diff --git a/configs/faster_rcnn/README.md b/configs/faster_rcnn/README.md index cb176afffc90348f2491fbbdfd5a2bd3fc94a1bf..92a547ce4701e7aa20c269d2bc776e879d338654 100644 --- a/configs/faster_rcnn/README.md +++ b/configs/faster_rcnn/README.md @@ -21,7 +21,6 @@ | ResNet50-vd-SSLDv2-FPN | Faster | 1 | 1x | ---- | 41.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_ssld_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_vd_fpn_ssld_1x_coco.yml) | | ResNet50-vd-SSLDv2-FPN | Faster | 1 | 2x | ---- | 42.3 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_ssld_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_vd_ssld_fpn_2x_coco.yml) | -**注意:** Faster R-CNN模型精度依赖Paddle develop分支修改,精度复现须使用[每日版本](https://www.paddlepaddle.org.cn/documentation/docs/zh/install/Tables.html#whl-dev)或2.0.1版本(将于2021.03发布),使用Paddle 2.0.0版本会有少量精度损失。 ## Citations ``` diff --git a/configs/fcos/README.md b/configs/fcos/README.md index f3333ada6ee6da29008cc5ac7e372bbe3c2958ef..2ba0893d8b81e50f1b4fb4259c62d2df9b31c712 100644 --- a/configs/fcos/README.md +++ b/configs/fcos/README.md @@ -19,7 +19,6 @@ FCOS (Fully Convolutional One-Stage Object Detection) is a fast anchor-free obje **Notes:** - FCOS is trained on COCO train2017 dataset and evaluated on val2017 results of `mAP(IoU=0.5:0.95)`. -- FCOS training performace is dependented on Paddle develop branch, performance reproduction shoule based on [Paddle daily version](https://www.paddlepaddle.org.cn/documentation/docs/zh/install/Tables.html#whl-dev) or Paddle 2.0.1(will be published on 2021.03), performace will loss slightly is training base on Paddle 2.0.0 ## Citations ``` diff --git a/configs/mask_rcnn/README.md b/configs/mask_rcnn/README.md index 300d67b466e2e99f9d56882f470a5487cc7bac85..020fe99f78e5d1c84c47929381090c6311694529 100644 --- a/configs/mask_rcnn/README.md +++ b/configs/mask_rcnn/README.md @@ -17,7 +17,6 @@ | ResNet50-vd-SSLDv2-FPN | Mask | 1 | 1x | ---- | 42.0 | 38.2 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_vd_fpn_ssld_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_r50_vd_fpn_ssld_1x_coco.yml) | | ResNet50-vd-SSLDv2-FPN | Mask | 1 | 2x | ---- | 42.7 | 38.9 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_vd_fpn_ssld_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_r50_vd_fpn_ssld_2x_coco.yml) | -**注意:** Mask R-CNN模型精度依赖Paddle develop分支修改,精度复现须使用[每日版本](https://www.paddlepaddle.org.cn/documentation/docs/zh/install/Tables.html#whl-dev)或2.0.1版本(将于2021.03发布),使用Paddle 2.0.0版本会有少量精度损失。 ## Citations ``` diff --git a/configs/pedestrian/README.md b/configs/pedestrian/README.md index fc7100b95ffe3328023653f54057bd4f36078cb2..f140360ffd00e12f66542ca6cc676954d34ff9cc 100644 --- a/configs/pedestrian/README.md +++ b/configs/pedestrian/README.md @@ -5,7 +5,7 @@ We provide some models implemented by PaddlePaddle to detect objects in specific | Task | Algorithm | Box AP | Download | Configs | |:---------------------|:---------:|:------:| :-------------------------------------------------------------------------------------: |:------:| -| Pedestrian Detection | YOLOv3 | 51.8 | [model](https://paddledet.bj.bcebos.com/models/pedestrian_yolov3_darknet.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/pedestrian/pedestrian_yolov3_darknet.yml) | +| Pedestrian Detection | YOLOv3 | 51.8 | [model](https://paddledet.bj.bcebos.com/models/pedestrian_yolov3_darknet.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/pedestrian/pedestrian_yolov3_darknet.yml) | ## Pedestrian Detection @@ -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_darknet53_270e_coco.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/dygraph/configs/yolov3/yolov3_darknet53_270e_coco.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_darknet53_270e_coco.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/yolov3/yolov3_darknet53_270e_coco.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: * num_classes: 1 * dataset_dir: dataset/pedestrian @@ -45,6 +45,6 @@ python -u tools/infer.py -c configs/pedestrian/pedestrian_yolov3_darknet.yml \ Some inference results are visualized below: -![](https://github.com/PaddlePaddle/PaddleDetection/tree/master/docs/images/PedestrianDetection_001.png) +![](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/docs/images/PedestrianDetection_001.png) -![](https://github.com/PaddlePaddle/PaddleDetection/tree/master/docs/images/PedestrianDetection_004.png) +![](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/docs/images/PedestrianDetection_004.png) diff --git a/configs/pedestrian/README_cn.md b/configs/pedestrian/README_cn.md index 112c55806153ee4e6e556e977da2395e6a18181b..6439e1f1d9ae70167e8d50158bae305f1c9cc6d3 100644 --- a/configs/pedestrian/README_cn.md +++ b/configs/pedestrian/README_cn.md @@ -5,7 +5,7 @@ | 任务 | 算法 | 精度(Box AP) | 下载 | 配置文件 | |:---------------------|:---------:|:------:| :---------------------------------------------------------------------------------: | :------:| -| 行人检测 | YOLOv3 | 51.8 | [下载链接](https://paddledet.bj.bcebos.com/models/pedestrian_yolov3_darknet.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/pedestrian/pedestrian_yolov3_darknet.yml) | +| 行人检测 | YOLOv3 | 51.8 | [下载链接](https://paddledet.bj.bcebos.com/models/pedestrian_yolov3_darknet.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/pedestrian/pedestrian_yolov3_darknet.yml) | ## 行人检测(Pedestrian Detection) @@ -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_darknet53_270e_coco.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/dygraph/configs/yolov3/yolov3_darknet53_270e_coco.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_darknet53_270e_coco.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/yolov3/yolov3_darknet53_270e_coco.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: * num_classes: 1 * dataset_dir: dataset/pedestrian @@ -46,6 +46,6 @@ python -u tools/infer.py -c configs/pedestrian/pedestrian_yolov3_darknet.yml \ 预测结果示例: -![](../../../docs/images/PedestrianDetection_001.png) +![](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/docs/images/PedestrianDetection_001.png) -![](../../../docs/images/PedestrianDetection_004.png) +![](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/docs/images/PedestrianDetection_004.png) diff --git a/configs/ppyolo/README.md b/configs/ppyolo/README.md index ba73b470a410e3519883bc09249a7b6d4999223a..646c14fe1e9296db88c54c9b3cb9074b9ac325f8 100644 --- a/configs/ppyolo/README.md +++ b/configs/ppyolo/README.md @@ -56,7 +56,7 @@ PP-YOLO improved performance and speed of YOLOv3 with following methods: **Notes:** - PP-YOLO is trained on COCO train2017 dataset and evaluated on val2017 & test-dev2017 dataset,Box APtest is evaluation results of `mAP(IoU=0.5:0.95)`. -- PP-YOLO used 8 GPUs for training and mini-batch size as 24 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/FAQ.md). +- PP-YOLO used 8 GPUs for training and mini-batch size as 24 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/docs/FAQ.md). - PP-YOLO inference speed is tesed on single Tesla V100 with batch size as 1, CUDA 10.2, CUDNN 7.5.1, TensorRT 5.1.2.2 in TensorRT mode. - PP-YOLO FP32 inference speed testing uses inference model exported by `tools/export_model.py` and benchmarked by running `depoly/python/infer.py` with `--run_benchmark`. All testing results do not contains the time cost of data reading and post-processing(NMS), which is same as [YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet) in testing method. - TensorRT FP16 inference speed testing exclude the time cost of bounding-box decoding(`yolo_box`) part comparing with FP32 testing above, which means that data reading, bounding-box decoding and post-processing(NMS) is excluded(test method same as [YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet) too) @@ -71,7 +71,7 @@ PP-YOLO improved performance and speed of YOLOv3 with following methods: **Notes:** - PP-YOLO_MobileNetV3 is trained on COCO train2017 datast and evaluated on val2017 dataset,Box APval is evaluation results of `mAP(IoU=0.5:0.95)`, Box APval is evaluation results of `mAP(IoU=0.5)`. -- PP-YOLO_MobileNetV3 used 4 GPUs for training and mini-batch size as 32 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/FAQ.md). +- PP-YOLO_MobileNetV3 used 4 GPUs for training and mini-batch size as 32 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/docs/FAQ.md). - PP-YOLO_MobileNetV3 inference speed is tested on Kirin 990 with 1 thread. ### PP-YOLO tiny @@ -84,7 +84,7 @@ PP-YOLO improved performance and speed of YOLOv3 with following methods: **Notes:** - PP-YOLO-tiny is trained on COCO train2017 datast and evaluated on val2017 dataset,Box APval is evaluation results of `mAP(IoU=0.5:0.95)`, Box APval is evaluation results of `mAP(IoU=0.5)`. -- PP-YOLO-tiny used 8 GPUs for training and mini-batch size as 32 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/FAQ.md). +- PP-YOLO-tiny used 8 GPUs for training and mini-batch size as 32 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/docs/FAQ.md). - PP-YOLO-tiny inference speed is tested on Kirin 990 with 4 threads by arm8 - we alse provide PP-YOLO-tiny post quant inference model, which can compress model to **1.3MB** with nearly no inference on inference speed and performance @@ -187,7 +187,7 @@ Optimizing method and ablation experiments of PP-YOLO compared with YOLOv3. - Performance and inference spedd are measure with input shape as 608 - All models are trained on COCO train2017 datast and evaluated on val2017 & test-dev2017 dataset,`Box AP` is evaluation results as `mAP(IoU=0.5:0.95)`. - Inference speed is tested on single Tesla V100 with batch size as 1 following test method and environment configuration in benchmark above. -- [YOLOv3-DarkNet53](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_darknet53_270e_coco.yml) with mAP as 39.0 is optimized YOLOv3 model in PaddleDetection,see [Model Zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/MODEL_ZOO.md) for details. +- [YOLOv3-DarkNet53](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_darknet53_270e_coco.yml) with mAP as 39.0 is optimized YOLOv3 model in PaddleDetection,see [Model Zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/MODEL_ZOO.md) for details. ## Citation diff --git a/configs/slim/README.md b/configs/slim/README.md index a4bb549dc2278a6ee636651f6bd863e1fec35e34..ad7d099ae91c851a74ea60a6592b10b9c2fd913d 100755 --- a/configs/slim/README.md +++ b/configs/slim/README.md @@ -12,12 +12,11 @@ ## 实验环境 - Python 3.7+ -- PaddlePaddle >= 2.0.0 +- PaddlePaddle >= 2.0.1 - PaddleSlim >= 2.0.0 - CUDA 9.0+ - cuDNN >=7.5 -**注意:** 量化训练需要依赖Paddle develop分支,可在[PaddlePaddle每日版本](https://www.paddlepaddle.org.cn/documentation/docs/zh/install/Tables.html#whl-dev)中下载安装合适的PaddlePaddle版本。 ## 快速开始 diff --git a/configs/vehicle/README.md b/configs/vehicle/README.md index 9219e9c1f9ad60d84754fb618b390fbda8a0434b..28a524eb17b9a416641d709c99016667bf3cf6e0 100644 --- a/configs/vehicle/README.md +++ b/configs/vehicle/README.md @@ -1,11 +1,11 @@ -English | [简体中文](CONTRIB_cn.md) +English | [简体中文](README_cn.md) # PaddleDetection applied for specific scenarios We provide some models implemented by PaddlePaddle to detect objects in specific scenarios, users can download the models and use them in these scenarios. | Task | Algorithm | Box AP | Download | Configs | |:---------------------|:---------:|:------:| :-------------------------------------------------------------------------------------: |:------:| -| Vehicle Detection | YOLOv3 | 54.5 | [model](https://paddledet.bj.bcebos.com/models/vehicle_yolov3_darknet.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/vehicle/vehicle_yolov3_darknet.yml) | +| Vehicle Detection | YOLOv3 | 54.5 | [model](https://paddledet.bj.bcebos.com/models/vehicle_yolov3_darknet.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/vehicle/vehicle_yolov3_darknet.yml) | ## Vehicle Detection @@ -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_darknet53_270e_coco.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/dygraph/configs/yolov3/yolov3_darknet53_270e_coco.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_darknet53_270e_coco.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/yolov3/yolov3_darknet53_270e_coco.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: * num_classes: 6 * anchors: [[8, 9], [10, 23], [19, 15], [23, 33], [40, 25], [54, 50], [101, 80], [139, 145], [253, 224]] @@ -48,6 +48,6 @@ python -u tools/infer.py -c configs/vehicle/vehicle_yolov3_darknet.yml \ Some inference results are visualized below: -![](https://github.com/PaddlePaddle/PaddleDetection/tree/master/docs/images/VehicleDetection_001.jpeg) +![](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/docs/images/VehicleDetection_001.jpeg) -![](https://github.com/PaddlePaddle/PaddleDetection/tree/master/docs/images/VehicleDetection_005.png) +![](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/docs/images/VehicleDetection_005.png) diff --git a/configs/vehicle/README_cn.md b/configs/vehicle/README_cn.md index 9a030fdc278127fc8af946f756cadff4f39943d7..275075d69fe9787eff57643e269c707aa1a844aa 100644 --- a/configs/vehicle/README_cn.md +++ b/configs/vehicle/README_cn.md @@ -1,11 +1,11 @@ -[English](CONTRIB.md) | 简体中文 +[English](README.md) | 简体中文 # 特色垂类检测模型 我们提供了针对不同场景的基于PaddlePaddle的检测模型,用户可以下载模型进行使用。 | 任务 | 算法 | 精度(Box AP) | 下载 | 配置文件 | |:---------------------|:---------:|:------:| :---------------------------------------------------------------------------------: | :------:| -| 车辆检测 | YOLOv3 | 54.5 | [下载链接](https://paddledet.bj.bcebos.com/models/vehicle_yolov3_darknet.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/vehicle/vehicle_yolov3_darknet.yml) | +| 车辆检测 | YOLOv3 | 54.5 | [下载链接](https://paddledet.bj.bcebos.com/models/vehicle_yolov3_darknet.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/vehicle/vehicle_yolov3_darknet.yml) | ## 车辆检测(Vehicle Detection) @@ -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_darknet53_270e_coco.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/dygraph/configs/yolov3/yolov3_darknet53_270e_coco.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_darknet53_270e_coco.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/yolov3/yolov3_darknet53_270e_coco.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: * num_classes: 6 * anchors: [[8, 9], [10, 23], [19, 15], [23, 33], [40, 25], [54, 50], [101, 80], [139, 145], [253, 224]] @@ -49,6 +49,6 @@ python -u tools/infer.py -c configs/vehicle/vehicle_yolov3_darknet.yml \ 预测结果示例: -![](https://github.com/PaddlePaddle/PaddleDetection/tree/master/docs/images/VehicleDetection_001.jpeg) +![](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/docs/images/VehicleDetection_001.jpeg) -![](https://github.com/PaddlePaddle/PaddleDetection/tree/master/docs/images/VehicleDetection_005.png) +![](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/docs/images/VehicleDetection_005.png) diff --git a/deploy/serving/README.md b/deploy/serving/README.md index 812c03044ee8cda82acaea557a125a464c38df4c..ee8aae384c952cb8a1125aaa526fd1ad95504de0 100644 --- a/deploy/serving/README.md +++ b/deploy/serving/README.md @@ -13,7 +13,7 @@ python tools/infer.py -c --infer_img=demo/000000014439.jpg -o use_gpu=True weig 请参考[PaddleServing](https://github.com/PaddlePaddle/Serving/tree/v0.5.0) 中安装教程安装 ## 3. 导出模型 -PaddleDetection在训练过程包括网络的前向和优化器相关参数,而在部署过程中,我们只需要前向参数,具体参考:[导出模型](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/advanced_tutorials/deploy/EXPORT_MODEL.md) +PaddleDetection在训练过程包括网络的前向和优化器相关参数,而在部署过程中,我们只需要前向参数,具体参考:[导出模型](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/advanced_tutorials/deploy/EXPORT_MODEL.md) ``` python tools/export_model.py -c configs/yolov3/yolov3_darknet53_270e_coco.yml -o weights=weights/yolov3_darknet53_270e_coco.pdparams --export_serving_model=True diff --git a/docs/MODEL_ZOO_cn.md b/docs/MODEL_ZOO_cn.md index 5d17e809dfe852ac8619d495b917c850cadd46a4..5cad37311eedfc3dbcb0d751d101858749c0a528 100644 --- a/docs/MODEL_ZOO_cn.md +++ b/docs/MODEL_ZOO_cn.md @@ -30,36 +30,36 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型 ### Faster R-CNN -请参考[Faster R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/) +请参考[Faster R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/) ### Mask R-CNN -请参考[Mask R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/) +请参考[Mask R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/) ### Cascade R-CNN -请参考[Cascade R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/cascade_rcnn/) +请参考[Cascade R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/developh/configs/cascade_rcnn/) ### YOLOv3 -请参考[YOLOv3](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/) +请参考[YOLOv3](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/) ### SSD -请参考[SSD](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/ssd/) +请参考[SSD](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ssd/) ### FCOS -请参考[FCOS](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/fcos/) +请参考[FCOS](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/fcos/) ### SOLOv2 -请参考[SOLOv2](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/solov2/) +请参考[SOLOv2](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/solov2/) ### PP-YOLO -请参考[PP-YOLO](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/ppyolo/) +请参考[PP-YOLO](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/) ### TTFNet -请参考[TTFNet](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/ttfnet/) +请参考[TTFNet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ttfnet/) diff --git a/ppdet/data/source/dataset.py b/ppdet/data/source/dataset.py index 6ca0273010966e20504dbad5166584107a81f84c..27916731d2e191dc0dbdcdb0283e1c7675034b08 100644 --- a/ppdet/data/source/dataset.py +++ b/ppdet/data/source/dataset.py @@ -77,6 +77,11 @@ class DetDataset(Dataset): copy.deepcopy(self.roidbs[np.random.randint(n)]) for _ in range(3) ] + if isinstance(roidb, Sequence): + for r in roidb: + r['curr_iter'] = self._curr_iter + else: + roidb['curr_iter'] = self._curr_iter roidb['curr_iter'] = self._curr_iter self._curr_iter += 1 diff --git a/ppdet/modeling/heads/ttf_head.py b/ppdet/modeling/heads/ttf_head.py index 00591829516f082f9af7112c92511426b1416bdc..1d80ad28bd71ff625f2b64cdc0ed9ea9d2738068 100644 --- a/ppdet/modeling/heads/ttf_head.py +++ b/ppdet/modeling/heads/ttf_head.py @@ -72,8 +72,7 @@ class HMHead(nn.Layer): in_channels=ch_in if i == 0 else ch_out, out_channels=ch_out, kernel_size=3, - weight_attr=ParamAttr(initializer=Normal(0, 0.01)), - name='hm.' + name)) + weight_attr=ParamAttr(initializer=Normal(0, 0.01)))) else: head_conv.add_sublayer( name, @@ -151,8 +150,7 @@ class WHHead(nn.Layer): in_channels=ch_in if i == 0 else ch_out, out_channels=ch_out, kernel_size=3, - weight_attr=ParamAttr(initializer=Normal(0, 0.01)), - name='wh.' + name)) + weight_attr=ParamAttr(initializer=Normal(0, 0.01)))) else: head_conv.add_sublayer( name,