docs: correct pfld_mbv2n_112 name

Seeed-Studio · Jul 10, 2023 · 7a869bb · 7a869bb
1 parent 184c1a4
commit 7a869bb
Show file tree

Hide file tree

Showing 10 changed files with 41 additions and 41 deletions.
diff --git a/configs/pfld/README.md b/configs/pfld/README.md
@@ -27,7 +27,7 @@ improvements from the community.
 
 | Backbone | Scale | param(K) | flop(G) | loss | config | pth | onnx | ncnn |
 | :------: | :---: | :------: | :-----: | :--: | :----: | :------: | :----:| :----:|
-| MoboNetv2| 112 | 140.55 | 0.0593 |3.5e-5| [config](./pfld_mv2n_112.py)| [model](https://github.com/Seeed-Studio/edgelab/releases/download/model_zoom/pfld_mv2n_112.pth) |[onnx](https://github.com/Seeed-Studio/edgelab/releases/download/model_zoom/pfld_mv2n_112.onnx)|[ncnn](https://github.com/Seeed-Studio/edgelab/releases/download/model_zoom/pfld_mv2n_112.ncnn.zip)|
+| MoboNetv2| 112 | 140.55 | 0.0593 |3.5e-5| [config](./pfld_mbv2n_112.py)| [model](https://github.com/Seeed-Studio/edgelab/releases/download/model_zoom/pfld_mbv2n_112.pth) |[onnx](https://github.com/Seeed-Studio/edgelab/releases/download/model_zoom/pfld_mbv2n_112.onnx)|[ncnn](https://github.com/Seeed-Studio/edgelab/releases/download/model_zoom/pfld_mbv2n_112.ncnn.zip)|
 
 ## Citation
 

diff --git a/docs/tutorials/config.md b/docs/tutorials/config.md
@@ -30,7 +30,7 @@ configs
 │ ├── fomo_shufflenetv2_0.1_x8_abl_coco.py
 │ └── fomo_squeezenet_0.1_x8_abl_coco.py
 ├── pfld
-│ └── pfld_mv2n_112.py
+│ └── pfld_mbv2n_112.py
 └── <Other Tasks...>
 ```
 
@@ -56,7 +56,7 @@ configs // [!code focus]
 │ ├── fomo_shufflenetv2_0.1_x8_abl_coco.py
 │ └── fomo_squeezenet_0.1_x8_abl_coco.py
 ├── pfld // [!code focus]
-│ └── pfld_mv2n_112.py
+│ └── pfld_mbv2n_112.py
 └── <Other Tasks...> // [!code focus]
 ```
 
@@ -82,7 +82,7 @@ configs // [!code focus]
 │ ├── fomo_shufflenetv2_0.1_x8_abl_coco.py // [!code focus]
 │ └── fomo_squeezenet_0.1_x8_abl_coco.py // [!code focus]
 ├── pfld
-│ └── pfld_mv2n_112.py
+│ └── pfld_mbv2n_112.py
 └── <Other Tasks...>
 ```
 

diff --git a/docs/tutorials/export/pytorch_2_onnx.md b/docs/tutorials/export/pytorch_2_onnx.md
@@ -54,8 +54,8 @@ python3 tools/export.py \
 
 ```sh [PFLD Model Conversion]
 python3 tools/export.py \
- configs/pfld/pfld_mv2n_112.py \
- "$(cat work_dirs/pfld_mv2n_112/last_checkpoint)" \
+ configs/pfld/pfld_mbv2n_112.py \
+ "$(cat work_dirs/pfld_mbv2n_112/last_checkpoint)" \
  onnx \
  --cfg-options \
  data_root='datasets/meter'
@@ -105,8 +105,8 @@ python3 tools/inference.py \
 
 ```sh [PFLD Model Validation]
 python3 tools/inference.py \
- configs/pfld/pfld_mv2n_112.py \
- "$(cat work_dirs/pfld_mv2n_112/last_checkpoint | sed -e 's/.pth/.onnx/g')" \
+ configs/pfld/pfld_mbv2n_112.py \
+ "$(cat work_dirs/pfld_mbv2n_112/last_checkpoint | sed -e 's/.pth/.onnx/g')" \
  --show \
  --cfg-options \
  data_root='datasets/meter'

diff --git a/docs/tutorials/export/pytorch_2_tflite.md b/docs/tutorials/export/pytorch_2_tflite.md
@@ -61,8 +61,8 @@ python3 tools/export.py \
 
 ```sh [PFLD Model Conversion]
 python3 tools/export.py \
- configs/pfld/pfld_mv2n_112.py \
- "$(cat work_dirs/pfld_mv2n_112/last_checkpoint)" \
+ configs/pfld/pfld_mbv2n_112.py \
+ "$(cat work_dirs/pfld_mbv2n_112/last_checkpoint)" \
  tflite \
  --cfg-options \
  data_root='datasets/meter'
@@ -114,8 +114,8 @@ python3 tools/inference.py \
 
 ```sh [PFLD Model Validation]
 python3 tools/inference.py \
- configs/pfld/pfld_mv2n_112.py \
- "$(cat work_dirs/pfld_mv2n_112/last_checkpoint | sed -e 's/.pth/_int8.tflite/g')" \
+ configs/pfld/pfld_mbv2n_112.py \
+ "$(cat work_dirs/pfld_mbv2n_112/last_checkpoint | sed -e 's/.pth/_int8.tflite/g')" \
  --show \
  --cfg-options \
  data_root='datasets/meter'

diff --git a/docs/tutorials/training/pfld.md b/docs/tutorials/training/pfld.md
@@ -14,11 +14,11 @@ EdgeLab uses [Custom Meter Datasets](../datasets.md#EdgeLab) by default to train
 
 We will choose a appropriate configuration file depending on the type of training task we need to perform, which we have already introduced in [Config](../config.md), for a brief description of the functions, structure, and principles of the configuration file.
 
-For the meter PFLD model example, we use `pfld_mv2n_112.py` as the configuration file, which is located in the folder under the EdgeLab root directory `configs/pfld` and its additionally inherits the `default_runtime_pose.py` configuration file.
+For the meter PFLD model example, we use `pfld_mbv2n_112.py` as the configuration file, which is located in the folder under the EdgeLab root directory `configs/pfld` and its additionally inherits the `default_runtime_pose.py` configuration file.
 
 For beginners, we recommend to pay attention to the `data_root` and `epochs` parameters in this configuration file at first.
 
-::: details `pfld_mv2n_112.py`
+::: details `pfld_mbv2n_112.py`
 
 ```python
 _base_='../_base_/default_runtime_pose.py'
@@ -120,19 +120,19 @@ Then, in the EdgeLab project root directory, we execute the following command to
 
 ```sh
 python3 tools/train.py \
- configs/pfld/pfld_mv2n_112.py \
+ configs/pfld/pfld_mbv2n_112.py \
  --cfg-options \
  data_root='datasets/meter' \
  epochs=50
 ```
 
-During training, the model weights and related log information are saved to the path `work_dirs/pfld_mv2n_112` by default, and you can use tools such as [TensorBoard](https://www.tensorflow.org/tensorboard/get_started) to monitor for training.
+During training, the model weights and related log information are saved to the path `work_dirs/pfld_mbv2n_112` by default, and you can use tools such as [TensorBoard](https://www.tensorflow.org/tensorboard/get_started) to monitor for training.
 
 ```sh
-tensorboard --logdir work_dirs/pfld_mv2n_112
+tensorboard --logdir work_dirs/pfld_mbv2n_112
 ```
 
-After the training is completed, the path of the latest FOMO model weights file is saved in the `work_dirs/pfld_mv2n_112/last_checkpoint` file. Please take care of the path of the weight file, as it is needed when converting the model to other formats.
+After the training is completed, the path of the latest FOMO model weights file is saved in the `work_dirs/pfld_mbv2n_112/last_checkpoint` file. Please take care of the path of the weight file, as it is needed when converting the model to other formats.
 
 ::: tip
 
@@ -152,8 +152,8 @@ After have finished training the PFLD model, you can specify specific weights an
 
 ```sh
 python3 tools/inference.py \
- configs/pfld/pfld_mv2n_112.py \
- "$(cat work_dirs/pfld_mv2n_112/last_checkpoint)" \
+ configs/pfld/pfld_mbv2n_112.py \
+ "$(cat work_dirs/pfld_mbv2n_112/last_checkpoint)" \
  --cfg-options \
  data_root='datasets/meter'
 ```

diff --git a/docs/zh_cn/tutorials/config.md b/docs/zh_cn/tutorials/config.md
@@ -30,7 +30,7 @@ configs
 │ ├── fomo_shufflenetv2_0.1_x8_abl_coco.py
 │ └── fomo_squeezenet_0.1_x8_abl_coco.py
 ├── pfld
-│ └── pfld_mv2n_112.py
+│ └── pfld_mbv2n_112.py
 └── <Other Tasks...>
 ```
 
@@ -56,7 +56,7 @@ configs // [!code focus]
 │ ├── fomo_shufflenetv2_0.1_x8_abl_coco.py
 │ └── fomo_squeezenet_0.1_x8_abl_coco.py
 ├── pfld // [!code focus]
-│ └── pfld_mv2n_112.py
+│ └── pfld_mbv2n_112.py
 └── <Other Tasks...> // [!code focus]
 ```
 
@@ -82,7 +82,7 @@ configs // [!code focus]
 │ ├── fomo_shufflenetv2_0.1_x8_abl_coco.py // [!code focus]
 │ └── fomo_squeezenet_0.1_x8_abl_coco.py // [!code focus]
 ├── pfld
-│ └── pfld_mv2n_112.py
+│ └── pfld_mbv2n_112.py
 └── <Other Tasks...>
 ```
 

diff --git a/docs/zh_cn/tutorials/export/pytorch_2_onnx.md b/docs/zh_cn/tutorials/export/pytorch_2_onnx.md
@@ -54,8 +54,8 @@ python3 tools/export.py \
 
 ```sh [PFLD Model Conversion]
 python3 tools/export.py \
- configs/pfld/pfld_mv2n_112.py \
- "$(cat work_dirs/pfld_mv2n_112/last_checkpoint)" \
+ configs/pfld/pfld_mbv2n_112.py \
+ "$(cat work_dirs/pfld_mbv2n_112/last_checkpoint)" \
  onnx \
  --cfg-options \
  data_root='datasets/meter'
@@ -105,8 +105,8 @@ python3 tools/inference.py \
 
 ```sh [PFLD Model Validation]
 python3 tools/inference.py \
- configs/pfld/pfld_mv2n_112.py \
- "$(cat work_dirs/pfld_mv2n_112/last_checkpoint | sed -e 's/.pth/.onnx/g')" \
+ configs/pfld/pfld_mbv2n_112.py \
+ "$(cat work_dirs/pfld_mbv2n_112/last_checkpoint | sed -e 's/.pth/.onnx/g')" \
  --show \
  --cfg-options \
  data_root='datasets/meter'

diff --git a/docs/zh_cn/tutorials/export/pytorch_2_tflite.md b/docs/zh_cn/tutorials/export/pytorch_2_tflite.md
@@ -61,8 +61,8 @@ python3 tools/export.py \
 
 ```sh [PFLD Model Conversion]
 python3 tools/export.py \
- configs/pfld/pfld_mv2n_112.py \
- "$(cat work_dirs/pfld_mv2n_112/last_checkpoint)" \
+ configs/pfld/pfld_mbv2n_112.py \
+ "$(cat work_dirs/pfld_mbv2n_112/last_checkpoint)" \
  tflite \
  --cfg-options \
  data_root='datasets/meter'
@@ -114,8 +114,8 @@ python3 tools/inference.py \
 
 ```sh [PFLD Model Validation]
 python3 tools/inference.py \
- configs/pfld/pfld_mv2n_112.py \
- "$(cat work_dirs/pfld_mv2n_112/last_checkpoint | sed -e 's/.pth/_int8.tflite/g')" \
+ configs/pfld/pfld_mbv2n_112.py \
+ "$(cat work_dirs/pfld_mbv2n_112/last_checkpoint | sed -e 's/.pth/_int8.tflite/g')" \
  --show \
  --cfg-options \
  data_root='datasets/meter'

diff --git a/docs/zh_cn/tutorials/training/pfld.md b/docs/zh_cn/tutorials/training/pfld.md
@@ -14,11 +14,11 @@
 
 我们将根据需要执行的训练任务类型来选择合适的配置文件，我们已经在[模型配置](../config.md)中对配置文件的功能、结构、原理进行了简单介绍。
 
-对于表计 PFLD 模型示例，我们使用 `pfld_mv2n_112.py` 作为配置文件，它位于 EdgeLab 主目录路径 `configs/pfld` 下的文件夹中，并额外继承了 `default_runtime_pose.py` 配置文件。
+对于表计 PFLD 模型示例，我们使用 `pfld_mbv2n_112.py` 作为配置文件，它位于 EdgeLab 主目录路径 `configs/pfld` 下的文件夹中，并额外继承了 `default_runtime_pose.py` 配置文件。
 
 配置文件内容如下，对于初学者，我们建议首先注意该配置文件中 `data_root` 和 `epochs` 这两个参数。
 
-::: details `pfld_mv2n_112.py`
+::: details `pfld_mbv2n_112.py`
 
 ```python
 _base_='../_base_/default_runtime_pose.py'
@@ -120,19 +120,19 @@ param_scheduler=[
 
 ```sh
 python3 tools/train.py \
- configs/pfld/pfld_mv2n_112.py \
+ configs/pfld/pfld_mbv2n_112.py \
  --cfg-options \
  data_root='datasets/meter' \
  epochs=50
 ```
 
-在训练期间，训练得到的模型权重和相关的日志信息会默认保存至路径 `work_dirs/pfld_mv2n_112` 下，您可以使用 [TensorBoard](https://www.tensorflow.org/tensorboard/get_started) 等工具事实监测训练情况。
+在训练期间，训练得到的模型权重和相关的日志信息会默认保存至路径 `work_dirs/pfld_mbv2n_112` 下，您可以使用 [TensorBoard](https://www.tensorflow.org/tensorboard/get_started) 等工具事实监测训练情况。
 
 ```sh
-tensorboard --logdir work_dirs/pfld_mv2n_112
+tensorboard --logdir work_dirs/pfld_mbv2n_112
 ```
 
-在训练完成后，最新的 PFLD 模型权重文件的路径会保存在 `work_dirs/pfld_mv2n_112/last_checkpoint` 文件中。请留意权重文件路径，在将模型转换为其他格式时需要用到。
+在训练完成后，最新的 PFLD 模型权重文件的路径会保存在 `work_dirs/pfld_mbv2n_112/last_checkpoint` 文件中。请留意权重文件路径，在将模型转换为其他格式时需要用到。
 
 ::: tip
 
@@ -152,8 +152,8 @@ conda activate edgelab
 
 ```sh
 python3 tools/inference.py \
- configs/pfld/pfld_mv2n_112.py \
- "$(cat work_dirs/pfld_mv2n_112/last_checkpoint)" \
+ configs/pfld/pfld_mbv2n_112.py \
+ "$(cat work_dirs/pfld_mbv2n_112/last_checkpoint)" \
  --cfg-options \
  data_root='datasets/meter'
 ```

diff --git a/notebooks/Google-Colab-PFLD-Grove-Example.ipynb b/notebooks/Google-Colab-PFLD-Grove-Example.ipynb
@@ -243,7 +243,7 @@
  },
  "outputs": [],
  "source": [
- "!wget -P pre-train/ https://github.com/Seeed-Studio/EdgeLab/releases/download/model_zoo/pfld_mv2n_112.pth "
+ "!wget -P pre-train/ https://github.com/Seeed-Studio/EdgeLab/releases/download/model_zoo/pfld_mbv2n_112.pth "
  ]
  },
  {
@@ -284,7 +284,7 @@
  " epochs=50 \\\n",
  " num_classes=1 \\\n",
  " data_root='datasets/meter' \\\n",
- " load_from='pre-train/pfld_mv2n_112.pth'"
+ " load_from='pre-train/pfld_mbv2n_112.pth'"
  ]
  },
  {