15:09:18.433993Z"
     }
+   },
+   "source": [
+    "# Split data\n",
+    "X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)"
    ],
-   "execution_count": 127
+   "outputs": [],
+   "execution_count": 11
   },
   {
+   "cell_type": "code",
+   "id": "c517bd23f4e1cd33",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T15:30:36.836796Z",
-     "start_time": "2024-06-27T15:30:36.807882Z"
+     "end_time": "2024-06-29T15:09:18.440060Z",
+     "start_time": "2024-06-29T15:09:18.438708Z"
     }
    },
+   "source": [],
+   "outputs": [],
+   "execution_count": 11
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9a67b9581ae4d63e",
+   "metadata": {},
+   "source": [
+    "## 1.2 Time series model"
+   ]
+  },
+  {
    "cell_type": "code",
+   "id": "cae5dc7dddfb509f",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-06-29T15:09:18.474784Z",
+     "start_time": "2024-06-29T15:09:18.440738Z"
+    }
+   },
    "source": [
-    "# time series model\n",
-    "\n",
-    "seq_len = 64  # Number of timesteps per sequence\n",
-    "feat_dim = 8  # Number of features per timestep\n",
+    "seq_len = 8  # Number of timesteps per sequence\n",
+    "feat_dim = 64  # Number of features per timestep\n",
     "output_dim = 2  # Number of output classes\n",
     "\n",
+    "X_train_ts = X_train.reshape(-1, seq_len, feat_dim) \n",
+    "X_val_ts = X_val.reshape(-1, seq_len, feat_dim)\n",
+    "\n",
     "model_ts_architecture = zoo['clf_cn'](seq_len, feat_dim, output_dim)\n",
     "model_ts = model_ts_architecture.model\n",
     "\n",
@@ -349,402 +304,661 @@
     "    optimizer='adam',\n",
     "    loss='sparse_categorical_crossentropy', \n",
     "    metrics=['accuracy']\n",
-    ")\n",
-    "\n",
-    "# Split data\n",
-    "X_train, X_val, y_train, y_val = train_test_split(features_matrix, relax_math['label'], test_size=0.2, random_state=42)\n",
-    "\n",
-    "X_train_ts = X_train.reshape(-1, seq_len, feat_dim) \n",
-    "X_val_ts = X_val.reshape(-1, seq_len, feat_dim)"
+    ")\n"
    ],
-   "id": "cae5dc7dddfb509f",
    "outputs": [],
-   "execution_count": 111
+   "execution_count": 12
   },
   {
+   "cell_type": "code",
+   "id": "fdf47499ec99cfdb",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T15:33:46.131734Z",
-     "start_time": "2024-06-27T15:33:44.932048Z"
+     "end_time": "2024-06-29T15:09:23.682727Z",
+     "start_time": "2024-06-29T15:09:18.475754Z"
     }
    },
-   "cell_type": "code",
    "source": [
     "# Model training\n",
     "history_ts = model_ts.fit(\n",
     "    X_train_ts, y_train,\n",
-    "    epochs=10,\n",
+    "    epochs=100,\n",
     "    batch_size=32,\n",
-    "    validation_data=(X_val_ts, y_val)\n",
+    "    validation_data=(X_val_ts, y_val),\n",
+    "    verbose=0\n",
     ")"
    ],
-   "id": "fdf47499ec99cfdb",
+   "outputs": [],
+   "execution_count": 13
+  },
+  {
+   "cell_type": "code",
+   "id": "f50b1aa7db9a102d",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-06-29T15:09:23.714237Z",
+     "start_time": "2024-06-29T15:09:23.683580Z"
+    }
+   },
+   "source": [
+    "val_loss_ts, val_acc_ts = model_ts.evaluate(X_val_ts, y_val)\n",
+    "print('val loss in ts model:', val_loss_ts)\n",
+    "print(\"val accuracy in ts model:\", val_acc_ts)"
+   ],
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch 1/10\n",
-      "47/47 [==============================] - 0s 3ms/step - loss: 0.6732 - accuracy: 0.5281 - val_loss: 0.6927 - val_accuracy: 0.4893\n",
-      "Epoch 2/10\n",
-      "47/47 [==============================] - 0s 2ms/step - loss: 0.6667 - accuracy: 0.5441 - val_loss: 0.7107 - val_accuracy: 0.4866\n",
-      "Epoch 3/10\n",
-      "47/47 [==============================] - 0s 2ms/step - loss: 0.6660 - accuracy: 0.5434 - val_loss: 0.7285 - val_accuracy: 0.4866\n",
-      "Epoch 4/10\n",
-      "47/47 [==============================] - 0s 2ms/step - loss: 0.6675 - accuracy: 0.5361 - val_loss: 0.7293 - val_accuracy: 0.4893\n",
-      "Epoch 5/10\n",
-      "47/47 [==============================] - 0s 2ms/step - loss: 0.6558 - accuracy: 0.5468 - val_loss: 0.7199 - val_accuracy: 0.4920\n",
-      "Epoch 6/10\n",
-      "47/47 [==============================] - 0s 2ms/step - loss: 0.6544 - accuracy: 0.5508 - val_loss: 0.7186 - val_accuracy: 0.4786\n",
-      "Epoch 7/10\n",
-      "47/47 [==============================] - 0s 2ms/step - loss: 0.6563 - accuracy: 0.5468 - val_loss: 0.7199 - val_accuracy: 0.5000\n",
-      "Epoch 8/10\n",
-      "47/47 [==============================] - 0s 2ms/step - loss: 0.6379 - accuracy: 0.5608 - val_loss: 0.7766 - val_accuracy: 0.4759\n",
-      "Epoch 9/10\n",
-      "47/47 [==============================] - 0s 2ms/step - loss: 0.6357 - accuracy: 0.5642 - val_loss: 0.8148 - val_accuracy: 0.4840\n",
-      "Epoch 10/10\n",
-      "47/47 [==============================] - 0s 2ms/step - loss: 0.6437 - accuracy: 0.5602 - val_loss: 0.7702 - val_accuracy: 0.4973\n"
+      "12/12 [==============================] - 0s 643us/step - loss: 2.0502 - accuracy: 0.6016\n",
+      "val loss in ts model: 2.050161123275757\n",
+      "val accuracy in ts model: 0.6016042828559875\n"
      ]
     }
    ],
-   "execution_count": 120
+   "execution_count": 14
   },
   {
+   "cell_type": "code",
+   "id": "1fabc7ac08ac7158",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T15:33:46.164397Z",
-     "start_time": "2024-06-27T15:33:46.132832Z"
+     "end_time": "2024-06-29T15:09:23.803015Z",
+     "start_time": "2024-06-29T15:09:23.715319Z"
     }
    },
-   "cell_type": "code",
    "source": [
-    "val_loss_ts, val_acc_ts = model_ts.evaluate(X_val_ts, y_val)\n",
-    "print('val loss in ts model:', val_loss_ts)\n",
-    "print(\"val accuracy in ts model:\", val_acc_ts)"
+    "# Plot training & validation loss values\n",
+    "plt.figure(figsize=(10, 5))\n",
+    "plt.plot(history_ts.history['loss'], label='Train Loss')\n",
+    "plt.plot(history_ts.history['val_loss'], label='Validation Loss')\n",
+    "plt.title('Model Loss')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.legend(loc='upper right')\n",
+    "plt.grid(True)\n",
+    "plt.show()"
    ],
-   "id": "f50b1aa7db9a102d",
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "12/12 [==============================] - 0s 760us/step - loss: 0.7702 - accuracy: 0.4973\n",
-      "val loss in ts model: 0.7702283263206482\n",
-      "val accuracy in ts model: 0.49732619524002075\n"
-     ]
+     "data": {
+      "text/plain": [
+       "<Figure size 1000x500 with 1 Axes>"
+      ],
+      "image/png": "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"
+     },
+     "metadata": {},
+     "output_type": "display_data"
     }
    ],
-   "execution_count": 121
+   "execution_count": 15
   },
   {
+   "cell_type": "code",
+   "id": "4d207133e91120cc",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T15:33:46.177316Z",
-     "start_time": "2024-06-27T15:33:46.165245Z"
+     "end_time": "2024-06-29T15:09:23.879069Z",
+     "start_time": "2024-06-29T15:09:23.803755Z"
     }
    },
+   "source": [
+    "# Plot training & validation accuracy values\n",
+    "plt.figure(figsize=(10, 5))\n",
+    "plt.plot(history_ts.history['accuracy'], label='Train Accuracy')\n",
+    "plt.plot(history_ts.history['val_accuracy'], label='Validation Accuracy')\n",
+    "plt.title('Model Accuracy')\n",
+    "plt.ylabel('Accuracy')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.legend(loc='lower right')\n",
+    "plt.grid(True)\n",
+    "plt.show()"
+   ],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Figure size 1000x500 with 1 Axes>"
+      ],
+      "image/png": "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"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "execution_count": 16
+  },
+  {
+   "cell_type": "markdown",
+   "id": "89a2dfdcd4ba5d98",
+   "metadata": {},
+   "source": [
+    "## 1.3 Sequential model"
+   ]
+  },
+  {
    "cell_type": "code",
+   "id": "c7b65afeabf81149",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-06-29T15:09:23.896207Z",
+     "start_time": "2024-06-29T15:09:23.879831Z"
+    }
+   },
    "source": [
     "model = Sequential([\n",
     "    Dense(10, activation='relu', input_shape=(max_len,)),\n",
-    "    Dense(3, activation='softmax')\n",
+    "    Dense(10, activation='relu'),\n",
+    "    Dense(1, activation='sigmoid')\n",
     "])\n",
     "\n",
     "model.compile(optimizer='adam', \n",
-    "              loss='sparse_categorical_crossentropy', \n",
+    "              loss='binary_crossentropy',\n",
+    "              # loss='sparse_categorical_crossentropy', \n",
     "              metrics=['accuracy'])"
    ],
-   "id": "c7b65afeabf81149",
    "outputs": [],
-   "execution_count": 122
+   "execution_count": 17
   },
   {
+   "cell_type": "code",
+   "id": "d3cac661d1539cde",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T15:33:46.682593Z",
-     "start_time": "2024-06-27T15:33:46.178476Z"
+     "end_time": "2024-06-29T15:09:26.865856Z",
+     "start_time": "2024-06-29T15:09:23.896822Z"
     }
    },
-   "cell_type": "code",
    "source": [
     "history = model.fit(\n",
     "    X_train, y_train,\n",
-    "    epochs=10,\n",
+    "    epochs=100,\n",
     "    batch_size=32,\n",
-    "    validation_data=(X_val, y_val)\n",
+    "    validation_data=(X_val, y_val),\n",
+    "    verbose=0\n",
     ")"
    ],
-   "id": "d3cac661d1539cde",
+   "outputs": [],
+   "execution_count": 18
+  },
+  {
+   "cell_type": "code",
+   "id": "2a74ef826b85b1bc",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-06-29T15:09:26.894687Z",
+     "start_time": "2024-06-29T15:09:26.866591Z"
+    }
+   },
+   "source": [
+    "val_loss, val_acc = model.evaluate(X_val, y_val)\n",
+    "print('val loss in normal model:', val_loss)\n",
+    "print(\"val accuracy in normal model:\", val_acc)"
+   ],
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch 1/10\n",
-      "47/47 [==============================] - 0s 2ms/step - loss: 27.6411 - accuracy: 0.4693 - val_loss: 13.5491 - val_accuracy: 0.4813\n",
-      "Epoch 2/10\n",
-      "47/47 [==============================] - 0s 760us/step - loss: 8.3371 - accuracy: 0.5087 - val_loss: 7.1260 - val_accuracy: 0.4626\n",
-      "Epoch 3/10\n",
-      "47/47 [==============================] - 0s 710us/step - loss: 4.5543 - accuracy: 0.5060 - val_loss: 4.3670 - val_accuracy: 0.4759\n",
-      "Epoch 4/10\n",
-      "47/47 [==============================] - 0s 711us/step - loss: 2.9879 - accuracy: 0.5033 - val_loss: 4.4653 - val_accuracy: 0.4840\n",
-      "Epoch 5/10\n",
-      "47/47 [==============================] - 0s 718us/step - loss: 2.5126 - accuracy: 0.5080 - val_loss: 4.0888 - val_accuracy: 0.5000\n",
-      "Epoch 6/10\n",
-      "47/47 [==============================] - 0s 739us/step - loss: 2.0560 - accuracy: 0.5120 - val_loss: 3.8600 - val_accuracy: 0.4893\n",
-      "Epoch 7/10\n",
-      "47/47 [==============================] - 0s 733us/step - loss: 2.1339 - accuracy: 0.5140 - val_loss: 3.7144 - val_accuracy: 0.5000\n",
-      "Epoch 8/10\n",
-      "47/47 [==============================] - 0s 750us/step - loss: 1.9127 - accuracy: 0.5154 - val_loss: 3.9637 - val_accuracy: 0.4947\n",
-      "Epoch 9/10\n",
-      "47/47 [==============================] - 0s 744us/step - loss: 1.3898 - accuracy: 0.5221 - val_loss: 2.7227 - val_accuracy: 0.5053\n",
-      "Epoch 10/10\n",
-      "47/47 [==============================] - 0s 729us/step - loss: 1.1935 - accuracy: 0.5201 - val_loss: 3.3667 - val_accuracy: 0.5000\n"
+      "12/12 [==============================] - 0s 472us/step - loss: 2.2675 - accuracy: 0.4973\n",
+      "val loss in normal model: 2.267547845840454\n",
+      "val accuracy in normal model: 0.49732619524002075\n"
      ]
     }
    ],
-   "execution_count": 123
+   "execution_count": 19
   },
   {
+   "cell_type": "code",
+   "id": "8621fe2128e0041e",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T15:33:46.709889Z",
-     "start_time": "2024-06-27T15:33:46.683357Z"
+     "end_time": "2024-06-29T15:09:26.968934Z",
+     "start_time": "2024-06-29T15:09:26.895330Z"
     }
    },
+   "source": [
+    "# Plot training & validation loss values\n",
+    "plt.figure(figsize=(10, 5))\n",
+    "plt.plot(history.history['loss'], label='Train Loss')\n",
+    "plt.plot(history.history['val_loss'], label='Validation Loss')\n",
+    "plt.title('Model Loss')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.legend(loc='upper right')\n",
+    "plt.grid(True)\n",
+    "plt.show()"
+   ],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Figure size 1000x500 with 1 Axes>"
+      ],
+      "image/png": "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"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "execution_count": 20
+  },
+  {
    "cell_type": "code",
+   "id": "ebb9591b7ca5c96a",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-06-29T15:09:27.048196Z",
+     "start_time": "2024-06-29T15:09:26.969739Z"
+    }
+   },
    "source": [
-    "val_loss, val_acc = model.evaluate(X_val, y_val)\n",
-    "print('val loss in normal model:', val_loss)\n",
-    "print(\"val accuracy in normal model:\", val_acc)"
+    "# Plot training & validation accuracy values\n",
+    "plt.figure(figsize=(10, 5))\n",
+    "plt.plot(history.history['accuracy'], label='Train Accuracy')\n",
+    "plt.plot(history.history['val_accuracy'], label='Validation Accuracy')\n",
+    "plt.title('Model Accuracy')\n",
+    "plt.ylabel('Accuracy')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.legend(loc='lower right')\n",
+    "plt.grid(True)\n",
+    "plt.show()"
    ],
-   "id": "2a74ef826b85b1bc",
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "12/12 [==============================] - 0s 455us/step - loss: 3.3667 - accuracy: 0.5000\n",
-      "val loss in normal model: 3.366678237915039\n",
-      "val accuracy in normal model: 0.5\n"
-     ]
+     "data": {
+      "text/plain": [
+       "<Figure size 1000x500 with 1 Axes>"
+      ],
+      "image/png": "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"
+     },
+     "metadata": {},
+     "output_type": "display_data"
     }
    ],
-   "execution_count": 124
+   "execution_count": 21
   },
   {
-   "metadata": {},
    "cell_type": "markdown",
+   "id": "711b16b767d9d67f",
+   "metadata": {},
    "source": [
     "# 2. Augmentations\n",
-    "augment X and y using GAN"
-   ],
-   "id": "711b16b767d9d67f"
+    "\n",
+    "augment X_train_ts and y_train using GAN"
+   ]
   },
   {
+   "cell_type": "code",
+   "id": "dc729243352e01d8",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T16:15:07.499787Z",
-     "start_time": "2024-06-27T16:15:07.496546Z"
+     "end_time": "2024-06-29T15:09:27.050794Z",
+     "start_time": "2024-06-29T15:09:27.048981Z"
     }
    },
-   "cell_type": "code",
    "source": [
-    "feature_dim = 8\n",
-    "seq_len = 64\n",
+    "seq_len = 8\n",
+    "feat_dim = 64\n",
     "batch_size = 128\n",
     "\n",
     "# generator_in_channels = latent_dim + output_dim\n",
     "# discriminator_in_channels = feature_dim + output_dim"
    ],
-   "id": "dc729243352e01d8",
    "outputs": [],
-   "execution_count": 139
+   "execution_count": 22
   },
   {
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T19:20:34.237328Z",
-     "start_time": "2024-06-27T19:20:34.234237Z"
+     "end_time": "2024-06-29T15:16:21.256451Z",
+     "start_time": "2024-06-29T15:16:21.254128Z"
     }
    },
    "cell_type": "code",
    "source": [
-    "# adjust its shape to series\n",
-    "X_ts = X.reshape(-1, seq_len, feat_dim) \n",
-    "X_ts.shape"
+    "print(X_train_ts.shape)\n",
+    "print(type(X_train_ts))"
    ],
-   "id": "2d1eb062a0c94ad1",
+   "id": "3c7f1bc66991ce9",
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "(1870, 64, 8)"
-      ]
-     },
-     "execution_count": 156,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(1496, 8, 64)\n",
+      "<class 'numpy.ndarray'>\n"
+     ]
     }
    ],
-   "execution_count": 156
+   "execution_count": 35
   },
   {
+   "cell_type": "code",
+   "id": "34ff743cd07c9274",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T19:27:28.227897Z",
-     "start_time": "2024-06-27T19:27:28.215404Z"
+     "end_time": "2024-06-29T15:23:25.066393Z",
+     "start_time": "2024-06-29T15:23:25.054620Z"
     }
    },
-   "cell_type": "code",
    "source": [
-    "# scaler = MinMaxScaler(feature_range=(-1, 1))\n",
-    "# X = np.stack(relax_math['raw_values'].apply(lambda x: scaler.fit_transform(x.reshape(-1, 1)).flatten()))\n",
-    "y = keras.utils.to_categorical(relax_math['label'], num_classes=2)\n",
-    "\n",
-    "scaler = tsgm.utils.TSFeatureWiseScaler((-1, 1))\n",
-    "X_train = scaler.fit_transform(X_ts)\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "# todo: do we need to scale X??\n",
+    "X_min = X_train_ts.min(axis=(0, 1), keepdims=True)\n",
+    "X_max = X_train_ts.max(axis=(0, 1), keepdims=True)\n",
     "\n",
-    "X_train = X_train.astype(np.float32)\n",
-    "y = y.astype(np.float32)\n",
+    "X_train_ts_scaled = 2 * ((X_train_ts - X_min) / (X_max - X_min)) - 1\n",
     "\n",
-    "print(X_train.shape)\n",
-    "print(y.shape)"
+    "# scaler = MinMaxScaler(feature_range=(-1, 1))\n",
+    "# X_train_ts_scaler = np.stack(X_train_ts.apply(lambda x: scaler.fit_transform(x.reshape(-1, 1)).flatten()))\n",
+    "X_train_ts_scaled_32 = X_train_ts_scaled.astype(np.float32)\n",
+    "y_train_32 = y_train.astype(np.float32)\n",
+    "y_train_onehot_32 = to_categorical(y_train, num_classes=output_dim)"
+   ],
+   "outputs": [],
+   "execution_count": 38
+  },
+  {
+   "cell_type": "code",
+   "id": "bb87871e2ccfd464",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-06-29T15:23:25.531325Z",
+     "start_time": "2024-06-29T15:23:25.529048Z"
+    }
+   },
+   "source": [
+    "print(X_train_ts_scaled_32.shape)\n",
+    "print(y_train_onehot_32.shape)"
    ],
-   "id": "98a7195f063f81bf",
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "(1870, 64, 8)\n",
-      "(1870, 2)\n"
+      "(1496, 8, 64)\n",
+      "(1496, 2)\n"
      ]
     }
    ],
-   "execution_count": 170
+   "execution_count": 39
   },
   {
+   "cell_type": "code",
+   "id": "2d1eb062a0c94ad1",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T19:27:28.855451Z",
-     "start_time": "2024-06-27T19:27:28.850230Z"
+     "end_time": "2024-06-29T15:09:27.060327Z",
+     "start_time": "2024-06-29T15:09:27.058168Z"
     }
    },
+   "source": [
+    "# adjust its shape to series\n",
+    "# X_np = X.to_numpy() \n",
+    "# X_ts = X_np.reshape(-1, seq_len, feat_dim) \n",
+    "# X_ts.shape\n",
+    "\n",
+    "# scaler = MinMaxScaler(feature_range=(-1, 1))\n",
+    "# X = np.stack(relax_math['raw_values'].apply(lambda x: scaler.fit_transform(x.reshape(-1, 1)).flatten()))\n",
+    "# y = keras.utils.to_categorical(relax_math['label'], num_classes=2)\n",
+    "\n",
+    "# scaler = tsgm.utils.TSFeatureWiseScaler((-1, 1))\n",
+    "# X_train = scaler.fit_transform(X_train_ts_32)\n"
+   ],
+   "outputs": [],
+   "execution_count": 25
+  },
+  {
    "cell_type": "code",
+   "id": "6a9b2bc71b4ba818",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-06-29T15:23:32.071036Z",
+     "start_time": "2024-06-29T15:23:32.057579Z"
+    }
+   },
    "source": [
-    "dataset = tf.data.Dataset.from_tensor_slices((X_train, y))\n",
+    "dataset = tf.data.Dataset.from_tensor_slices((X_train_ts_scaled_32, y_train_onehot_32))\n",
     "dataset = dataset.shuffle(buffer_size=1024).batch(batch_size)"
    ],
-   "id": "6a9b2bc71b4ba818",
    "outputs": [],
-   "execution_count": 171
+   "execution_count": 40
   },
   {
+   "cell_type": "code",
+   "id": "23fcd7bc7eb1a429",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T19:27:29.535403Z",
-     "start_time": "2024-06-27T19:27:29.352740Z"
+     "end_time": "2024-06-29T15:23:36.974778Z",
+     "start_time": "2024-06-29T15:23:36.780981Z"
     }
    },
-   "cell_type": "code",
    "source": [
     "latent_dim = 64\n",
     "output_dim = 2\n",
     "\n",
     "architecture = tsgm.models.architectures.zoo[\"cgan_base_c4_l1\"](\n",
-    "    seq_len=seq_len, feat_dim=feature_dim,\n",
+    "    seq_len=seq_len, feat_dim=feat_dim,\n",
     "    latent_dim=latent_dim, output_dim=output_dim)\n",
     "discriminator, generator = architecture.discriminator, architecture.generator"
    ],
-   "id": "23fcd7bc7eb1a429",
    "outputs": [],
-   "execution_count": 172
+   "execution_count": 41
   },
   {
+   "cell_type": "code",
+   "id": "deaffcb0749659bc",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T19:27:29.717424Z",
-     "start_time": "2024-06-27T19:27:29.707180Z"
+     "end_time": "2024-06-29T15:23:37.122107Z",
+     "start_time": "2024-06-29T15:23:37.107634Z"
     }
    },
-   "cell_type": "code",
    "source": [
     "cond_gan = tsgm.models.cgan.ConditionalGAN(\n",
     "    discriminator=discriminator, generator=generator, latent_dim=latent_dim\n",
     ")\n",
     "cond_gan.compile(\n",
-    "    d_optimizer=keras.optimizers.Adam(learning_rate=0.002, beta_1=0.5),\n",
-    "    g_optimizer=keras.optimizers.Adam(learning_rate=0.002, beta_1=0.5),\n",
+    "    d_optimizer=keras.optimizers.legacy.Adam(learning_rate=0.02, beta_1=0.5),\n",
+    "    g_optimizer=keras.optimizers.legacy.Adam(learning_rate=0.02, beta_1=0.5),\n",
     "    loss_fn=keras.losses.BinaryCrossentropy(),\n",
     ")"
    ],
-   "id": "deaffcb0749659bc",
+   "outputs": [],
+   "execution_count": 42
+  },
+  {
+   "cell_type": "code",
+   "id": "d68f276742d83031",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-06-29T15:23:38.039676Z",
+     "start_time": "2024-06-29T15:23:38.036661Z"
+    }
+   },
+   "source": [
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ],
+   "outputs": [],
+   "execution_count": 43
+  },
+  {
+   "cell_type": "code",
+   "id": "c3481a532fd2d7f7",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-06-29T15:23:57.308173Z",
+     "start_time": "2024-06-29T15:23:39.215585Z"
+    }
+   },
+   "source": [
+    "cbk = tsgm.models.monitors.GANMonitor(num_samples=3, latent_dim=latent_dim, save=False, labels=y_train_onehot_32, save_path=\"./tmp\")\n",
+    "cond_gan.fit(dataset, epochs=5, callbacks=[cbk], verbose=0)"
+   ],
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "WARNING:absl:At this time, the v2.11+ optimizer `tf.keras.optimizers.Adam` runs slowly on M1/M2 Macs, please use the legacy Keras optimizer instead, located at `tf.keras.optimizers.legacy.Adam`.\n",
-      "WARNING:absl:At this time, the v2.11+ optimizer `tf.keras.optimizers.Adam` runs slowly on M1/M2 Macs, please use the legacy Keras optimizer instead, located at `tf.keras.optimizers.legacy.Adam`.\n"
+      "WARNING:monitors:save_path is specified, but save is False.\n"
      ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.src.callbacks.History at 0x16b8fe730>"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
-   "execution_count": 173
+   "execution_count": 44
   },
   {
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-06-27T19:27:50.812764Z",
-     "start_time": "2024-06-27T19:27:30.203404Z"
+     "end_time": "2024-06-29T15:24:00.393312Z",
+     "start_time": "2024-06-29T15:24:00.389447Z"
     }
    },
    "cell_type": "code",
    "source": [
-    "cbk = tsgm.models.monitors.GANMonitor(num_samples=3, latent_dim=latent_dim, save=False, labels=y, save_path=\"/tmp\")\n",
-    "cond_gan.fit(dataset, epochs=1000, callbacks=[cbk])"
+    "print(y_train_onehot_32[:5])\n",
+    "\n"
    ],
-   "id": "c3481a532fd2d7f7",
+   "id": "362b3df76d8cd9a1",
    "outputs": [
     {
-     "name": "stderr",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
-      "WARNING:monitors:save_path is specified, but save is False.\n"
+      "[[1. 0.]\n",
+      " [0. 1.]\n",
+      " [1. 0.]\n",
+      " [1. 0.]\n",
+      " [0. 1.]]\n"
      ]
-    },
+    }
+   ],
+   "execution_count": 45
+  },
+  {
+   "cell_type": "code",
+   "id": "ff469cddf905be6b",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-06-29T15:24:10.878396Z",
+     "start_time": "2024-06-29T15:24:10.804351Z"
+    }
+   },
+   "source": [
+    "limit = 5\n",
+    "X_gen = cond_gan.generate(y_train_onehot_32[:limit])\n",
+    "X_gen = X_gen.numpy()\n",
+    "y_gen = y[:limit]\n",
+    "print(X_gen[1])\n"
+   ],
+   "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch 1/1000\n",
-      " 7/15 [=============>................] - ETA: 18s - g_loss: 0.7600 - d_loss: 0.7387"
-     ]
-    },
-    {
-     "ename": "KeyboardInterrupt",
-     "evalue": "",
-     "output_type": "error",
-     "traceback": [
-      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
-      "\u001B[0;31mKeyboardInterrupt\u001B[0m                         Traceback (most recent call last)",
-      "Cell \u001B[0;32mIn[174], line 2\u001B[0m\n\u001B[1;32m      1\u001B[0m cbk \u001B[38;5;241m=\u001B[39m tsgm\u001B[38;5;241m.\u001B[39mmodels\u001B[38;5;241m.\u001B[39mmonitors\u001B[38;5;241m.\u001B[39mGANMonitor(num_samples\u001B[38;5;241m=\u001B[39m\u001B[38;5;241m3\u001B[39m, latent_dim\u001B[38;5;241m=\u001B[39mlatent_dim, save\u001B[38;5;241m=\u001B[39m\u001B[38;5;28;01mFalse\u001B[39;00m, labels\u001B[38;5;241m=\u001B[39my, save_path\u001B[38;5;241m=\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m/tmp\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n\u001B[0;32m----> 2\u001B[0m \u001B[43mcond_gan\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mfit\u001B[49m\u001B[43m(\u001B[49m\u001B[43mdataset\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mepochs\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;241;43m1000\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcallbacks\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m[\u001B[49m\u001B[43mcbk\u001B[49m\u001B[43m]\u001B[49m\u001B[43m)\u001B[49m\n",
-      "File \u001B[0;32m~/PycharmProjects/BayesianWF/env/lib/python3.9/site-packages/keras/src/utils/traceback_utils.py:65\u001B[0m, in \u001B[0;36mfilter_traceback.<locals>.error_handler\u001B[0;34m(*args, **kwargs)\u001B[0m\n\u001B[1;32m     63\u001B[0m filtered_tb \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[1;32m     64\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[0;32m---> 65\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mfn\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m     66\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m     67\u001B[0m     filtered_tb \u001B[38;5;241m=\u001B[39m _process_traceback_frames(e\u001B[38;5;241m.\u001B[39m__traceback__)\n",
-      "File \u001B[0;32m~/PycharmProjects/BayesianWF/env/lib/python3.9/site-packages/keras/src/engine/training.py:1807\u001B[0m, in \u001B[0;36mModel.fit\u001B[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)\u001B[0m\n\u001B[1;32m   1799\u001B[0m \u001B[38;5;28;01mwith\u001B[39;00m tf\u001B[38;5;241m.\u001B[39mprofiler\u001B[38;5;241m.\u001B[39mexperimental\u001B[38;5;241m.\u001B[39mTrace(\n\u001B[1;32m   1800\u001B[0m     \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mtrain\u001B[39m\u001B[38;5;124m\"\u001B[39m,\n\u001B[1;32m   1801\u001B[0m     epoch_num\u001B[38;5;241m=\u001B[39mepoch,\n\u001B[0;32m   (...)\u001B[0m\n\u001B[1;32m   1804\u001B[0m     _r\u001B[38;5;241m=\u001B[39m\u001B[38;5;241m1\u001B[39m,\n\u001B[1;32m   1805\u001B[0m ):\n\u001B[1;32m   1806\u001B[0m     callbacks\u001B[38;5;241m.\u001B[39mon_train_batch_begin(step)\n\u001B[0;32m-> 1807\u001B[0m     tmp_logs \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mtrain_function\u001B[49m\u001B[43m(\u001B[49m\u001B[43miterator\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1808\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m data_handler\u001B[38;5;241m.\u001B[39mshould_sync:\n\u001B[1;32m   1809\u001B[0m         context\u001B[38;5;241m.\u001B[39masync_wait()\n",
-      "File \u001B[0;32m~/PycharmProjects/BayesianWF/env/lib/python3.9/site-packages/tensorflow/python/util/traceback_utils.py:150\u001B[0m, in \u001B[0;36mfilter_traceback.<locals>.error_handler\u001B[0;34m(*args, **kwargs)\u001B[0m\n\u001B[1;32m    148\u001B[0m filtered_tb \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[1;32m    149\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[0;32m--> 150\u001B[0m   \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mfn\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    151\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m    152\u001B[0m   filtered_tb \u001B[38;5;241m=\u001B[39m _process_traceback_frames(e\u001B[38;5;241m.\u001B[39m__traceback__)\n",
-      "File \u001B[0;32m~/PycharmProjects/BayesianWF/env/lib/python3.9/site-packages/tensorflow/python/eager/polymorphic_function/polymorphic_function.py:832\u001B[0m, in \u001B[0;36mFunction.__call__\u001B[0;34m(self, *args, **kwds)\u001B[0m\n\u001B[1;32m    829\u001B[0m compiler \u001B[38;5;241m=\u001B[39m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mxla\u001B[39m\u001B[38;5;124m\"\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_jit_compile \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mnonXla\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[1;32m    831\u001B[0m \u001B[38;5;28;01mwith\u001B[39;00m OptionalXlaContext(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_jit_compile):\n\u001B[0;32m--> 832\u001B[0m   result \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_call\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwds\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    834\u001B[0m new_tracing_count \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mexperimental_get_tracing_count()\n\u001B[1;32m    835\u001B[0m without_tracing \u001B[38;5;241m=\u001B[39m (tracing_count \u001B[38;5;241m==\u001B[39m new_tracing_count)\n",
-      "File \u001B[0;32m~/PycharmProjects/BayesianWF/env/lib/python3.9/site-packages/tensorflow/python/eager/polymorphic_function/polymorphic_function.py:868\u001B[0m, in \u001B[0;36mFunction._call\u001B[0;34m(self, *args, **kwds)\u001B[0m\n\u001B[1;32m    865\u001B[0m   \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_lock\u001B[38;5;241m.\u001B[39mrelease()\n\u001B[1;32m    866\u001B[0m   \u001B[38;5;66;03m# In this case we have created variables on the first call, so we run the\u001B[39;00m\n\u001B[1;32m    867\u001B[0m   \u001B[38;5;66;03m# defunned version which is guaranteed to never create variables.\u001B[39;00m\n\u001B[0;32m--> 868\u001B[0m   \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mtracing_compilation\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mcall_function\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m    869\u001B[0m \u001B[43m      \u001B[49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mkwds\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_no_variable_creation_config\u001B[49m\n\u001B[1;32m    870\u001B[0m \u001B[43m  \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    871\u001B[0m \u001B[38;5;28;01melif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_variable_creation_config \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[1;32m    872\u001B[0m   \u001B[38;5;66;03m# Release the lock early so that multiple threads can perform the call\u001B[39;00m\n\u001B[1;32m    873\u001B[0m   \u001B[38;5;66;03m# in parallel.\u001B[39;00m\n\u001B[1;32m    874\u001B[0m   \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_lock\u001B[38;5;241m.\u001B[39mrelease()\n",
-      "File \u001B[0;32m~/PycharmProjects/BayesianWF/env/lib/python3.9/site-packages/tensorflow/python/eager/polymorphic_function/tracing_compilation.py:139\u001B[0m, in \u001B[0;36mcall_function\u001B[0;34m(args, kwargs, tracing_options)\u001B[0m\n\u001B[1;32m    137\u001B[0m bound_args \u001B[38;5;241m=\u001B[39m function\u001B[38;5;241m.\u001B[39mfunction_type\u001B[38;5;241m.\u001B[39mbind(\u001B[38;5;241m*\u001B[39margs, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs)\n\u001B[1;32m    138\u001B[0m flat_inputs \u001B[38;5;241m=\u001B[39m function\u001B[38;5;241m.\u001B[39mfunction_type\u001B[38;5;241m.\u001B[39munpack_inputs(bound_args)\n\u001B[0;32m--> 139\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mfunction\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_call_flat\u001B[49m\u001B[43m(\u001B[49m\u001B[43m  \u001B[49m\u001B[38;5;66;43;03m# pylint: disable=protected-access\u001B[39;49;00m\n\u001B[1;32m    140\u001B[0m \u001B[43m    \u001B[49m\u001B[43mflat_inputs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcaptured_inputs\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mfunction\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mcaptured_inputs\u001B[49m\n\u001B[1;32m    141\u001B[0m \u001B[43m\u001B[49m\u001B[43m)\u001B[49m\n",
-      "File \u001B[0;32m~/PycharmProjects/BayesianWF/env/lib/python3.9/site-packages/tensorflow/python/eager/polymorphic_function/concrete_function.py:1323\u001B[0m, in \u001B[0;36mConcreteFunction._call_flat\u001B[0;34m(self, tensor_inputs, captured_inputs)\u001B[0m\n\u001B[1;32m   1319\u001B[0m possible_gradient_type \u001B[38;5;241m=\u001B[39m gradients_util\u001B[38;5;241m.\u001B[39mPossibleTapeGradientTypes(args)\n\u001B[1;32m   1320\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m (possible_gradient_type \u001B[38;5;241m==\u001B[39m gradients_util\u001B[38;5;241m.\u001B[39mPOSSIBLE_GRADIENT_TYPES_NONE\n\u001B[1;32m   1321\u001B[0m     \u001B[38;5;129;01mand\u001B[39;00m executing_eagerly):\n\u001B[1;32m   1322\u001B[0m   \u001B[38;5;66;03m# No tape is watching; skip to running the function.\u001B[39;00m\n\u001B[0;32m-> 1323\u001B[0m   \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_inference_function\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mcall_preflattened\u001B[49m\u001B[43m(\u001B[49m\u001B[43margs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1324\u001B[0m forward_backward \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_select_forward_and_backward_functions(\n\u001B[1;32m   1325\u001B[0m     args,\n\u001B[1;32m   1326\u001B[0m     possible_gradient_type,\n\u001B[1;32m   1327\u001B[0m     executing_eagerly)\n\u001B[1;32m   1328\u001B[0m forward_function, args_with_tangents \u001B[38;5;241m=\u001B[39m forward_backward\u001B[38;5;241m.\u001B[39mforward()\n",
-      "File \u001B[0;32m~/PycharmProjects/BayesianWF/env/lib/python3.9/site-packages/tensorflow/python/eager/polymorphic_function/atomic_function.py:216\u001B[0m, in \u001B[0;36mAtomicFunction.call_preflattened\u001B[0;34m(self, args)\u001B[0m\n\u001B[1;32m    214\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21mcall_preflattened\u001B[39m(\u001B[38;5;28mself\u001B[39m, args: Sequence[core\u001B[38;5;241m.\u001B[39mTensor]) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m Any:\n\u001B[1;32m    215\u001B[0m \u001B[38;5;250m  \u001B[39m\u001B[38;5;124;03m\"\"\"Calls with flattened tensor inputs and returns the structured output.\"\"\"\u001B[39;00m\n\u001B[0;32m--> 216\u001B[0m   flat_outputs \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mcall_flat\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    217\u001B[0m   \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunction_type\u001B[38;5;241m.\u001B[39mpack_output(flat_outputs)\n",
-      "File \u001B[0;32m~/PycharmProjects/BayesianWF/env/lib/python3.9/site-packages/tensorflow/python/eager/polymorphic_function/atomic_function.py:251\u001B[0m, in \u001B[0;36mAtomicFunction.call_flat\u001B[0;34m(self, *args)\u001B[0m\n\u001B[1;32m    249\u001B[0m \u001B[38;5;28;01mwith\u001B[39;00m record\u001B[38;5;241m.\u001B[39mstop_recording():\n\u001B[1;32m    250\u001B[0m   \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_bound_context\u001B[38;5;241m.\u001B[39mexecuting_eagerly():\n\u001B[0;32m--> 251\u001B[0m     outputs \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_bound_context\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mcall_function\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m    252\u001B[0m \u001B[43m        \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mname\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    253\u001B[0m \u001B[43m        \u001B[49m\u001B[38;5;28;43mlist\u001B[39;49m\u001B[43m(\u001B[49m\u001B[43margs\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    254\u001B[0m \u001B[43m        \u001B[49m\u001B[38;5;28;43mlen\u001B[39;49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mfunction_type\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mflat_outputs\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    255\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    256\u001B[0m   \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[1;32m    257\u001B[0m     outputs \u001B[38;5;241m=\u001B[39m make_call_op_in_graph(\n\u001B[1;32m    258\u001B[0m         \u001B[38;5;28mself\u001B[39m,\n\u001B[1;32m    259\u001B[0m         \u001B[38;5;28mlist\u001B[39m(args),\n\u001B[1;32m    260\u001B[0m         \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_bound_context\u001B[38;5;241m.\u001B[39mfunction_call_options\u001B[38;5;241m.\u001B[39mas_attrs(),\n\u001B[1;32m    261\u001B[0m     )\n",
-      "File \u001B[0;32m~/PycharmProjects/BayesianWF/env/lib/python3.9/site-packages/tensorflow/python/eager/context.py:1486\u001B[0m, in \u001B[0;36mContext.call_function\u001B[0;34m(self, name, tensor_inputs, num_outputs)\u001B[0m\n\u001B[1;32m   1484\u001B[0m cancellation_context \u001B[38;5;241m=\u001B[39m cancellation\u001B[38;5;241m.\u001B[39mcontext()\n\u001B[1;32m   1485\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m cancellation_context \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[0;32m-> 1486\u001B[0m   outputs \u001B[38;5;241m=\u001B[39m \u001B[43mexecute\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mexecute\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1487\u001B[0m \u001B[43m      \u001B[49m\u001B[43mname\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mdecode\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mutf-8\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1488\u001B[0m \u001B[43m      \u001B[49m\u001B[43mnum_outputs\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mnum_outputs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1489\u001B[0m \u001B[43m      \u001B[49m\u001B[43minputs\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mtensor_inputs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1490\u001B[0m \u001B[43m      \u001B[49m\u001B[43mattrs\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mattrs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1491\u001B[0m \u001B[43m      \u001B[49m\u001B[43mctx\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1492\u001B[0m \u001B[43m  \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1493\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[1;32m   1494\u001B[0m   outputs \u001B[38;5;241m=\u001B[39m execute\u001B[38;5;241m.\u001B[39mexecute_with_cancellation(\n\u001B[1;32m   1495\u001B[0m       name\u001B[38;5;241m.\u001B[39mdecode(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mutf-8\u001B[39m\u001B[38;5;124m\"\u001B[39m),\n\u001B[1;32m   1496\u001B[0m       num_outputs\u001B[38;5;241m=\u001B[39mnum_outputs,\n\u001B[0;32m   (...)\u001B[0m\n\u001B[1;32m   1500\u001B[0m       cancellation_manager\u001B[38;5;241m=\u001B[39mcancellation_context,\n\u001B[1;32m   1501\u001B[0m   )\n",
-      "File \u001B[0;32m~/PycharmProjects/BayesianWF/env/lib/python3.9/site-packages/tensorflow/python/eager/execute.py:53\u001B[0m, in \u001B[0;36mquick_execute\u001B[0;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001B[0m\n\u001B[1;32m     51\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m     52\u001B[0m   ctx\u001B[38;5;241m.\u001B[39mensure_initialized()\n\u001B[0;32m---> 53\u001B[0m   tensors \u001B[38;5;241m=\u001B[39m \u001B[43mpywrap_tfe\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mTFE_Py_Execute\u001B[49m\u001B[43m(\u001B[49m\u001B[43mctx\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_handle\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mdevice_name\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mop_name\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m     54\u001B[0m \u001B[43m                                      \u001B[49m\u001B[43minputs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mattrs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mnum_outputs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m     55\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m core\u001B[38;5;241m.\u001B[39m_NotOkStatusException \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m     56\u001B[0m   \u001B[38;5;28;01mif\u001B[39;00m name \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n",
-      "\u001B[0;31mKeyboardInterrupt\u001B[0m: "
+      "[[-0.99999976  0.9996441   0.9947663   0.9985018  -0.99605376  0.9999972\n",
+      "  -0.9999939  -0.9994647  -0.9998888  -0.9967149  -0.99874616 -0.9999729\n",
+      "  -0.9999519  -0.99992204  0.9999877   0.99847806  0.99726915  0.99867976\n",
+      "  -0.9999949   0.99938124 -0.99927175 -0.9909994  -0.9868546  -0.9997206\n",
+      "  -0.9999986  -0.9997139  -0.99998975  0.9965205   0.9982372  -0.9979722\n",
+      "   0.9957258   0.99986047 -0.99990445  0.99999    -0.99997604 -0.9996386\n",
+      "  -0.9981849   0.9999987   0.97191584 -0.99948037  0.99991816  0.9999658\n",
+      "   0.99961644  0.99980754 -0.99975014 -0.9995929  -0.99996126  0.998848\n",
+      "   0.9361116  -0.99990314 -0.9962934   0.9975584  -0.99999976 -0.9999932\n",
+      "   0.9949587  -0.99999255  0.99976283 -0.9999991  -0.99899447 -0.9999977\n",
+      "  -0.99929804 -0.9874998  -0.999999    0.9947624 ]\n",
+      " [-0.9999968   0.9982716  -0.9999986  -0.99999636 -0.99999976  0.9995329\n",
+      "  -0.9999988  -0.9999957  -0.99999404  0.99926263 -0.9999935  -0.99999976\n",
+      "  -0.99999535 -0.9999989  -0.9995394   0.9999867   0.9990056  -0.99999976\n",
+      "   0.9999662  -0.9998403  -0.9993128  -0.99911857 -0.9999926  -0.9999989\n",
+      "  -0.99999833 -0.999984   -0.99999905 -0.9999989  -0.99999976 -0.99999917\n",
+      "  -0.9999888  -0.99962425  0.9999838  -0.9946048   0.9994441   0.99999845\n",
+      "   0.9999989   0.9999988   0.9998186   0.999996    0.9999943   0.9999842\n",
+      "   0.99999523  0.9999315   0.99999976 -0.99988574 -0.99999654 -0.99999976\n",
+      "   0.99944854 -0.9999992  -0.9999977  -0.9999984  -0.99999905 -0.99999917\n",
+      "   0.9992732   0.99935013 -0.99999744 -0.9999988  -0.99999917 -0.99544924\n",
+      "   0.9999812  -0.9996824  -0.9999985  -0.9999994 ]\n",
+      " [-0.9999561  -0.9999933  -0.9999763  -0.99999845  0.99266624  0.9999977\n",
+      "  -0.99999815 -0.998961   -0.99999833 -0.9999845  -0.9999969  -0.9999883\n",
+      "  -0.9999988  -0.99999446 -0.9999855  -0.9999927  -0.9999976  -0.9999965\n",
+      "  -0.99999255 -0.9999852  -0.9997299  -0.99989235 -0.9999953  -0.9999976\n",
+      "  -0.99999416 -0.99998105 -0.9994704  -0.99999696 -0.9999991  -0.99999654\n",
+      "  -0.99998516 -0.99936587 -0.9986064   0.99996036  0.9999915   0.99999094\n",
+      "   0.99999833  0.9999997  -0.99983835 -0.99894506  0.9999989  -0.9979365\n",
+      "  -0.99999124 -0.99999243 -0.9999888  -0.99328196 -0.9999985  -0.99999726\n",
+      "  -0.99999803 -0.99999744 -0.9999864  -0.9999984  -0.99920315 -0.9999982\n",
+      "  -0.99998206 -0.9995369   0.9999471  -0.99999    -0.9999945  -0.99999976\n",
+      "  -0.99999905 -0.99999714 -0.9999789  -0.9999692 ]\n",
+      " [-0.999997    0.98825043 -0.99998623 -0.999988   -0.9999593   0.985381\n",
+      "  -0.9999864  -0.99993765 -0.99999386 -0.9999939  -0.99999875 -0.99999976\n",
+      "  -0.9999957  -0.9999982  -0.99999887 -0.9999636  -0.99999803 -0.99999803\n",
+      "  -0.9999122  -0.9999841  -0.99976397 -0.99999344 -0.99943864 -0.999934\n",
+      "  -0.9999944  -0.99994016 -0.9999939  -0.99999815 -0.99999976 -0.99999195\n",
+      "  -0.99994934 -0.9999592   0.9999904  -0.9997867   0.99994373  0.9999926\n",
+      "   0.9999982   0.9999988   0.9999996   0.99996316  0.9999846   0.9999985\n",
+      "   0.99999076  0.9999832   0.99999976 -0.99787337 -0.99998194 -0.99999666\n",
+      "   0.9959502  -0.99998254 -0.9999969  -0.9999962  -0.9999891  -0.9999989\n",
+      "  -0.9998134  -0.9999992  -0.9997599  -0.99993443 -0.99994755 -0.99998105\n",
+      "  -0.9997127  -0.9999987  -0.9999931  -0.9999932 ]\n",
+      " [-0.9999421  -0.99998665 -0.9995325  -0.99969804 -0.9999829   0.99999696\n",
+      "  -0.9999471  -0.9992818  -0.99989516 -0.99997455 -0.9998411  -0.9989085\n",
+      "  -0.99997354 -0.9889412  -0.9999261  -0.99996156 -0.9999716  -0.9999796\n",
+      "  -0.9999912  -0.9998562  -0.99971825 -0.999953   -0.9999741  -0.99981976\n",
+      "  -0.999757   -0.9996374  -0.9999037  -0.999242   -0.9999954  -0.9993764\n",
+      "   0.9992573   0.9991352  -0.9996752   0.99996287  0.9997413   0.9999844\n",
+      "   0.9999277   0.99999934  0.9987086   0.99944854  0.9979512   0.99999666\n",
+      "  -0.9999396   0.9999934  -0.9999389  -0.9999933  -0.9999946   0.99995685\n",
+      "  -0.99988604 -0.999767   -0.9992542  -0.99998903 -0.9999793  -0.999968\n",
+      "  -0.99988014 -0.99999714 -0.9999834  -0.99876434 -0.99996954 -0.9999292\n",
+      "  -0.9999992  -0.9994855  -0.9999001  -0.9999853 ]\n",
+      " [-0.9999939  -0.99999976  0.99352807  0.9971322  -0.999862   -0.9999927\n",
+      "  -0.99994135 -0.9997949  -0.9993257  -0.9999985  -0.9996534  -0.99999976\n",
+      "  -0.99996257 -0.9999958  -0.9999951   0.99993646 -0.99999017 -0.99997663\n",
+      "  -0.99999976 -0.9999856   0.99998724 -0.99925035 -0.99941885 -0.9996326\n",
+      "  -0.99997157 -0.9995122  -0.99937385 -0.9997256  -0.99999976 -0.9998475\n",
+      "  -0.9998366  -0.99580395  0.99821043 -0.9851937  -0.99769247  0.99365795\n",
+      "  -0.99977356  0.99998635  0.9999958   0.99999297 -0.99989665  0.99993974\n",
+      "  -0.99986935 -0.99999565  0.9999972  -0.9999306   0.99971545  0.61991394\n",
+      "  -0.99996305 -0.9999873  -0.99997044 -0.99997276 -0.9998678  -0.9999904\n",
+      "  -0.99999833 -0.9998604  -0.9997495  -0.9995082  -0.99978197 -0.9999705\n",
+      "  -0.9998504  -0.9999979  -0.99990165 -0.9999905 ]\n",
+      " [-0.99999493 -0.9999982  -0.99997985 -0.99994165 -0.9999967   0.99998194\n",
+      "  -0.9999982  -0.98493916 -0.99988323 -0.9995759  -0.9999657  -0.9997109\n",
+      "  -0.9994305  -0.99998045 -0.9990914   0.9996333   0.99999833 -0.99989957\n",
+      "  -0.9999964  -0.999929    0.9999801  -0.9999402  -0.9997864  -0.99965894\n",
+      "  -0.9999944  -0.99999243 -0.9998329  -0.9999752  -0.9999914  -0.9996994\n",
+      "   0.99780184 -0.9998631   0.9999977   0.9992804  -0.999985    0.99998844\n",
+      "   0.9999697  -0.9999571   0.99999976  0.9999976   0.9999945   0.99999505\n",
+      "   0.9998842   0.99974537  0.99987787 -0.99995846 -0.99999416 -0.9998887\n",
+      "  -0.99998796 -0.99999976 -0.9999395  -0.99998295 -0.99996275 -0.99999017\n",
+      "  -0.9998628  -0.99992025 -0.99999976 -0.9996439  -0.9999134  -0.99999976\n",
+      "  -0.9999971  -0.9992671  -0.9999896  -0.9999427 ]\n",
+      " [-0.9999719  -0.9998268  -0.99844486  0.99946636 -0.99790776 -0.9999976\n",
+      "  -0.9998898  -0.999999   -0.9999722  -0.99999976 -0.99999535 -0.99999976\n",
+      "  -0.9999832  -0.9999994  -0.99975187  0.99981755 -0.999988   -0.9999988\n",
+      "  -0.9999972  -0.9999534   0.9999966  -0.9991455  -0.99969715 -0.99974597\n",
+      "  -0.999996   -0.99999607 -0.9998127  -0.99999297 -0.99999976 -0.9999864\n",
+      "  -0.9998945  -0.9961749  -0.9993872   0.99999976 -0.9999907   0.99999017\n",
+      "  -0.99999416  0.99999654  0.9996782   0.999984   -0.9998355   0.99999803\n",
+      "   0.99934554 -0.99983096  0.99797106  0.9999943  -0.9999972  -0.99999964\n",
+      "  -0.99999976 -0.999995   -0.99985164 -0.9999385  -0.9999896  -0.9999989\n",
+      "  -0.99999905 -0.99999315 -0.9997763  -0.9997161  -0.9997882  -0.9992735\n",
+      "   0.99969673  0.99989885 -0.9997767  -0.9999623 ]]\n"
      ]
     }
    ],
-   "execution_count": 174
+   "execution_count": 47
   },
   {
    "metadata": {},
@@ -752,26 +966,26 @@
    "outputs": [],
    "execution_count": null,
    "source": "",
-   "id": "fd686b0472300a9f"
+   "id": "3f94f12a716ac9eb"
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python (env)",
+   "display_name": "tsgm_env",
    "language": "python",
-   "name": "env"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.6"
+   "pygments_lexer": "ipython3",
+   "version": "3.9.15"
   }
  },
  "nbformat": 4,