From a8282705e265fe3d71f0a4614eba5e76cc9440e6 Mon Sep 17 00:00:00 2001 From: wangguanzhong Date: Fri, 22 Nov 2019 19:26:28 +0800 Subject: [PATCH] move path to PaddleDetection repo in docs (#35) * move path to PaddleDetection repo in docs * refine README --- README.md | 153 +++++++++++++++++------------------- README_cn.md | 125 ----------------------------- README_en.md | 138 ++++++++++++++++++++++++++++++++ contrib/README.md | 4 +- contrib/README_cn.md | 4 +- demo/mask_rcnn_demo.ipynb | 2 +- docs/INSTALL.md | 8 +- docs/INSTALL_cn.md | 7 +- docs/MODEL_ZOO.md | 4 +- docs/MODEL_ZOO_cn.md | 4 +- slim/distillation/README.md | 4 +- slim/prune/README.md | 2 +- slim/quantization/README.md | 4 +- 13 files changed, 230 insertions(+), 229 deletions(-) delete mode 100644 README_cn.md create mode 100644 README_en.md diff --git a/README.md b/README.md index 6fcc42ddd..0f0375e7e 100644 --- a/README.md +++ b/README.md @@ -1,136 +1,127 @@ -English | [简体中文](README_cn.md) +[English](README_en.md) | 简体中文 # PaddleDetection -The goal of PaddleDetection is to provide easy access to a wide range of object -detection models in both industry and research settings. We design -PaddleDetection to be not only performant, production-ready but also highly -flexible, catering to research needs. +PaddleDetection的目的是为工业界和学术界提供丰富、易用的目标检测模型。不仅性能优越、易于部署，而且能够灵活的满足算法研究的需求。 -**Now all models in PaddleDetection require PaddlePaddle version 1.6 or higher, or suitable develop version.** +**目前检测库下模型均要求使用PaddlePaddle 1.6及以上版本或适当的develop版本。**
-## Introduction +## 简介 -Features: +特性： -- Production Ready: +- 易部署: - Key operations are implemented in C++ and CUDA, together with PaddlePaddle's -highly efficient inference engine, enables easy deployment in server environments. + PaddleDetection的模型中使用的核心算子均通过C++或CUDA实现，同时基于PaddlePaddle的高性能推理引擎可以方便地部署在多种硬件平台上。 -- Highly Flexible: +- 高灵活度： - Components are designed to be modular. Model architectures, as well as data -preprocess pipelines, can be easily customized with simple configuration -changes. + PaddleDetection通过模块化设计来解耦各个组件，基于配置文件可以轻松地搭建各种检测模型。 -- Performance Optimized: +- 高性能： - With the help of the underlying PaddlePaddle framework, faster training and -reduced GPU memory footprint is achieved. Notably, YOLOv3 training is -much faster compared to other frameworks. Another example is Mask-RCNN -(ResNet50), we managed to fit up to 4 images per GPU (Tesla V100 16GB) during -multi-GPU training. + 基于PaddlePaddle框架的高性能内核，在模型训练速度、显存占用上有一定的优势。例如，YOLOv3的训练速度快于其他框架，在Tesla V100 16GB环境下，Mask-RCNN(ResNet50)可以单卡Batch Size可以达到4 (甚至到5)。 -Supported Architectures: +支持的模型结构： -| | ResNet | ResNet-vd [1](#vd) | ResNeXt-vd | SENet | MobileNet | DarkNet | VGG | -| ------------------- | :----: | ----------------------------: | :--------: | :---: | :-------: | :-----: | :--: | -| Faster R-CNN | ✓ | ✓ | x | ✓ | ✗ | ✗ | ✗ | -| Faster R-CNN + FPN | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | -| Mask R-CNN | ✓ | ✓ | x | ✓ | ✗ | ✗ | ✗ | -| Mask R-CNN + FPN | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | -| Cascade Faster-RCNN | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ✗ | -| Cascade Mask-RCNN | ✓ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | -| RetinaNet | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | -| YOLOv3 | ✓ | ✗ | ✗ | ✗ | ✓ | ✓ | ✗ | -| SSD | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ | ✓ | +| | ResNet | ResNet-vd [1](#vd) | ResNeXt-vd | SENet | MobileNet | DarkNet | VGG | +|--------------------|:------:|------------------------------:|:----------:|:-----:|:---------:|:-------:|:---:| +| Faster R-CNN | ✓ | ✓ | x | ✓ | ✗ | ✗ | ✗ | +| Faster R-CNN + FPN | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | +| Mask R-CNN | ✓ | ✓ | x | ✓ | ✗ | ✗ | ✗ | +| Mask R-CNN + FPN | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | +| Cascade Faster-CNN | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ✗ | +| Cascade Mask-CNN | ✓ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | +| RetinaNet | ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | +| YOLOv3 | ✓ | ✗ | ✗ | ✗ | ✓ | ✓ | ✗ | +| SSD | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ | ✓ | -[1] [ResNet-vd](https://arxiv.org/pdf/1812.01187) models offer much improved accuracy with negligible performance cost. +[1] [ResNet-vd](https://arxiv.org/pdf/1812.01187) 模型提供了较大的精度提高和较少的性能损失。 -Advanced Features: +扩展特性： -- [x] **Synchronized Batch Norm**: currently used by YOLOv3. +- [x] **Synchronized Batch Norm**: 目前在YOLOv3中使用。 - [x] **Group Norm** - [x] **Modulated Deformable Convolution** - [x] **Deformable PSRoI Pooling** -**NOTE:** Synchronized batch normalization can only be used on multiple GPU devices, can not be used on CPU devices or single GPU device. +**注意:** Synchronized batch normalization 只能在多GPU环境下使用，不能在CPU环境或者单GPU环境下使用。 -## Get Started -- [Installation guide](docs/INSTALL.md) -- [Quick start on small dataset](docs/QUICK_STARTED.md) -- For detailed training and evaluation workflow, please refer to [GETTING_STARTED](docs/GETTING_STARTED.md) -- [Guide to preprocess pipeline and custom dataset](docs/DATA.md) -- [Introduction to the configuration workflow](docs/CONFIG.md) -- [Examples for detailed configuration explanation](docs/config_example/) +## 使用教程 + +- [安装说明](docs/INSTALL_cn.md) +- [快速开始](docs/QUICK_STARTED_cn.md) +- [训练、评估流程](docs/GETTING_STARTED_cn.md) +- [数据预处理及自定义数据集](docs/DATA_cn.md) +- [配置模块设计和介绍](docs/CONFIG_cn.md) +- [详细的配置信息和参数说明示例](docs/config_example/) - [IPython Notebook demo](demo/mask_rcnn_demo.ipynb) -- [Transfer learning document](docs/TRANSFER_LEARNING.md) +- [迁移学习教程](docs/TRANSFER_LEARNING_cn.md) -## Model Zoo +## 模型库 -- Pretrained models are available in the [PaddleDetection model zoo](docs/MODEL_ZOO.md). -- [Face detection models](configs/face_detection/README.md) -- [Pretrained models for pedestrian and vehicle detection](contrib/README.md) +- [模型库](docs/MODEL_ZOO_cn.md) +- [人脸检测模型](configs/face_detection/README.md) +- [行人检测和车辆检测预训练模型](contrib/README_cn.md) 针对不同场景的检测模型 +- [YOLOv3增强模型](docs/YOLOv3_ENHANCEMENT.md) 改进原始YOLOv3，精度达到41.4%，原论文精度为33.0%，同时预测速度也得到提升 +- [Objects365 2019 Challenge夺冠模型](docs/CACascadeRCNN.md) Objects365 Full Track任务中最好的单模型之一,精度达到31.7% -## Model compression -- [Quantization-aware training example](slim/quantization) -- [Model pruning example](slim/prune) +## 模型压缩 +- [量化训练压缩示例](slim/quantization) +- [剪枝压缩示例](slim/prune) -## Deployment +## 推理部署 -- [Export model for inference](docs/EXPORT_MODEL.md) -- [C++ inference](inference/README.md) +- [模型导出教程](docs/EXPORT_MODEL.md) +- [C++推理部署](inference/README.md) ## Benchmark -- [Inference benchmark](docs/BENCHMARK_INFER_cn.md) +- [推理Benchmark](docs/BENCHMARK_INFER_cn.md) -## Updates -#### 10/2019 +## 版本更新 -- Add enhanced YOLOv3 models, box mAP up to 41.4%. -- Face detection models included: BlazeFace, Faceboxes. -- Enrich COCO models, box mAP up to 51.9%. -- Add CACacascade RCNN, one of the best single model of Objects365 2019 challenge Full Track champion. -- Add pretrained models for pedestrian and vehicle detection. -- Support mixed-precision training. -- Add C++ inference depolyment. -- Add model compression examples. +### 10/2019 -#### 2/9/2019 +- 增加增强版YOLOv3模型，精度高达41.4%。 +- 增加人脸检测模型BlazeFace、Faceboxes。 +- 丰富基于COCO的模型，精度高达51.9%。 +- 增加Objects365 2019 Challenge上夺冠的最佳单模型之一CACascade-RCNN。 +- 增加行人检测和车辆检测预训练模型。 +- 支持FP16训练。 +- 增加跨平台的C++推理部署方案。 +- 增加模型压缩示例。 -- Add retrained models for GroupNorm. -- Add Cascade-Mask-RCNN+FPN. +### 2/9/2019 +- 增加GroupNorm模型。 +- 增加CascadeRCNN+Mask模型。 #### 5/8/2019 - -- Add a series of models ralated modulated Deformable Convolution. +- 增加Modulated Deformable Convolution系列模型。 #### 29/7/2019 -- Update Chinese docs for PaddleDetection -- Fix bug in R-CNN models when train and test at the same time -- Add ResNext101-vd + Mask R-CNN + FPN models -- Add YOLOv3 on VOC models +- 增加检测库中文文档 +- 修复R-CNN系列模型训练同时进行评估的问题 +- 新增ResNext101-vd + Mask R-CNN + FPN模型 +- 新增基于VOC数据集的YOLOv3模型 #### 3/7/2019 -- Initial release of PaddleDetection and detection model zoo -- Models included: Faster R-CNN, Mask R-CNN, Faster R-CNN+FPN, Mask - R-CNN+FPN, Cascade-Faster-RCNN+FPN, RetinaNet, YOLOv3, and SSD. - +- 首次发布PaddleDetection检测库和检测模型库 +- 模型包括：Faster R-CNN, Mask R-CNN, Faster R-CNN+FPN, Mask + R-CNN+FPN, Cascade-Faster-RCNN+FPN, RetinaNet, YOLOv3, 和SSD. -## Contributing +## 如何贡献代码 -Contributions are highly welcomed and we would really appreciate your feedback!! +我们非常欢迎你可以为PaddleDetection提供代码，也十分感谢你的反馈。 diff --git a/README_cn.md b/README_cn.md deleted file mode 100644 index 37291d516..000000000 --- a/README_cn.md +++ /dev/null @@ -1,125 +0,0 @@ -[English](README.md) | 简体中文 - -# PaddleDetection - -PaddleDetection的目的是为工业界和学术界提供丰富、易用的目标检测模型。不仅性能优越、易于部署，而且能够灵活的满足算法研究的需求。 - -**目前检测库下模型均要求使用PaddlePaddle 1.6及以上版本或适当的develop版本。** - -
- -
- - -## 简介 - -特性： - -- 易部署: - - PaddleDetection的模型中使用的核心算子均通过C++或CUDA实现，同时基于PaddlePaddle的高性能推理引擎可以方便地部署在多种硬件平台上。 - -- 高灵活度： - - PaddleDetection通过模块化设计来解耦各个组件，基于配置文件可以轻松地搭建各种检测模型。 - -- 高性能： - - 基于PaddlePaddle框架的高性能内核，在模型训练速度、显存占用上有一定的优势。例如，YOLOv3的训练速度快于其他框架，在Tesla V100 16GB环境下，Mask-RCNN(ResNet50)可以单卡Batch Size可以达到4 (甚至到5)。 - -支持的模型结构： - -| | ResNet | ResNet-vd [1](#vd) | ResNeXt-vd | SENet | MobileNet | DarkNet | VGG | -|--------------------|:------:|------------------------------:|:----------:|:-----:|:---------:|:-------:|:---:| -| Faster R-CNN | ✓ | ✓ | x | ✓ | ✗ | ✗ | ✗ | -| Faster R-CNN + FPN | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | -| Mask R-CNN | ✓ | ✓ | x | ✓ | ✗ | ✗ | ✗ | -| Mask R-CNN + FPN | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | -| Cascade Faster-CNN | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ✗ | -| Cascade Mask-CNN | ✓ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | -| RetinaNet | ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | -| YOLOv3 | ✓ | ✗ | ✗ | ✗ | ✓ | ✓ | ✗ | -| SSD | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ | ✓ | - -[1] [ResNet-vd](https://arxiv.org/pdf/1812.01187) 模型提供了较大的精度提高和较少的性能损失。 - -扩展特性： - -- [x] **Synchronized Batch Norm**: 目前在YOLOv3中使用。 -- [x] **Group Norm** -- [x] **Modulated Deformable Convolution** -- [x] **Deformable PSRoI Pooling** - -**注意:** Synchronized batch normalization 只能在多GPU环境下使用，不能在CPU环境或者单GPU环境下使用。 - - -## 使用教程 - -- [安装说明](docs/INSTALL_cn.md) -- [快速开始](docs/QUICK_STARTED_cn.md) -- [训练、评估流程](docs/GETTING_STARTED_cn.md) -- [数据预处理及自定义数据集](docs/DATA_cn.md) -- [配置模块设计和介绍](docs/CONFIG_cn.md) -- [详细的配置信息和参数说明示例](docs/config_example/) -- [IPython Notebook demo](demo/mask_rcnn_demo.ipynb) -- [迁移学习教程](docs/TRANSFER_LEARNING_cn.md) - -## 模型库 - -- [模型库](docs/MODEL_ZOO_cn.md) -- [人脸检测模型](configs/face_detection/README.md) -- [行人检测和车辆检测预训练模型](contrib/README_cn.md) - - -## 模型压缩 -- [量化训练压缩示例](slim/quantization) -- [剪枝压缩示例](slim/prune) - -## 推理部署 - -- [模型导出教程](docs/EXPORT_MODEL.md) -- [C++推理部署](inference/README.md) - -## Benchmark - -- [推理Benchmark](docs/BENCHMARK_INFER_cn.md) - - - -## 版本更新 - -### 10/2019 - -- 增加增强版YOLOv3模型，精度高达41.4%。 -- 增加人脸检测模型BlazeFace、Faceboxes。 -- 丰富基于COCO的模型，精度高达51.9%。 -- 增加Objects365 2019 Challenge上夺冠的最佳单模型之一CACascade-RCNN。 -- 增加行人检测和车辆检测预训练模型。 -- 支持FP16训练。 -- 增加跨平台的C++推理部署方案。 -- 增加模型压缩示例。 - - -### 2/9/2019 -- 增加GroupNorm模型。 -- 增加CascadeRCNN+Mask模型。 - -#### 5/8/2019 -- 增加Modulated Deformable Convolution系列模型。 - -#### 29/7/2019 - -- 增加检测库中文文档 -- 修复R-CNN系列模型训练同时进行评估的问题 -- 新增ResNext101-vd + Mask R-CNN + FPN模型 -- 新增基于VOC数据集的YOLOv3模型 - -#### 3/7/2019 - -- 首次发布PaddleDetection检测库和检测模型库 -- 模型包括：Faster R-CNN, Mask R-CNN, Faster R-CNN+FPN, Mask - R-CNN+FPN, Cascade-Faster-RCNN+FPN, RetinaNet, YOLOv3, 和SSD. - -## 如何贡献代码 - -我们非常欢迎你可以为PaddleDetection提供代码，也十分感谢你的反馈。 diff --git a/README_en.md b/README_en.md new file mode 100644 index 000000000..e055beadc --- /dev/null +++ b/README_en.md @@ -0,0 +1,138 @@ +English | [简体中文](README.md) + +# PaddleDetection + +The goal of PaddleDetection is to provide easy access to a wide range of object +detection models in both industry and research settings. We design +PaddleDetection to be not only performant, production-ready but also highly +flexible, catering to research needs. + +**Now all models in PaddleDetection require PaddlePaddle version 1.6 or higher, or suitable develop version.** + +
+ +
+ + +## Introduction + +Features: + +- Production Ready: + + Key operations are implemented in C++ and CUDA, together with PaddlePaddle's +highly efficient inference engine, enables easy deployment in server environments. + +- Highly Flexible: + + Components are designed to be modular. Model architectures, as well as data +preprocess pipelines, can be easily customized with simple configuration +changes. + +- Performance Optimized: + + With the help of the underlying PaddlePaddle framework, faster training and +reduced GPU memory footprint is achieved. Notably, YOLOv3 training is +much faster compared to other frameworks. Another example is Mask-RCNN +(ResNet50), we managed to fit up to 4 images per GPU (Tesla V100 16GB) during +multi-GPU training. + +Supported Architectures: + +| | ResNet | ResNet-vd [1](#vd) | ResNeXt-vd | SENet | MobileNet | DarkNet | VGG | +| ------------------- | :----: | ----------------------------: | :--------: | :---: | :-------: | :-----: | :--: | +| Faster R-CNN | ✓ | ✓ | x | ✓ | ✗ | ✗ | ✗ | +| Faster R-CNN + FPN | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | +| Mask R-CNN | ✓ | ✓ | x | ✓ | ✗ | ✗ | ✗ | +| Mask R-CNN + FPN | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | +| Cascade Faster-RCNN | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ✗ | +| Cascade Mask-RCNN | ✓ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | +| RetinaNet | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | +| YOLOv3 | ✓ | ✗ | ✗ | ✗ | ✓ | ✓ | ✗ | +| SSD | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ | ✓ | + +[1] [ResNet-vd](https://arxiv.org/pdf/1812.01187) models offer much improved accuracy with negligible performance cost. + +Advanced Features: + +- [x] **Synchronized Batch Norm**: currently used by YOLOv3. +- [x] **Group Norm** +- [x] **Modulated Deformable Convolution** +- [x] **Deformable PSRoI Pooling** + +**NOTE:** Synchronized batch normalization can only be used on multiple GPU devices, can not be used on CPU devices or single GPU device. + +## Get Started + +- [Installation guide](docs/INSTALL.md) +- [Quick start on small dataset](docs/QUICK_STARTED.md) +- For detailed training and evaluation workflow, please refer to [GETTING_STARTED](docs/GETTING_STARTED.md) +- [Guide to preprocess pipeline and custom dataset](docs/DATA.md) +- [Introduction to the configuration workflow](docs/CONFIG.md) +- [Examples for detailed configuration explanation](docs/config_example/) +- [IPython Notebook demo](demo/mask_rcnn_demo.ipynb) +- [Transfer learning document](docs/TRANSFER_LEARNING.md) + +## Model Zoo + +- Pretrained models are available in the [PaddleDetection model zoo](docs/MODEL_ZOO.md). +- [Face detection models](configs/face_detection/README.md) +- [Pretrained models for pedestrian and vehicle detection](contrib/README.md) Models for object detection in specific scenarios. +- [YOLOv3 enhanced model](docs/YOLOv3_ENHANCEMENT.md) Compared to MAP of 33.0% in paper, enhanced YOLOv3 reaches the MAP of 41.4% and inference speed is improved as well +- [Objects365 2019 Challenge champion model](docs/CACascadeRCNN.md) One of the best single models in Objects365 Full Track of which MAP reaches 31.7%. + +## Model compression + +- [Quantization-aware training example](slim/quantization) +- [Model pruning example](slim/prune) + +## Deployment + +- [Export model for inference](docs/EXPORT_MODEL.md) +- [C++ inference](inference/README.md) + +## Benchmark + +- [Inference benchmark](docs/BENCHMARK_INFER_cn.md) + + +## Updates + +#### 10/2019 + +- Add enhanced YOLOv3 models, box mAP up to 41.4%. +- Face detection models included: BlazeFace, Faceboxes. +- Enrich COCO models, box mAP up to 51.9%. +- Add CACacascade RCNN, one of the best single model of Objects365 2019 challenge Full Track champion. +- Add pretrained models for pedestrian and vehicle detection. +- Support mixed-precision training. +- Add C++ inference depolyment. +- Add model compression examples. + +#### 2/9/2019 + +- Add retrained models for GroupNorm. + +- Add Cascade-Mask-RCNN+FPN. + +#### 5/8/2019 + +- Add a series of models ralated modulated Deformable Convolution. + +#### 29/7/2019 + +- Update Chinese docs for PaddleDetection +- Fix bug in R-CNN models when train and test at the same time +- Add ResNext101-vd + Mask R-CNN + FPN models +- Add YOLOv3 on VOC models + +#### 3/7/2019 + +- Initial release of PaddleDetection and detection model zoo +- Models included: Faster R-CNN, Mask R-CNN, Faster R-CNN+FPN, Mask + R-CNN+FPN, Cascade-Faster-RCNN+FPN, RetinaNet, YOLOv3, and SSD. + + +## Contributing + +Contributions are highly welcomed and we would really appreciate your feedback!! diff --git a/contrib/README.md b/contrib/README.md index 11f93b85b..52a1179cf 100644 --- a/contrib/README.md +++ b/contrib/README.md @@ -17,7 +17,7 @@ The network for detecting vehicles is YOLOv3, the backbone of which is Dacknet53 ### 2. Configuration for training -PaddleDetection provides users with a configuration file [yolov3_darnet.yml](https://github.com/PaddlePaddle/models/blob/develop/PaddleCV/PaddleDetection/configs/yolov3_darknet.yml) to train YOLOv3 on the COCO dataset, compared with this file, we modify some parameters as followed to conduct the training for vehicle detection: +PaddleDetection provides users with a configuration file [yolov3_darknet.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/yolov3_darknet.yml) to train YOLOv3 on the COCO dataset, compared with this file, we modify some parameters as followed to conduct the training for vehicle detection: * max_iters: 120000 * num_classes: 6 @@ -67,7 +67,7 @@ The network for detecting vehicles is YOLOv3, the backbone of which is Dacknet53 ### 2. Configuration for training -PaddleDetection provides users with a configuration file [yolov3_darnet.yml](https://github.com/PaddlePaddle/models/blob/develop/PaddleCV/PaddleDetection/configs/yolov3_darknet.yml) to train YOLOv3 on the COCO dataset, compared with this file, we modify some parameters as followed to conduct the training for pedestrian detection: +PaddleDetection provides users with a configuration file [yolov3_darknet.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/yolov3_darknet.yml) to train YOLOv3 on the COCO dataset, compared with this file, we modify some parameters as followed to conduct the training for pedestrian detection: * max_iters: 200000 * num_classes: 1 diff --git a/contrib/README_cn.md b/contrib/README_cn.md index ca2a0fda3..d5278bc1c 100644 --- a/contrib/README_cn.md +++ b/contrib/README_cn.md @@ -18,7 +18,7 @@ Backbone为Dacknet53的YOLOv3。 ### 2. 训练参数配置 -PaddleDetection提供了使用COCO数据集对YOLOv3进行训练的参数配置文件[yolov3_darnet.yml](https://github.com/PaddlePaddle/models/blob/develop/PaddleCV/PaddleDetection/configs/yolov3_darknet.yml)，与之相比，在进行车辆检测的模型训练时，我们对以下参数进行了修改： +PaddleDetection提供了使用COCO数据集对YOLOv3进行训练的参数配置文件[yolov3_darnet.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/yolov3_darknet.yml)，与之相比，在进行车辆检测的模型训练时，我们对以下参数进行了修改： * max_iters: 120000 * num_classes: 6 @@ -69,7 +69,7 @@ Backbone为Dacknet53的YOLOv3。 ### 2. 训练参数配置 -PaddleDetection提供了使用COCO数据集对YOLOv3进行训练的参数配置文件[yolov3_darnet.yml](https://github.com/PaddlePaddle/models/blob/develop/PaddleCV/PaddleDetection/configs/yolov3_darknet.yml)，与之相比，在进行行人检测的模型训练时，我们对以下参数进行了修改： +PaddleDetection提供了使用COCO数据集对YOLOv3进行训练的参数配置文件[yolov3_darknet.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/yolov3_darknet.yml)，与之相比，在进行行人检测的模型训练时，我们对以下参数进行了修改： * max_iters: 200000 * num_classes: 1 diff --git a/demo/mask_rcnn_demo.ipynb b/demo/mask_rcnn_demo.ipynb index 860b18504..f767cf748 100644 --- a/demo/mask_rcnn_demo.ipynb +++ b/demo/mask_rcnn_demo.ipynb @@ -28,7 +28,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "/home/yang/models/PaddleCV/PaddleDetection\n" + "/home/yang/PaddleDetection\n" ] } ], diff --git a/docs/INSTALL.md b/docs/INSTALL.md index 7ac6dd8e3..97b3b1435 100644 --- a/docs/INSTALL.md +++ b/docs/INSTALL.md @@ -71,13 +71,11 @@ COCO-API is needed for running. Installation is as follows: **Clone Paddle models repository:** -You can clone Paddle models and change working directory to PaddleDetection -with the following commands: +You can clone PaddleDetection with the following commands: ``` -cd -git clone https://github.com/PaddlePaddle/models -cd models/PaddleCV/PaddleDetection +cd +git clone https://github.com/PaddlePaddle/PaddleDetection.git ``` **Install Python dependencies:** diff --git a/docs/INSTALL_cn.md b/docs/INSTALL_cn.md index 5ad6185d5..7ebf95620 100644 --- a/docs/INSTALL_cn.md +++ b/docs/INSTALL_cn.md @@ -67,12 +67,11 @@ python -c "import paddle; print(paddle.__version__)" **克隆Paddle models模型库：** -您可以通过以下命令克隆Paddle models模型库并切换工作目录至PaddleDetection： +您可以通过以下命令克隆PaddleDetection： ``` -cd -git clone https://github.com/PaddlePaddle/models -cd models/PaddleCV/PaddleDetection +cd +git clone https://github.com/PaddlePaddle/PaddleDetection.git ``` **安装Python依赖库：** diff --git a/docs/MODEL_ZOO.md b/docs/MODEL_ZOO.md index 7f32742dc..02e8b7e79 100644 --- a/docs/MODEL_ZOO.md +++ b/docs/MODEL_ZOO.md @@ -90,7 +90,7 @@ The backbone models pretrained on ImageNet are available. All backbone models ar #### Notes: - Deformable ConvNets v2(dcn_v2) reference from [Deformable ConvNets v2](https://arxiv.org/abs/1811.11168). - `c3-c5` means adding `dcn` in resnet stage 3 to 5. -- Detailed configuration file in [configs/dcn](https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/PaddleDetection/configs/dcn) +- Detailed configuration file in [configs/dcn](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn) ### Group Normalization | Backbone | Type | Image/gpu | Lr schd | Box AP | Mask AP | Download | @@ -100,7 +100,7 @@ The backbone models pretrained on ImageNet are available. All backbone models ar #### Notes: - Group Normalization reference from [Group Normalization](https://arxiv.org/abs/1803.08494). -- Detailed configuration file in [configs/gn](https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/PaddleDetection/configs/gn) +- Detailed configuration file in [configs/gn](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/gn) ### YOLO v3 diff --git a/docs/MODEL_ZOO_cn.md b/docs/MODEL_ZOO_cn.md index 31794481c..b889cd9a6 100644 --- a/docs/MODEL_ZOO_cn.md +++ b/docs/MODEL_ZOO_cn.md @@ -86,7 +86,7 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型 #### 注意事项: - Deformable卷积网络v2(dcn_v2)参考自论文[Deformable ConvNets v2](https://arxiv.org/abs/1811.11168). - `c3-c5`意思是在resnet模块的3到5阶段增加`dcn`. -- 详细的配置文件在[configs/dcn](https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/PaddleDetection/configs/dcn) +- 详细的配置文件在[configs/dcn](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn) ### Group Normalization | 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 | Box AP | Mask AP | 下载 | @@ -96,7 +96,7 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型 #### 注意事项: - Group Normalization参考论文[Group Normalization](https://arxiv.org/abs/1803.08494). -- 详细的配置文件在[configs/gn](https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/PaddleDetection/configs/gn) +- 详细的配置文件在[configs/gn](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/gn) ### YOLO v3 diff --git a/slim/distillation/README.md b/slim/distillation/README.md index e970cc42b..e2666cd01 100755 --- a/slim/distillation/README.md +++ b/slim/distillation/README.md @@ -7,7 +7,7 @@ 该示例使用PaddleSlim提供的[蒸馏策略](https://github.com/PaddlePaddle/models/blob/develop/PaddleSlim/docs/tutorial.md#3-蒸馏)对检测库中的模型进行蒸馏训练。 在阅读该示例前，建议您先了解以下内容： -- [检测库的常规训练方法](https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/PaddleDetection) +- [检测库的常规训练方法](https://github.com/PaddlePaddle/PaddleDetection) - [PaddleSlim使用文档](https://github.com/PaddlePaddle/models/blob/develop/PaddleSlim/docs/usage.md) @@ -61,7 +61,7 @@ strategies: ## 训练 -根据[PaddleDetection/tools/train.py](https://github.com/PaddlePaddle/models/blob/develop/PaddleCV/PaddleDetection/tools/train.py)编写压缩脚本compress.py。 +根据[PaddleDetection/tools/train.py](https://github.com/PaddlePaddle/PaddleDetection/tree/master/tools/train.py)编写压缩脚本compress.py。 在该脚本中定义了Compressor对象，用于执行压缩任务。 diff --git a/slim/prune/README.md b/slim/prune/README.md index b06fdd2bd..16509624d 100644 --- a/slim/prune/README.md +++ b/slim/prune/README.md @@ -8,7 +8,7 @@ 在阅读该示例前，建议您先了解以下内容： - 检测库的常规训练方法 -- [检测模型数据准备](https://github.com/PaddlePaddle/models/blob/develop/PaddleCV/PaddleDetection/docs/INSTALL_cn.md#%E6%95%B0%E6%8D%AE%E9%9B%86) +- [检测模型数据准备](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/INSTALL_cn.md#%E6%95%B0%E6%8D%AE%E9%9B%86) - [PaddleSlim使用文档](https://github.com/PaddlePaddle/models/blob/develop/PaddleSlim/docs/usage.md) diff --git a/slim/quantization/README.md b/slim/quantization/README.md index acb4c9efc..159b7a7f8 100644 --- a/slim/quantization/README.md +++ b/slim/quantization/README.md @@ -7,7 +7,7 @@ 该示例使用PaddleSlim提供的[量化压缩策略](https://github.com/PaddlePaddle/models/blob/develop/PaddleSlim/docs/tutorial.md#1-quantization-aware-training%E9%87%8F%E5%8C%96%E4%BB%8B%E7%BB%8D)对分类模型进行压缩。 在阅读该示例前，建议您先了解以下内容： -- [检测模型的常规训练方法](https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/PaddleDetection) +- [检测模型的常规训练方法](https://github.com/PaddlePaddle/PaddleDetection) - [PaddleSlim使用文档](https://github.com/PaddlePaddle/models/blob/develop/PaddleSlim/docs/usage.md) @@ -29,7 +29,7 @@ 根据运行结果可看到Variable的名字为：`multiclass_nms_0.tmp_0`。 ## 训练 -根据 [PaddleCV/PaddleDetection/tools/train.py](https://github.com/PaddlePaddle/models/blob/develop/PaddleCV/PaddleDetection/tools/train.py) 编写压缩脚本compress.py。 +根据 [tools/train.py](https://github.com/PaddlePaddle/PaddleDetection/tree/master/tools/train.py) 编写压缩脚本compress.py。 在该脚本中定义了Compressor对象，用于执行压缩任务。 通过`python compress.py --help`查看可配置参数，简述如下： -- GitLab