diff --git a/configs/ppyolo/README_cn.md b/configs/ppyolo/README_cn.md index 4a17db7a20bf3b0d27dbc9f41cda282fadae6fcc..2718648d19d2e7b178d442f1fc9be873440fcb71 100644 --- a/configs/ppyolo/README_cn.md +++ b/configs/ppyolo/README_cn.md @@ -55,7 +55,7 @@ PP-YOLO从如下方面优化和提升YOLOv3模型的精度和速度： **注意:** - PP-YOLO模型使用COCO数据集中train2017作为训练集，使用val2017和test-dev2017作为测试集，Box APtest为`mAP(IoU=0.5:0.95)`评估结果。 -- PP-YOLO模型训练过程中使用8 GPUs，每GPU batch size为24进行训练，如训练GPU数和batch size不使用上述配置，须参考[FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/FAQ.md)调整学习率和迭代次数。 +- PP-YOLO模型训练过程中使用8 GPUs，每GPU batch size为24进行训练，如训练GPU数和batch size不使用上述配置，须参考[FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ.md)调整学习率和迭代次数。 - PP-YOLO模型推理速度测试采用单卡V100，batch size=1进行测试，使用CUDA 10.2, CUDNN 7.5.1，TensorRT推理速度测试使用TensorRT 5.1.2.2。 - PP-YOLO模型FP32的推理速度测试数据为使用`tools/export_model.py`脚本导出模型后，使用`deploy/python/infer.py`脚本中的`--run_benchnark`参数使用Paddle预测库进行推理速度benchmark测试结果, 且测试的均为不包含数据预处理和模型输出后处理(NMS)的数据(与[YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet)测试方法一致)。 - TensorRT FP16的速度测试相比于FP32去除了`yolo_box`(bbox解码)部分耗时，即不包含数据预处理，bbox解码和NMS(与[YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet)测试方法一致)。 @@ -68,7 +68,7 @@ PP-YOLO从如下方面优化和提升YOLOv3模型的精度和速度： | PP-YOLO_MobileNetV3_small | 4 | 32 | 16MB | 320 | 17.2 | 33.8 | 21.5 | [下载链接](https://paddledet.bj.bcebos.com/models/ppyolo_mbv3_small_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_mbv3_small_coco.yml) | - PP-YOLO_MobileNetV3 模型使用COCO数据集中train2017作为训练集，使用val2017作为测试集，Box APval为`mAP(IoU=0.5:0.95)`评估结果, Box AP50val为`mAP(IoU=0.5)`评估结果。 -- PP-YOLO_MobileNetV3 模型训练过程中使用4GPU，每GPU batch size为32进行训练，如训练GPU数和batch size不使用上述配置，须参考[FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/FAQ.md)调整学习率和迭代次数。 +- PP-YOLO_MobileNetV3 模型训练过程中使用4GPU，每GPU batch size为32进行训练，如训练GPU数和batch size不使用上述配置，须参考[FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ.md)调整学习率和迭代次数。 - PP-YOLO_MobileNetV3 模型推理速度测试环境配置为麒麟990芯片单线程。 ### PP-YOLO tiny模型 diff --git a/static/configs/acfpn/README.md b/static/configs/acfpn/README.md index 81a3250acc645539978f1fbefbe9d85effb58f85..802d61478150af1b22e1e94fa53b30f2ed905cbc 100644 --- a/static/configs/acfpn/README.md +++ b/static/configs/acfpn/README.md @@ -13,4 +13,4 @@ Cao J, Chen Q, Guo J, et al. Attention-guided Context Feature Pyramid Network fo | Backbone | Type | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs | | :---------------------- | :-------------: | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: | -| ResNet50-vd-ACFPN | Faster | 2 | 1x | 23.432 | 39.6 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_acfpn_1x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/acfpn/faster_rcnn_r50_vd_acfpn_1x.yml) | +| ResNet50-vd-ACFPN | Faster | 2 | 1x | 23.432 | 39.6 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_acfpn_1x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/acfpn/faster_rcnn_r50_vd_acfpn_1x.yml) | diff --git a/static/configs/anchor_free/README.md b/static/configs/anchor_free/README.md index a1f6994a14c4c53d1fa4fa5caffb382565d794e0..15b1717be3f156ca92b490fe038dd979a95a502e 100644 --- a/static/configs/anchor_free/README.md +++ b/static/configs/anchor_free/README.md @@ -26,14 +26,14 @@ | 网络结构 | 骨干网络 | 图片个数/GPU | 预训练模型 | mAP | FPS | 模型下载 | 配置文件 | |:------------:|:--------:|:----:|:-------:|:-------:|:---------:|:----------:|:----------:| -| CornerNet-Squeeze | Hourglass104 | 14 | 无 | 34.5 | 35.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cornernet_squeeze_hg104.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/anchor_free/cornernet_squeeze_hg104.yml) | -| CornerNet-Squeeze | ResNet50-vd | 14 | [faster\_rcnn\_r50\_vd\_fpn\_2x](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_2x.tar) | 32.7 | 47.01 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cornernet_squeeze_r50_vd_fpn.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/anchor_free/cornernet_squeeze_r50_vd_fpn.yml) | -| CornerNet-Squeeze-dcn | ResNet50-vd | 14 | [faster\_rcnn\_dcn\_r50\_vd\_fpn\_2x](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_vd_fpn_2x.tar) | 34.9 | 40.43 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cornernet_squeeze_dcn_r50_vd_fpn.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/anchor_free/cornernet_squeeze_dcn_r50_vd_fpn.yml) | -| CornerNet-Squeeze-dcn-mixup-cosine* | ResNet50-vd | 14 | [faster\_rcnn\_dcn\_r50\_vd\_fpn\_2x](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_vd_fpn_2x.tar) | 38.2 | 39.70 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cornernet_squeeze_dcn_r50_vd_fpn_mixup_cosine.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/anchor_free/cornernet_squeeze_dcn_r50_vd_fpn_mixup_cosine.yml) | -| FCOS | ResNet50 | 2 | [ResNet50\_cos\_pretrained](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar) | 39.8 | 18.85 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/fcos_r50_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/anchor_free/fcos_r50_fpn_1x.yml) | -| FCOS+multiscale_train | ResNet50 | 2 | [ResNet50\_cos\_pretrained](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar) | 42.0 | 19.05 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/fcos_r50_fpn_multiscale_2x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/anchor_free/fcos_r50_fpn_multiscale_2x.yml) | -| FCOS+DCN | ResNet50 | 2 | [ResNet50\_cos\_pretrained](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar) | 44.4 | 13.66 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/fcos_dcn_r50_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/anchor_free/fcos_dcn_r50_fpn_1x.yml) | -| TTFNet | DarkNet53 | 12 | [DarkNet53_pretrained](https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_pretrained.tar) | 32.9 | 85.92 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ttfnet_darknet.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/anchor_free/ttfnet_darknet.yml) | +| CornerNet-Squeeze | Hourglass104 | 14 | 无 | 34.5 | 35.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cornernet_squeeze_hg104.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/anchor_free/cornernet_squeeze_hg104.yml) | +| CornerNet-Squeeze | ResNet50-vd | 14 | [faster\_rcnn\_r50\_vd\_fpn\_2x](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_2x.tar) | 32.7 | 47.01 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cornernet_squeeze_r50_vd_fpn.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/anchor_free/cornernet_squeeze_r50_vd_fpn.yml) | +| CornerNet-Squeeze-dcn | ResNet50-vd | 14 | [faster\_rcnn\_dcn\_r50\_vd\_fpn\_2x](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_vd_fpn_2x.tar) | 34.9 | 40.43 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cornernet_squeeze_dcn_r50_vd_fpn.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/anchor_free/cornernet_squeeze_dcn_r50_vd_fpn.yml) | +| CornerNet-Squeeze-dcn-mixup-cosine* | ResNet50-vd | 14 | [faster\_rcnn\_dcn\_r50\_vd\_fpn\_2x](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_vd_fpn_2x.tar) | 38.2 | 39.70 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cornernet_squeeze_dcn_r50_vd_fpn_mixup_cosine.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/anchor_free/cornernet_squeeze_dcn_r50_vd_fpn_mixup_cosine.yml) | +| FCOS | ResNet50 | 2 | [ResNet50\_cos\_pretrained](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar) | 39.8 | 18.85 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/fcos_r50_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/anchor_free/fcos_r50_fpn_1x.yml) | +| FCOS+multiscale_train | ResNet50 | 2 | [ResNet50\_cos\_pretrained](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar) | 42.0 | 19.05 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/fcos_r50_fpn_multiscale_2x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/anchor_free/fcos_r50_fpn_multiscale_2x.yml) | +| FCOS+DCN | ResNet50 | 2 | [ResNet50\_cos\_pretrained](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar) | 44.4 | 13.66 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/fcos_dcn_r50_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/anchor_free/fcos_dcn_r50_fpn_1x.yml) | +| TTFNet | DarkNet53 | 12 | [DarkNet53_pretrained](https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_pretrained.tar) | 32.9 | 85.92 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ttfnet_darknet.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/anchor_free/ttfnet_darknet.yml) | **注意:** diff --git a/static/configs/autoaugment/README.md b/static/configs/autoaugment/README.md index 7512b057184530347b036df66412b9735279799b..0f960db95325b7b27a7b2b5535f94d6325f19373 100644 --- a/static/configs/autoaugment/README.md +++ b/static/configs/autoaugment/README.md @@ -19,5 +19,5 @@ | Backbone | Type | AutoAug policy | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs | | :---------------------- | :-------------:| :-------: | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: | -| ResNet50-vd-FPN | Faster | v1 | 2 | 3x | 22.800 | 39.9 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_aa_3x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/autoaugment/faster_rcnn_r50_vd_fpn_aa_3x.yml) | -| ResNet101-vd-FPN | Faster | v1 | 2 | 3x | 17.652 | 42.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_vd_fpn_aa_3x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/autoaugment/faster_rcnn_r101_vd_fpn_aa_3x.yml) | +| ResNet50-vd-FPN | Faster | v1 | 2 | 3x | 22.800 | 39.9 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_aa_3x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/autoaugment/faster_rcnn_r50_vd_fpn_aa_3x.yml) | +| ResNet101-vd-FPN | Faster | v1 | 2 | 3x | 17.652 | 42.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_vd_fpn_aa_3x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/autoaugment/faster_rcnn_r101_vd_fpn_aa_3x.yml) | diff --git a/static/configs/gcnet/README.md b/static/configs/gcnet/README.md index b6df001a9c5644064627cf17c2d55feceb847426..5c25d34676f9bd6bcc66a8d90a4197f69c744d9c 100644 --- a/static/configs/gcnet/README.md +++ b/static/configs/gcnet/README.md @@ -30,5 +30,5 @@ | Backbone | Type | Context| Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs | | :---------------------- | :-------------: | :-------------: | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: | -| ResNet50-vd-FPN | Mask | GC(c3-c5, r16, add) | 2 | 2x | 15.31 | 41.4 | 36.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_gcb_add_r16_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/gcnet/mask_rcnn_r50_vd_fpn_gcb_add_r16_2x.yml) | -| ResNet50-vd-FPN | Mask | GC(c3-c5, r16, mul) | 2 | 2x | 15.35 | 40.7 | 36.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_gcb_mul_r16_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/gcnet/mask_rcnn_r50_vd_fpn_gcb_mul_r16_2x.yml) | +| ResNet50-vd-FPN | Mask | GC(c3-c5, r16, add) | 2 | 2x | 15.31 | 41.4 | 36.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_gcb_add_r16_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/gcnet/mask_rcnn_r50_vd_fpn_gcb_add_r16_2x.yml) | +| ResNet50-vd-FPN | Mask | GC(c3-c5, r16, mul) | 2 | 2x | 15.35 | 40.7 | 36.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_gcb_mul_r16_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/gcnet/mask_rcnn_r50_vd_fpn_gcb_mul_r16_2x.yml) | diff --git a/static/configs/gcnet/README_cn.md b/static/configs/gcnet/README_cn.md index 795e62ef61b5427f31dd9f0baf81c3e383711d24..579bfe0ca9fca376e7645dd0a9b59b15d7e817a0 100644 --- a/static/configs/gcnet/README_cn.md +++ b/static/configs/gcnet/README_cn.md @@ -42,8 +42,8 @@ SNL模块可以抽象为上下文建模、特征转换和特征聚合三个部 | 骨架网络 | 网络类型 | Context设置 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP | 下载 | 配置文件 | | :---------------------- | :-------------: | :-------------: | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: | -| ResNet50-vd-FPN | Mask | GC(c3-c5, r16, add) | 2 | 2x | 15.31 | 41.4 | 36.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_gcb_add_r16_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/gcnet/mask_rcnn_r50_vd_fpn_gcb_add_r16_2x.yml) | -| ResNet50-vd-FPN | Mask | GC(c3-c5, r16, mul) | 2 | 2x | 15.35 | 40.7 | 36.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_gcb_mul_r16_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/gcnet/mask_rcnn_r50_vd_fpn_gcb_mul_r16_2x.yml) | +| ResNet50-vd-FPN | Mask | GC(c3-c5, r16, add) | 2 | 2x | 15.31 | 41.4 | 36.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_gcb_add_r16_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/gcnet/mask_rcnn_r50_vd_fpn_gcb_add_r16_2x.yml) | +| ResNet50-vd-FPN | Mask | GC(c3-c5, r16, mul) | 2 | 2x | 15.35 | 40.7 | 36.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_gcb_mul_r16_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/gcnet/mask_rcnn_r50_vd_fpn_gcb_mul_r16_2x.yml) | ## 引用 diff --git a/static/configs/gridmask/README.md b/static/configs/gridmask/README.md index 6b8cb153e88a614736a3cfa43aab7641af23bb8e..3e39b8a7120b6522fe151ee3b378d584d5556d7d 100644 --- a/static/configs/gridmask/README.md +++ b/static/configs/gridmask/README.md @@ -19,4 +19,4 @@ | Backbone | Type | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs | | :---------------------- | :-------------: | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: | -| ResNet50-vd-FPN | Faster | 2 | 4x | 21.847 | 39.1% | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_gridmask_4x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/gridmask/faster_rcnn_r50_vd_fpn_gridmask_4x.yml) | +| ResNet50-vd-FPN | Faster | 2 | 4x | 21.847 | 39.1% | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_gridmask_4x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/gridmask/faster_rcnn_r50_vd_fpn_gridmask_4x.yml) | diff --git a/static/configs/hrnet/README.md b/static/configs/hrnet/README.md index e858b9afe970e4e3ced86efde2b02676b16f48cf..c18cb6d7d27ba1ac30d9fcb48803233dc6aa16e1 100644 --- a/static/configs/hrnet/README.md +++ b/static/configs/hrnet/README.md @@ -30,5 +30,5 @@ | Backbone | Type | deformable Conv | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs | | :---------------------- | :------------- | :---: | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: | -| HRNetV2p_W18 | Faster | False | 2 | 1x | 17.509 | 36.0 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_hrnetv2p_w18_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/hrnet/faster_rcnn_hrnetv2p_w18_1x.yml) | -| HRNetV2p_W18 | Faster | False | 2 | 2x | 17.509 | 38.0 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_hrnetv2p_w18_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/hrnet/faster_rcnn_hrnetv2p_w18_2x.yml) | +| HRNetV2p_W18 | Faster | False | 2 | 1x | 17.509 | 36.0 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_hrnetv2p_w18_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/hrnet/faster_rcnn_hrnetv2p_w18_1x.yml) | +| HRNetV2p_W18 | Faster | False | 2 | 2x | 17.509 | 38.0 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_hrnetv2p_w18_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/hrnet/faster_rcnn_hrnetv2p_w18_2x.yml) | diff --git a/static/configs/iou_loss/README.md b/static/configs/iou_loss/README.md index 30aa5bd265a09190f886a1ba3e81c054b9ec6b27..2082ece3892341f05954a83d51e6859ebeb6e4e5 100644 --- a/static/configs/iou_loss/README.md +++ b/static/configs/iou_loss/README.md @@ -43,6 +43,6 @@ | Backbone | Type | Loss Type | Loss Weight | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs | | :---------------------- | :------------- | :---: | :---: | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :---: | -| ResNet50-vd-FPN | Faster | GIOU | 10 | 2 | 1x | 22.94 | 39.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_giou_loss_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/iou_loss/faster_rcnn_r50_vd_fpn_giou_loss_1x.yml) | -| ResNet50-vd-FPN | Faster | DIOU | 12 | 2 | 1x | 22.94 | 39.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_diou_loss_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/iou_loss/faster_rcnn_r50_vd_fpn_diou_loss_1x.yml) | -| ResNet50-vd-FPN | Faster | CIOU | 12 | 2 | 1x | 22.95 | 39.6 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_ciou_loss_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/iou_loss/faster_rcnn_r50_vd_fpn_ciou_loss_1x.yml) | +| ResNet50-vd-FPN | Faster | GIOU | 10 | 2 | 1x | 22.94 | 39.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_giou_loss_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/iou_loss/faster_rcnn_r50_vd_fpn_giou_loss_1x.yml) | +| ResNet50-vd-FPN | Faster | DIOU | 12 | 2 | 1x | 22.94 | 39.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_diou_loss_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/iou_loss/faster_rcnn_r50_vd_fpn_diou_loss_1x.yml) | +| ResNet50-vd-FPN | Faster | CIOU | 12 | 2 | 1x | 22.95 | 39.6 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_ciou_loss_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/iou_loss/faster_rcnn_r50_vd_fpn_ciou_loss_1x.yml) | diff --git a/static/configs/iou_loss/README_cn.md b/static/configs/iou_loss/README_cn.md index 0710944c53281f2c1c7c9374eb246364112abf1e..3288e587dda9e787c7de265c5d94c2d39f764264 100644 --- a/static/configs/iou_loss/README_cn.md +++ b/static/configs/iou_loss/README_cn.md @@ -83,9 +83,9 @@ CIOU loss使得在边框回归时，与目标框有重叠甚至包含时能够 | 骨架网络 | 网络类型 | Loss类型 | Loss权重 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP | 下载 | 配置文件 | | :---------------------- | :------------- | :---: | :---: | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :---: | -| ResNet50-vd-FPN | Faster | GIOU | 10 | 2 | 1x | 22.94 | 39.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_giou_loss_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/iou_loss/faster_rcnn_r50_vd_fpn_giou_loss_1x.yml) | -| ResNet50-vd-FPN | Faster | DIOU | 12 | 2 | 1x | 22.94 | 39.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_diou_loss_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/iou_loss/faster_rcnn_r50_vd_fpn_diou_loss_1x.yml) | -| ResNet50-vd-FPN | Faster | CIOU | 12 | 2 | 1x | 22.95 | 39.6 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_ciou_loss_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/iou_loss/faster_rcnn_r50_vd_fpn_ciou_loss_1x.yml) | +| ResNet50-vd-FPN | Faster | GIOU | 10 | 2 | 1x | 22.94 | 39.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_giou_loss_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/iou_loss/faster_rcnn_r50_vd_fpn_giou_loss_1x.yml) | +| ResNet50-vd-FPN | Faster | DIOU | 12 | 2 | 1x | 22.94 | 39.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_diou_loss_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/iou_loss/faster_rcnn_r50_vd_fpn_diou_loss_1x.yml) | +| ResNet50-vd-FPN | Faster | CIOU | 12 | 2 | 1x | 22.95 | 39.6 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_ciou_loss_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/iou_loss/faster_rcnn_r50_vd_fpn_ciou_loss_1x.yml) | diff --git a/static/configs/libra_rcnn/README.md b/static/configs/libra_rcnn/README.md index b91d9a9f182647505d319635fc37b4925ec8fc66..3451390d34f969444503f4c5ebc90993be85b568 100644 --- a/static/configs/libra_rcnn/README.md +++ b/static/configs/libra_rcnn/README.md @@ -19,5 +19,5 @@ | Backbone | Type | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs | | :---------------------- | :-------------: | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: | -| ResNet50-vd-BFP | Faster | 2 | 1x | 18.247 | 40.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/libra_rcnn_r50_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/libra_rcnn/libra_rcnn_r50_vd_fpn_1x.yml) | -| ResNet101-vd-BFP | Faster | 2 | 1x | 14.865 | 42.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/libra_rcnn_r101_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/libra_rcnn/libra_rcnn_r101_vd_fpn_1x.yml) | +| ResNet50-vd-BFP | Faster | 2 | 1x | 18.247 | 40.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/libra_rcnn_r50_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/libra_rcnn/libra_rcnn_r50_vd_fpn_1x.yml) | +| ResNet101-vd-BFP | Faster | 2 | 1x | 14.865 | 42.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/libra_rcnn_r101_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/libra_rcnn/libra_rcnn_r101_vd_fpn_1x.yml) | diff --git a/static/configs/libra_rcnn/README_cn.md b/static/configs/libra_rcnn/README_cn.md index 134c1c390eaec3869b4cce7e46e4973ca6e8440c..7d71aae1bb977aac21dc28520633995d006442a8 100644 --- a/static/configs/libra_rcnn/README_cn.md +++ b/static/configs/libra_rcnn/README_cn.md @@ -60,8 +60,8 @@ Faster RCNN中生成许多候选框之后，使用随机的方法挑选正负样 | 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP | 下载 | 配置文件 | | :---------------------- | :-------------: | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: | -| ResNet50-vd-BFP | Faster | 2 | 1x | 18.247 | 40.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/libra_rcnn_r50_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/libra_rcnn/libra_rcnn_r50_vd_fpn_1x.yml) | -| ResNet101-vd-BFP | Faster | 2 | 1x | 14.865 | 42.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/libra_rcnn_r101_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/libra_rcnn/libra_rcnn_r101_vd_fpn_1x.yml) | +| ResNet50-vd-BFP | Faster | 2 | 1x | 18.247 | 40.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/libra_rcnn_r50_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/libra_rcnn/libra_rcnn_r50_vd_fpn_1x.yml) | +| ResNet101-vd-BFP | Faster | 2 | 1x | 14.865 | 42.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/libra_rcnn_r101_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/libra_rcnn/libra_rcnn_r101_vd_fpn_1x.yml) | ## 引用 diff --git a/static/configs/ppyolo/README.md b/static/configs/ppyolo/README.md index 52cc0874cf16aca3fc2dca48d2a17b105f102a66..eb9091287e24abdcf9b9d162733ea4d2b58f77d6 100644 --- a/static/configs/ppyolo/README.md +++ b/static/configs/ppyolo/README.md @@ -101,7 +101,7 @@ 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 diff --git a/static/configs/random_erasing/README.md b/static/configs/random_erasing/README.md index c7e4622b5c59c19a6ee41c4ceb49a36cce442326..2b101348e086a8115f5fe4e6a0a10a008e6228b3 100644 --- a/static/configs/random_erasing/README.md +++ b/static/configs/random_erasing/README.md @@ -18,4 +18,4 @@ | Backbone | Type | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs | | :---------------------- | :-------------: | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: | -| ResNet50-vd-FPN | Faster | 2 | 4x | 21.847 | 39.0% | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_random_erasing_4x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/random_erasing/faster_rcnn_r50_vd_fpn_random_erasing_4x.yml) | +| ResNet50-vd-FPN | Faster | 2 | 4x | 21.847 | 39.0% | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_random_erasing_4x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/random_erasing/faster_rcnn_r50_vd_fpn_random_erasing_4x.yml) | diff --git a/static/configs/rcnn_enhance/README.md b/static/configs/rcnn_enhance/README.md index 4b75d8327be33cbf62719d96ac210b0b2c0d98e8..7fc757fc159e67ed1266c04c067467b2d5da111b 100644 --- a/static/configs/rcnn_enhance/README.md +++ b/static/configs/rcnn_enhance/README.md @@ -32,9 +32,9 @@ | 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP | 下载 | 配置文件 | | :---------------------- | :-------------: | :-------: | :-----: | :------------: | :----: | :-----: | :-------------: | :-----: | -| ResNet50-vd-FPN-Dcnv2 | Faster | 2 | 3x | 61.425 | 41.6 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_vd_fpn_3x_server_side.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/rcnn_enhance/faster_rcnn_dcn_r50_vd_fpn_3x_server_side.yml) | -| ResNet50-vd-FPN-Dcnv2 | Cascade Faster | 2 | 3x | 20.001 | 47.8 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_vd_fpn_3x_server_side.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/rcnn_enhance/cascade_rcnn_dcn_r50_vd_fpn_3x_server_side.yml) | -| ResNet101-vd-FPN-Dcnv2 | Cascade Faster | 2 | 3x | 19.523 | 49.4 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r101_vd_fpn_3x_server_side.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/rcnn_enhance/cascade_rcnn_dcn_r101_vd_fpn_3x_server_side.yml) | +| ResNet50-vd-FPN-Dcnv2 | Faster | 2 | 3x | 61.425 | 41.6 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_vd_fpn_3x_server_side.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/rcnn_enhance/faster_rcnn_dcn_r50_vd_fpn_3x_server_side.yml) | +| ResNet50-vd-FPN-Dcnv2 | Cascade Faster | 2 | 3x | 20.001 | 47.8 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_vd_fpn_3x_server_side.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/rcnn_enhance/cascade_rcnn_dcn_r50_vd_fpn_3x_server_side.yml) | +| ResNet101-vd-FPN-Dcnv2 | Cascade Faster | 2 | 3x | 19.523 | 49.4 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r101_vd_fpn_3x_server_side.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/rcnn_enhance/cascade_rcnn_dcn_r101_vd_fpn_3x_server_side.yml) | **注**：generic文件夹下面的配置文件对应的预训练模型均只支持预测，不支持训练与评估。 diff --git a/static/configs/rcnn_enhance/README_en.md b/static/configs/rcnn_enhance/README_en.md index f70cc9422b627051d315866e48cfe6ca0af7c244..2572376450f55d6851a53da647b7ab27d754953b 100644 --- a/static/configs/rcnn_enhance/README_en.md +++ b/static/configs/rcnn_enhance/README_en.md @@ -36,9 +36,9 @@ And the following figure shows `mAP-Speed` curves for some common detectors. | Backbone | Type | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs | | :---------------------- | :-------------: | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: | -| ResNet50-vd-FPN-Dcnv2 | Faster | 2 | 3x | 61.425 | 41.6 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_vd_fpn_3x_server_side.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/rcnn_enhance/faster_rcnn_dcn_r50_vd_fpn_3x_server_side.yml) | -| ResNet50-vd-FPN-Dcnv2 | Cascade Faster | 2 | 3x | 20.001 | 47.8 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_vd_fpn_3x_server_side.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/rcnn_enhance/cascade_rcnn_dcn_r50_vd_fpn_3x_server_side.yml) | -| ResNet101-vd-FPN-Dcnv2 | Cascade Faster | 2 | 3x | 19.523 | 49.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r101_vd_fpn_3x_server_side.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/rcnn_enhance/cascade_rcnn_dcn_r101_vd_fpn_3x_server_side.yml) | +| ResNet50-vd-FPN-Dcnv2 | Faster | 2 | 3x | 61.425 | 41.6 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_vd_fpn_3x_server_side.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/rcnn_enhance/faster_rcnn_dcn_r50_vd_fpn_3x_server_side.yml) | +| ResNet50-vd-FPN-Dcnv2 | Cascade Faster | 2 | 3x | 20.001 | 47.8 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_vd_fpn_3x_server_side.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/rcnn_enhance/cascade_rcnn_dcn_r50_vd_fpn_3x_server_side.yml) | +| ResNet101-vd-FPN-Dcnv2 | Cascade Faster | 2 | 3x | 19.523 | 49.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r101_vd_fpn_3x_server_side.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/rcnn_enhance/cascade_rcnn_dcn_r101_vd_fpn_3x_server_side.yml) | **Attention**: Pretrained models whose congigurations are in the directory `generic` just support inference but do not support training and evaluation as now. diff --git a/static/configs/res2net/README.md b/static/configs/res2net/README.md index 647df40d5c02a0845e467443dd64e9e5b48a90b4..4926264e1395540ec230a02e09892292cde99c8e 100644 --- a/static/configs/res2net/README.md +++ b/static/configs/res2net/README.md @@ -30,7 +30,7 @@ | Backbone | Type | deformable Conv | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs | | :---------------------- | :------------- | :---: | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: | -| Res2Net50-FPN | Faster | False | 2 | 1x | 20.320 | 39.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_res2net50_vb_26w_4s_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/res2net/faster_rcnn_res2net50_vb_26w_4s_fpn_1x.yml) | -| Res2Net50-FPN | Mask | False | 2 | 2x | 16.069 | 40.7 | 36.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_res2net50_vb_26w_4s_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/res2net/faster_rcnn_res2net50_vb_26w_4s_fpn_2x.yml) | -| Res2Net50-vd-FPN | Mask | False | 2 | 2x | 15.816 | 40.9 | 36.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_res2net50_vd_26w_4s_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/res2net/mask_rcnn_res2net50_vd_26w_4s_fpn_2x.yml) | -| Res2Net50-vd-FPN | Mask | True | 2 | 2x | 14.478 | 43.5 | 38.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_res2net50_vd_26w_4s_fpn_dcnv2_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/res2net/mask_rcnn_res2net50_vd_26w_4s_fpn_dcnv2_1x.yml) | +| Res2Net50-FPN | Faster | False | 2 | 1x | 20.320 | 39.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_res2net50_vb_26w_4s_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/res2net/faster_rcnn_res2net50_vb_26w_4s_fpn_1x.yml) | +| Res2Net50-FPN | Mask | False | 2 | 2x | 16.069 | 40.7 | 36.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_res2net50_vb_26w_4s_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/res2net/faster_rcnn_res2net50_vb_26w_4s_fpn_2x.yml) | +| Res2Net50-vd-FPN | Mask | False | 2 | 2x | 15.816 | 40.9 | 36.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_res2net50_vd_26w_4s_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/res2net/mask_rcnn_res2net50_vd_26w_4s_fpn_2x.yml) | +| Res2Net50-vd-FPN | Mask | True | 2 | 2x | 14.478 | 43.5 | 38.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_res2net50_vd_26w_4s_fpn_dcnv2_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/res2net/mask_rcnn_res2net50_vd_26w_4s_fpn_dcnv2_1x.yml) | diff --git a/static/configs/solov2/README.md b/static/configs/solov2/README.md index 60040b4995d8277a9727a38264a8d1e0402aeb77..c7581da229a16b24de831a9861aec327d6f337e4 100644 --- a/static/configs/solov2/README.md +++ b/static/configs/solov2/README.md @@ -25,15 +25,15 @@ SOLOv2 (Segmenting Objects by Locations) is a fast instance segmentation framewo | BlendMask | R50-FPN | True | 3x | 37.8 | 13.5 | V100 | - | - | | SOLOv2 (Paper) | R50-FPN | False | 1x | 34.8 | 18.5 | V100 | - | - | | SOLOv2 (Paper) | X101-DCN-FPN | True | 3x | 42.4 | 5.9 | V100 | - | - | -| SOLOv2 | Mobilenetv3-FPN | True | 3x | 30.0 | 50 | V100 | [model](https://paddlemodels.bj.bcebos.com/object_detection/solov2_mobilenetv3_fpn_448_3x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/solov2/solov2_mobilenetv3_fpn_448_3x.yml) | -| SOLOv2 | R50-FPN | False | 1x | 35.6 | 21.9 | V100 | [model](https://paddlemodels.bj.bcebos.com/object_detection/solov2_r50_fpn_1x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/solov2/solov2_r50_fpn_1x.yml) | -| SOLOv2 | R50-FPN | True | 3x | 37.9 | 21.9 | V100 | [model](https://paddlemodels.bj.bcebos.com/object_detection/solov2_r50_fpn_3x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/solov2/solov2_r50_fpn_3x.yml) | -| SOLOv2 | R101-VD-FPN | True | 3x | 42.6 | 12.1 | V100 | [model](https://paddlemodels.bj.bcebos.com/object_detection/solov2_r101_vd_fpn_3x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/solov2/solov2_r101_vd_fpn_3x.yml) | +| SOLOv2 | Mobilenetv3-FPN | True | 3x | 30.0 | 50 | V100 | [model](https://paddlemodels.bj.bcebos.com/object_detection/solov2_mobilenetv3_fpn_448_3x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/solov2/solov2_mobilenetv3_fpn_448_3x.yml) | +| SOLOv2 | R50-FPN | False | 1x | 35.6 | 21.9 | V100 | [model](https://paddlemodels.bj.bcebos.com/object_detection/solov2_r50_fpn_1x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/solov2/solov2_r50_fpn_1x.yml) | +| SOLOv2 | R50-FPN | True | 3x | 37.9 | 21.9 | V100 | [model](https://paddlemodels.bj.bcebos.com/object_detection/solov2_r50_fpn_3x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/solov2/solov2_r50_fpn_3x.yml) | +| SOLOv2 | R101-VD-FPN | True | 3x | 42.6 | 12.1 | V100 | [model](https://paddlemodels.bj.bcebos.com/object_detection/solov2_r101_vd_fpn_3x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/solov2/solov2_r101_vd_fpn_3x.yml) | ## Enhanced model | Backbone | Input size | Lr schd | V100 FP32(FPS) | Mask APval | Download | Configs | | :---------------------: | :-------------------: | :-----: | :------------: | :-----: | :---------: | :------------------------: | -| Light-R50-VD-DCN-FPN | 512 | 3x | 38.6 | 38.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/solov2_light_r50_vd_fpn_dcn_512_3x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/solov2/solov2_light_r50_vd_fpn_dcn_512_3x.yml) | +| Light-R50-VD-DCN-FPN | 512 | 3x | 38.6 | 38.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/solov2_light_r50_vd_fpn_dcn_512_3x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/solov2/solov2_light_r50_vd_fpn_dcn_512_3x.yml) | **Notes:** diff --git a/static/configs/yolov4/README.md b/static/configs/yolov4/README.md index 9394975af1bd19aca032c9349b327f9b5f8998b0..d99ce88dd1dc2d30688ea7412151868b7a3455e9 100644 --- a/static/configs/yolov4/README.md +++ b/static/configs/yolov4/README.md @@ -41,8 +41,8 @@ python tools/anchor_cluster.py -c ${config} -m ${method} -s ${size} | | GPU个数 | 测试集 | 骨干网络 | 精度 | 模型下载 | 配置文件 | |:------------------------:|:-------:|:------:|:--------------------------:|:------------------------:| :---------:| :-----: | -| YOLO v4 | - |test-dev2019 | CSPDarkNet53 | 43.5 |[下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov4_cspdarknet.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov4/yolov4_cspdarknet.yml) | -| YOLO v4 VOC | 2 | VOC2007 | CSPDarkNet53 | 85.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov4_cspdarknet_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov4/yolov4_cspdarknet_voc.yml) | +| YOLO v4 | - |test-dev2019 | CSPDarkNet53 | 43.5 |[下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov4_cspdarknet.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov4/yolov4_cspdarknet.yml) | +| YOLO v4 VOC | 2 | VOC2007 | CSPDarkNet53 | 85.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov4_cspdarknet_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov4/yolov4_cspdarknet_voc.yml) | **注意:** diff --git a/static/deploy/README.md b/static/deploy/README.md index 2f8818816bb0f70302ac4305c449669ff3c04cc5..39595a7ff4cdbd99a4c1b6043212b40a542f23cc 100644 --- a/static/deploy/README.md +++ b/static/deploy/README.md @@ -8,7 +8,7 @@ ## 模型导出 训练得到一个满足要求的模型后，如果想要将该模型接入到C++服务器端预测库或移动端预测库，需要通过`tools/export_model.py`导出该模型。 -- [导出教程](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/advanced_tutorials/deploy/EXPORT_MODEL.md) +- [导出教程](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/docs/advanced_tutorials/deploy/EXPORT_MODEL.md) 模型导出后, 目录结构如下(以`yolov3_darknet`为例): ``` @@ -21,8 +21,8 @@ yolov3_darknet # 模型目录 预测时，该目录所在的路径会作为程序的输入参数。 ## 预测部署 -- [1. Python预测(支持 Linux 和 Windows)](https://github.com/PaddlePaddle/PaddleDetection/blob/master/deploy/python) -- [2. C++预测(支持 Linux 和 Windows)](https://github.com/PaddlePaddle/PaddleDetection/blob/master/deploy/cpp) +- [1. Python预测(支持 Linux 和 Windows)](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/deploy/python) +- [2. C++预测(支持 Linux 和 Windows)](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/deploy/cpp) - [3. 在线服务化部署](./serving/README.md) - [4. 移动端部署](https://github.com/PaddlePaddle/Paddle-Lite-Demo) - [5. Jetson设备部署](./cpp/docs/Jetson_build.md) diff --git a/static/deploy/cpp/README.md b/static/deploy/cpp/README.md index 2792afefc216d01fee6fcf18b4de1e9bf5fc7267..248062898e5d452b85f9634459ff32110c36750a 100644 --- a/static/deploy/cpp/README.md +++ b/static/deploy/cpp/README.md @@ -52,7 +52,7 @@ deploy/cpp ## 3.编译部署 ### 3.1 导出模型 -请确认您已经基于`PaddleDetection`的[export_model.py](https://github.com/PaddlePaddle/PaddleDetection/blob/master/tools/export_model.py)导出您的模型，并妥善保存到合适的位置。导出模型细节请参考 [导出模型教程](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/advanced_tutorials/deploy/EXPORT_MODEL.md)。 +请确认您已经基于`PaddleDetection`的[export_model.py](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/tools/export_model.py)导出您的模型，并妥善保存到合适的位置。导出模型细节请参考 [导出模型教程](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/docs/advanced_tutorials/deploy/EXPORT_MODEL.md)。 模型导出后, 目录结构如下(以`yolov3_darknet`为例): ``` diff --git a/static/deploy/python/README.md b/static/deploy/python/README.md index 928910f6bcb9e7fe445b6592fb733e5fc8cd4b70..2e8d761bc58db7d29f499c6888fd2396633f3343 100644 --- a/static/deploy/python/README.md +++ b/static/deploy/python/README.md @@ -3,7 +3,7 @@ Python预测可以使用`tools/infer.py`，此种方式依赖PaddleDetection源码；也可以使用本篇教程预测方式，先将模型导出，使用一个独立的文件进行预测。 -本篇教程使用AnalysisPredictor对[导出模型](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/advanced_tutorials/deploy/EXPORT_MODEL.md)进行高性能预测。 +本篇教程使用AnalysisPredictor对[导出模型](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/docs/advanced_tutorials/deploy/EXPORT_MODEL.md)进行高性能预测。 在PaddlePaddle中预测引擎和训练引擎底层有着不同的优化方法, 下面列出了两种不同的预测方式。Executor同时支持训练和预测，AnalysisPredictor则专门针对推理进行了优化，是基于[C++预测库](https://www.paddlepaddle.org.cn/documentation/docs/zh/advanced_guide/inference_deployment/inference/native_infer.html)的Python接口，该引擎可以对模型进行多项图优化，减少不必要的内存拷贝。如果用户在部署已训练模型的过程中对性能有较高的要求，我们提供了独立于PaddleDetection的预测脚本，方便用户直接集成部署。 @@ -18,7 +18,7 @@ Python预测可以使用`tools/infer.py`，此种方式依赖PaddleDetection源 ## 1. 导出预测模型 -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/static/docs/advanced_tutorials/deploy/EXPORT_MODEL.md) 导出后目录下，包括`__model__`，`__params__`和`infer_cfg.yml`三个文件。 diff --git a/static/deploy/serving/README.md b/static/deploy/serving/README.md index 48fc2f03d687328aa1f8d26116ca8165ab202e98..c61e673b316a67c9a9fd205cf800e9adbd2c7ebd 100644 --- a/static/deploy/serving/README.md +++ b/static/deploy/serving/README.md @@ -22,7 +22,7 @@ pip install paddle-serving-server-gpu -i https://mirror.baidu.com/pypi/simple ``` ## 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/static/docs/advanced_tutorials/deploy/EXPORT_MODEL.md) ``` python tools/export_serving_model.py -c configs/yolov3_mobilenet_v1_roadsign.yml -o use_gpu=true weights=https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_roadsign.pdparams --output_dir=./inference_model diff --git a/static/docs/MODEL_ZOO.md b/static/docs/MODEL_ZOO.md index 6a1ed97af1af4eb6d2279a378c6554051227ab36..6ccc6cae56e5e904391e290c11e8cd6a6a5e0a78 100644 --- a/static/docs/MODEL_ZOO.md +++ b/static/docs/MODEL_ZOO.md @@ -36,96 +36,96 @@ The backbone models pretrained on ImageNet are available. All backbone models ar | Backbone | Type | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs | | :---------------------- | :------------- | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :----: | -| ResNet50 | Faster | 1 | 1x | 12.747 | 35.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r50_1x.yml) | -| ResNet50 | Faster | 1 | 2x | 12.686 | 37.1 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r50_2x.yml) | -| ResNet50 | Mask | 1 | 1x | 11.615 | 36.5 | 32.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_r50_1x.yml) | -| ResNet50 | Mask | 1 | 2x | 11.494 | 38.2 | 33.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_r50_2x.yml) | -| ResNet50-vd | Faster | 1 | 1x | 12.575 | 36.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r50_vd_1x.yml) | -| ResNet34-FPN | Faster | 2 | 1x | - | 36.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r34_fpn_1x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r34_fpn_1x.yml) | -| ResNet34-vd-FPN | Faster | 2 | 1x | - | 37.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r34_vd_fpn_1x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r34_vd_fpn_1x.yml) | -| ResNet50-FPN | Faster | 2 | 1x | 22.273 | 37.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r50_fpn_1x.yml) | -| ResNet50-FPN | Faster | 2 | 2x | 22.297 | 37.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r50_fpn_2x.yml) | -| ResNet50-FPN | Mask | 1 | 1x | 15.184 | 37.9 | 34.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_r50_fpn_1x.yml) | -| ResNet50-FPN | Mask | 1 | 2x | 15.881 | 38.7 | 34.7 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_r50_fpn_2x.yml) | -| ResNet50-FPN | Cascade Faster | 2 | 1x | 17.507 | 40.9 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/cascade_rcnn_r50_fpn_1x.yml) | -| ResNet50-FPN | Cascade Mask | 1 | 1x | 12.43 | 41.3 | 35.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_mask_rcnn_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/cascade_mask_rcnn_r50_fpn_1x.yml) | -| ResNet50-vd-FPN | Faster | 2 | 2x | 21.847 | 38.9 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r50_vd_fpn_2x.yml) | -| ResNet50-vd-FPN | Mask | 1 | 2x | 15.825 | 39.8 | 35.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_r50_vd_fpn_2x.yml) | -| CBResNet50-vd-FPN | Faster | 2 | 1x | - | 39.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_cbr50_vd_dual_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_cbr50_vd_dual_fpn_1x.yml) | -| ResNet101 | Faster | 1 | 1x | 9.316 | 38.3 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r101_1x.yml) | -| ResNet101-FPN | Faster | 1 | 1x | 17.297 | 38.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r101_fpn_1x.yml) | -| ResNet101-FPN | Faster | 1 | 2x | 17.246 | 39.1 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r101_fpn_2x.yml) | -| ResNet101-FPN | Mask | 1 | 1x | 12.983 | 39.5 | 35.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r101_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_r101_fpn_1x.yml) | -| ResNet101-vd-FPN | Faster | 1 | 1x | 17.011 | 40.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r101_vd_fpn_1x.yml) | -| ResNet101-vd-FPN | Faster | 1 | 2x | 16.934 | 40.8 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_vd_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r101_vd_fpn_2x.yml) | -| ResNet101-vd-FPN | Mask | 1 | 1x | 13.105 | 41.4 | 36.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r101_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_r101_vd_fpn_1x.yml) | -| CBResNet101-vd-FPN | Faster | 2 | 1x | - | 42.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_cbr101_vd_dual_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_cbr101_vd_dual_fpn_1x.yml) | -| ResNeXt101-vd-64x4d-FPN | Faster | 1 | 1x | 8.815 | 42.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_x101_vd_64x4d_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml) | -| ResNeXt101-vd-64x4d-FPN | Faster | 1 | 2x | 8.809 | 41.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_x101_vd_64x4d_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_x101_vd_64x4d_fpn_2x.yml) | -| ResNeXt101-vd-64x4d-FPN | Mask | 1 | 1x | 7.689 | 42.9 | 37.9 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_x101_vd_64x4d_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_x101_vd_64x4d_fpn_1x.yml) | -| ResNeXt101-vd-64x4d-FPN | Mask | 1 | 2x | 7.859 | 42.6 | 37.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_x101_vd_64x4d_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_x101_vd_64x4d_fpn_2x.yml) | -| SENet154-vd-FPN | Faster | 1 | 1.44x | 3.408 | 42.9 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_se154_vd_fpn_s1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_se154_vd_fpn_s1x.yml) | -| SENet154-vd-FPN | Mask | 1 | 1.44x | 3.233 | 44.0 | 38.7 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_se154_vd_fpn_s1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_se154_vd_fpn_s1x.yml) | -| ResNet101-vd-FPN | CascadeClsAware Faster | 2 | 1x | - | 44.7(softnms) | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.yml) | -| ResNet101-vd-FPN | CascadeClsAware Faster | 2 | 1x | - | 46.5(multi-scale test) | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.yml) | +| ResNet50 | Faster | 1 | 1x | 12.747 | 35.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r50_1x.yml) | +| ResNet50 | Faster | 1 | 2x | 12.686 | 37.1 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r50_2x.yml) | +| ResNet50 | Mask | 1 | 1x | 11.615 | 36.5 | 32.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_r50_1x.yml) | +| ResNet50 | Mask | 1 | 2x | 11.494 | 38.2 | 33.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_r50_2x.yml) | +| ResNet50-vd | Faster | 1 | 1x | 12.575 | 36.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r50_vd_1x.yml) | +| ResNet34-FPN | Faster | 2 | 1x | - | 36.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r34_fpn_1x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r34_fpn_1x.yml) | +| ResNet34-vd-FPN | Faster | 2 | 1x | - | 37.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r34_vd_fpn_1x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r34_vd_fpn_1x.yml) | +| ResNet50-FPN | Faster | 2 | 1x | 22.273 | 37.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r50_fpn_1x.yml) | +| ResNet50-FPN | Faster | 2 | 2x | 22.297 | 37.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r50_fpn_2x.yml) | +| ResNet50-FPN | Mask | 1 | 1x | 15.184 | 37.9 | 34.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_r50_fpn_1x.yml) | +| ResNet50-FPN | Mask | 1 | 2x | 15.881 | 38.7 | 34.7 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_r50_fpn_2x.yml) | +| ResNet50-FPN | Cascade Faster | 2 | 1x | 17.507 | 40.9 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/cascade_rcnn_r50_fpn_1x.yml) | +| ResNet50-FPN | Cascade Mask | 1 | 1x | 12.43 | 41.3 | 35.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_mask_rcnn_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/cascade_mask_rcnn_r50_fpn_1x.yml) | +| ResNet50-vd-FPN | Faster | 2 | 2x | 21.847 | 38.9 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r50_vd_fpn_2x.yml) | +| ResNet50-vd-FPN | Mask | 1 | 2x | 15.825 | 39.8 | 35.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_r50_vd_fpn_2x.yml) | +| CBResNet50-vd-FPN | Faster | 2 | 1x | - | 39.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_cbr50_vd_dual_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_cbr50_vd_dual_fpn_1x.yml) | +| ResNet101 | Faster | 1 | 1x | 9.316 | 38.3 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r101_1x.yml) | +| ResNet101-FPN | Faster | 1 | 1x | 17.297 | 38.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r101_fpn_1x.yml) | +| ResNet101-FPN | Faster | 1 | 2x | 17.246 | 39.1 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r101_fpn_2x.yml) | +| ResNet101-FPN | Mask | 1 | 1x | 12.983 | 39.5 | 35.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r101_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_r101_fpn_1x.yml) | +| ResNet101-vd-FPN | Faster | 1 | 1x | 17.011 | 40.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r101_vd_fpn_1x.yml) | +| ResNet101-vd-FPN | Faster | 1 | 2x | 16.934 | 40.8 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_vd_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r101_vd_fpn_2x.yml) | +| ResNet101-vd-FPN | Mask | 1 | 1x | 13.105 | 41.4 | 36.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r101_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_r101_vd_fpn_1x.yml) | +| CBResNet101-vd-FPN | Faster | 2 | 1x | - | 42.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_cbr101_vd_dual_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_cbr101_vd_dual_fpn_1x.yml) | +| ResNeXt101-vd-64x4d-FPN | Faster | 1 | 1x | 8.815 | 42.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_x101_vd_64x4d_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml) | +| ResNeXt101-vd-64x4d-FPN | Faster | 1 | 2x | 8.809 | 41.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_x101_vd_64x4d_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_x101_vd_64x4d_fpn_2x.yml) | +| ResNeXt101-vd-64x4d-FPN | Mask | 1 | 1x | 7.689 | 42.9 | 37.9 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_x101_vd_64x4d_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_x101_vd_64x4d_fpn_1x.yml) | +| ResNeXt101-vd-64x4d-FPN | Mask | 1 | 2x | 7.859 | 42.6 | 37.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_x101_vd_64x4d_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_x101_vd_64x4d_fpn_2x.yml) | +| SENet154-vd-FPN | Faster | 1 | 1.44x | 3.408 | 42.9 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_se154_vd_fpn_s1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_se154_vd_fpn_s1x.yml) | +| SENet154-vd-FPN | Mask | 1 | 1.44x | 3.233 | 44.0 | 38.7 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_se154_vd_fpn_s1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_se154_vd_fpn_s1x.yml) | +| ResNet101-vd-FPN | CascadeClsAware Faster | 2 | 1x | - | 44.7(softnms) | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.yml) | +| ResNet101-vd-FPN | CascadeClsAware Faster | 2 | 1x | - | 46.5(multi-scale test) | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.yml) | ### Deformable ConvNets v2 | Backbone | Type | Conv | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs | | :---------------------- | :------------- | :---: | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :----: | -| ResNet50-FPN | Faster | c3-c5 | 2 | 1x | 19.978 | 41.0 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/faster_rcnn_dcn_r50_fpn_1x.yml) | -| ResNet50-vd-FPN | Faster | c3-c5 | 2 | 2x | 19.222 | 42.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_vd_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_2x.yml) | -| ResNet101-vd-FPN | Faster | c3-c5 | 2 | 1x | 14.477 | 44.1 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r101_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/faster_rcnn_dcn_r101_vd_fpn_1x.yml) | -| ResNeXt101-vd-64x4d-FPN | Faster | c3-c5 | 1 | 1x | 7.209 | 45.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) | -| ResNet50-FPN | Mask | c3-c5 | 1 | 1x | 14.53 | 41.9 | 37.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/mask_rcnn_dcn_r50_fpn_1x.yml) | -| ResNet50-vd-FPN | Mask | c3-c5 | 1 | 2x | 14.832 | 42.9 | 38.0 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r50_vd_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/mask_rcnn_dcn_r50_vd_fpn_2x.yml) | -| ResNet101-vd-FPN | Mask | c3-c5 | 1 | 1x | 11.546 | 44.6 | 39.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r101_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x.yml) | -| ResNeXt101-vd-64x4d-FPN | Mask | c3-c5 | 1 | 1x | 6.45 | 46.2 | 40.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) | -| ResNet50-FPN | Cascade Faster | c3-c5 | 2 | 1x | - | 44.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/cascade_rcnn_dcn_r50_fpn_1x.yml) | -| ResNet101-vd-FPN | Cascade Faster | c3-c5 | 2 | 1x | - | 46.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r101_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/cascade_rcnn_dcn_r101_vd_fpn_1x.yml) | -| ResNeXt101-vd-FPN | Cascade Faster | c3-c5 | 2 | 1x | - | 47.3 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) | -| SENet154-vd-FPN | Cascade Mask | c3-c5 | 1 | 1.44x | - | 51.9 | 43.9 | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_mask_rcnn_dcnv2_se154_vd_fpn_gn_s1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/cascade_mask_rcnn_dcnv2_se154_vd_fpn_gn_s1x.yml) | -| ResNet200-vd-FPN-Nonlocal | CascadeClsAware Faster | c3-c5 | 1 | 2.5x | 3.103 | 51.7%(softnms) | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.yml) | -| CBResNet200-vd-FPN-Nonlocal | Cascade Faster | c3-c5 | 1 | 2.5x | 1.68 | 53.3%(softnms) | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cbr200_vd_fpn_dcnv2_nonlocal_softnms.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/cascade_rcnn_cbr200_vd_fpn_dcnv2_nonlocal_softnms.yml) | +| ResNet50-FPN | Faster | c3-c5 | 2 | 1x | 19.978 | 41.0 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/faster_rcnn_dcn_r50_fpn_1x.yml) | +| ResNet50-vd-FPN | Faster | c3-c5 | 2 | 2x | 19.222 | 42.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_vd_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_2x.yml) | +| ResNet101-vd-FPN | Faster | c3-c5 | 2 | 1x | 14.477 | 44.1 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r101_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/faster_rcnn_dcn_r101_vd_fpn_1x.yml) | +| ResNeXt101-vd-64x4d-FPN | Faster | c3-c5 | 1 | 1x | 7.209 | 45.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) | +| ResNet50-FPN | Mask | c3-c5 | 1 | 1x | 14.53 | 41.9 | 37.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/mask_rcnn_dcn_r50_fpn_1x.yml) | +| ResNet50-vd-FPN | Mask | c3-c5 | 1 | 2x | 14.832 | 42.9 | 38.0 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r50_vd_fpn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/mask_rcnn_dcn_r50_vd_fpn_2x.yml) | +| ResNet101-vd-FPN | Mask | c3-c5 | 1 | 1x | 11.546 | 44.6 | 39.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r101_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x.yml) | +| ResNeXt101-vd-64x4d-FPN | Mask | c3-c5 | 1 | 1x | 6.45 | 46.2 | 40.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) | +| ResNet50-FPN | Cascade Faster | c3-c5 | 2 | 1x | - | 44.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/cascade_rcnn_dcn_r50_fpn_1x.yml) | +| ResNet101-vd-FPN | Cascade Faster | c3-c5 | 2 | 1x | - | 46.4 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r101_vd_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/cascade_rcnn_dcn_r101_vd_fpn_1x.yml) | +| ResNeXt101-vd-FPN | Cascade Faster | c3-c5 | 2 | 1x | - | 47.3 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) | +| SENet154-vd-FPN | Cascade Mask | c3-c5 | 1 | 1.44x | - | 51.9 | 43.9 | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_mask_rcnn_dcnv2_se154_vd_fpn_gn_s1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/cascade_mask_rcnn_dcnv2_se154_vd_fpn_gn_s1x.yml) | +| ResNet200-vd-FPN-Nonlocal | CascadeClsAware Faster | c3-c5 | 1 | 2.5x | 3.103 | 51.7%(softnms) | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.yml) | +| CBResNet200-vd-FPN-Nonlocal | Cascade Faster | c3-c5 | 1 | 2.5x | 1.68 | 53.3%(softnms) | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cbr200_vd_fpn_dcnv2_nonlocal_softnms.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/cascade_rcnn_cbr200_vd_fpn_dcnv2_nonlocal_softnms.yml) | **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/PaddleDetection/tree/master/configs/dcn) +- Detailed configuration file in [configs/dcn](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn) ### HRNet -* See more details in [HRNet model zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/hrnet/). +* See more details in [HRNet model zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/hrnet/). ### Res2Net -* See more details in [Res2Net model zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/res2net/). +* See more details in [Res2Net model zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/res2net/). ### IOU loss -* GIOU loss and DIOU loss are included now. See more details in [IOU loss model zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/iou_loss/). +* GIOU loss and DIOU loss are included now. See more details in [IOU loss model zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/iou_loss/). ### GCNet -* See more details in [GCNet model zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/gcnet/). +* See more details in [GCNet model zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/gcnet/). ### Libra R-CNN -* See more details in [Libra R-CNN model zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/libra_rcnn/). +* See more details in [Libra R-CNN model zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/libra_rcnn/). ### Auto Augmentation -* See more details in [Auto Augmentation model zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/autoaugment/). +* See more details in [Auto Augmentation model zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/autoaugment/). ### Group Normalization | Backbone | Type | Image/gpu | Lr schd | Box AP | Mask AP | Download | Configs | | :------------------- | :------------- | :-----: | :-----: | :----: | :-----: | :----------------------------------------------------------: |:----: | -| ResNet50-FPN | Faster | 2 | 2x | 39.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_gn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/gn/faster_rcnn_r50_fpn_gn_2x.yml) | -| ResNet50-FPN | Mask | 1 | 2x | 40.1 | 35.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_gn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/gn/mask_rcnn_r50_fpn_gn_2x.yml) | +| ResNet50-FPN | Faster | 2 | 2x | 39.7 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_gn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/gn/faster_rcnn_r50_fpn_gn_2x.yml) | +| ResNet50-FPN | Mask | 1 | 2x | 40.1 | 35.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_gn_2x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/gn/mask_rcnn_r50_fpn_gn_2x.yml) | **Notes:** - Group Normalization reference from [Group Normalization](https://arxiv.org/abs/1803.08494). -- Detailed configuration file in [configs/gn](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/gn) +- Detailed configuration file in [configs/gn](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/gn) ### YOLO v3 @@ -134,35 +134,35 @@ The backbone models pretrained on ImageNet are available. All backbone models ar | DarkNet53 (paper) | ImageNet | 608 | False | 8 | 270e | - | 33.0 | - | - | | DarkNet53 (paper) | ImageNet | 416 | False | 8 | 270e | - | 31.0 | - | - | | DarkNet53 (paper) | ImageNet | 320 | False | 8 | 270e | - | 28.2 | - | - | -| DarkNet53 | ImageNet | 608 | False | 8 | 270e | 45.571 | 38.9 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet.yml) | -| DarkNet53 | ImageNet | 416 | False | 8 | 270e | - | 37.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet.yml) | -| DarkNet53 | ImageNet | 320 | False | 8 | 270e | - | 34.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet.yml) | -| MobileNet-V1 | ImageNet | 608 | False | 8 | 270e | 78.302 | 29.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v1.yml) | -| MobileNet-V1 | ImageNet | 416 | False | 8 | 270e | - | 29.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v1.yml) | -| MobileNet-V1 | ImageNet | 320 | False | 8 | 270e | - | 27.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v1.yml) | -| MobileNet-V3 | ImageNet | 608 | False | 8 | 270e | - | 31.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v3.yml) | -| MobileNet-V3 | ImageNet | 416 | False | 8 | 270e | - | 29.9 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v3.yml) | -| MobileNet-V3 | ImageNet | 320 | False | 8 | 270e | - | 27.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v3.yml) | -| ResNet34 | ImageNet | 608 | False | 8 | 270e | 63.356 | 36.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_r34.yml) | -| ResNet34 | ImageNet | 416 | False | 8 | 270e | - | 34.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_r34.yml) | -| ResNet34 | ImageNet | 320 | False | 8 | 270e | - | 31.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_r34.yml) | -| ResNet50_vd | ImageNet | 608 | True | 8 | 270e | - | 39.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/dcn/yolov3_r50vd_dcn.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/yolov3_r50vd_dcn.yml) | -| ResNet50_vd | Object365 | 608 | True | 8 | 270e | - | 41.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_obj365_pretrained_coco.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/yolov3_r50vd_dcn_obj365_pretrained_coco.yml) | +| DarkNet53 | ImageNet | 608 | False | 8 | 270e | 45.571 | 38.9 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet.yml) | +| DarkNet53 | ImageNet | 416 | False | 8 | 270e | - | 37.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet.yml) | +| DarkNet53 | ImageNet | 320 | False | 8 | 270e | - | 34.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet.yml) | +| MobileNet-V1 | ImageNet | 608 | False | 8 | 270e | 78.302 | 29.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v1.yml) | +| MobileNet-V1 | ImageNet | 416 | False | 8 | 270e | - | 29.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v1.yml) | +| MobileNet-V1 | ImageNet | 320 | False | 8 | 270e | - | 27.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v1.yml) | +| MobileNet-V3 | ImageNet | 608 | False | 8 | 270e | - | 31.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v3.yml) | +| MobileNet-V3 | ImageNet | 416 | False | 8 | 270e | - | 29.9 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v3.yml) | +| MobileNet-V3 | ImageNet | 320 | False | 8 | 270e | - | 27.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v3.yml) | +| ResNet34 | ImageNet | 608 | False | 8 | 270e | 63.356 | 36.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_r34.yml) | +| ResNet34 | ImageNet | 416 | False | 8 | 270e | - | 34.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_r34.yml) | +| ResNet34 | ImageNet | 320 | False | 8 | 270e | - | 31.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_r34.yml) | +| ResNet50_vd | ImageNet | 608 | True | 8 | 270e | - | 39.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/dcn/yolov3_r50vd_dcn.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/yolov3_r50vd_dcn.yml) | +| ResNet50_vd | Object365 | 608 | True | 8 | 270e | - | 41.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_obj365_pretrained_coco.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/yolov3_r50vd_dcn_obj365_pretrained_coco.yml) | ### YOLO v3 on Pascal VOC | Backbone | Size | Image/gpu | Lr schd | Inf time (fps) | Box AP(0.5) | Download | Configs | | :----------- | :--: | :-------: | :-----: | :------------: | :----: | :----------------------------------------------------------: | :----: | -| DarkNet53 | 608 | 8 | 270e | 54.977 | 83.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet_voc.yml) | -| DarkNet53 | 416 | 8 | 270e | - | 83.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet_voc.yml) | -| DarkNet53 | 320 | 8 | 270e | - | 82.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet_voc.yml) | -| DarkNet53 Diou-Loss | 608 | 8 | 270e | - | 83.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc_diouloss.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet_voc_diouloss.yml) | -| MobileNet-V1 | 608 | 8 | 270e | 104.291 | 76.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v1_voc.yml) | -| MobileNet-V1 | 416 | 8 | 270e | - | 76.7 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v1_voc.yml) | -| MobileNet-V1 | 320 | 8 | 270e | - | 75.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v1_voc.yml) | -| ResNet34 | 608 | 8 | 270e | 82.247 | 82.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_r34_voc.yml) | -| ResNet34 | 416 | 8 | 270e | - | 81.9 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_r34_voc.yml) | -| ResNet34 | 320 | 8 | 270e | - | 80.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_r34_voc.yml) | +| DarkNet53 | 608 | 8 | 270e | 54.977 | 83.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet_voc.yml) | +| DarkNet53 | 416 | 8 | 270e | - | 83.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet_voc.yml) | +| DarkNet53 | 320 | 8 | 270e | - | 82.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet_voc.yml) | +| DarkNet53 Diou-Loss | 608 | 8 | 270e | - | 83.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc_diouloss.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet_voc_diouloss.yml) | +| MobileNet-V1 | 608 | 8 | 270e | 104.291 | 76.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v1_voc.yml) | +| MobileNet-V1 | 416 | 8 | 270e | - | 76.7 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v1_voc.yml) | +| MobileNet-V1 | 320 | 8 | 270e | - | 75.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v1_voc.yml) | +| ResNet34 | 608 | 8 | 270e | 82.247 | 82.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_r34_voc.yml) | +| ResNet34 | 416 | 8 | 270e | - | 81.9 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_r34_voc.yml) | +| ResNet34 | 320 | 8 | 270e | - | 80.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_r34_voc.yml) | **Notes:** @@ -179,9 +179,9 @@ results of image size 608/416/320 above. Deformable conv is added on stage 5 of | Backbone | Image/gpu | Lr schd | Inf time (fps) | Box AP | Download | Configs | | :---------------: | :-----: | :-----: | :----: | :----: | :-------: | :----: | -| ResNet50-FPN | 2 | 1x | - | 36.0 | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/retinanet_r50_fpn_1x.yml) | -| ResNet101-FPN | 2 | 1x | - | 37.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r101_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/retinanet_r101_fpn_1x.yml) | -| ResNeXt101-vd-FPN | 1 | 1x | - | 40.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_x101_vd_64x4d_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/retinanet_x101_vd_64x4d_fpn_1x.yml) | +| ResNet50-FPN | 2 | 1x | - | 36.0 | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r50_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/retinanet_r50_fpn_1x.yml) | +| ResNet101-FPN | 2 | 1x | - | 37.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r101_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/retinanet_r101_fpn_1x.yml) | +| ResNeXt101-vd-FPN | 1 | 1x | - | 40.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_x101_vd_64x4d_fpn_1x.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/retinanet_x101_vd_64x4d_fpn_1x.yml) | **Notes:** In RetinaNet, the base LR is changed to 0.01 for minibatch size 16. @@ -197,12 +197,12 @@ results of image size 608/416/320 above. Deformable conv is added on stage 5 of | Backbone | Size | Image/gpu | Lr schd | Inf time (fps) | Box AP | Download | Configs | | :------: | :--: | :-------: | :-----: | :------------: | :----: | :----------------------------------------------------------: | :----: | -| MobileNet_v1 | 300 | 64 | Cosine decay(40w) | - | 23.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssdlite_mobilenet_v1.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssdlite_mobilenet_v1.yml) | -| MobileNet_v3 small | 320 | 64 | Cosine decay(40w) | - | 16.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_small.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssdlite_mobilenet_v3_small.yml) | -| MobileNet_v3 large | 320 | 64 | Cosine decay(40w) | - | 23.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_large.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssdlite_mobilenet_v3_large.yml) | -| MobileNet_v3 small w/ FPN | 320 | 64 | Cosine decay(40w) | - | 18.9 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_small_fpn.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssdlite_mobilenet_v3_small_fpn.yml) | -| MobileNet_v3 large w/ FPN | 320 | 64 | Cosine decay(40w) | - | 24.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_large_fpn.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssdlite_mobilenet_v3_large_fpn.yml) | -| GhostNet | 320 | 64 | Cosine decay(40w) | - | 23.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_ghostnet.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssdlite_ghostnet.yml) | +| MobileNet_v1 | 300 | 64 | Cosine decay(40w) | - | 23.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssdlite_mobilenet_v1.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssdlite_mobilenet_v1.yml) | +| MobileNet_v3 small | 320 | 64 | Cosine decay(40w) | - | 16.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_small.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssdlite_mobilenet_v3_small.yml) | +| MobileNet_v3 large | 320 | 64 | Cosine decay(40w) | - | 23.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_large.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssdlite_mobilenet_v3_large.yml) | +| MobileNet_v3 small w/ FPN | 320 | 64 | Cosine decay(40w) | - | 18.9 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_small_fpn.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssdlite_mobilenet_v3_small_fpn.yml) | +| MobileNet_v3 large w/ FPN | 320 | 64 | Cosine decay(40w) | - | 24.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_large_fpn.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssdlite_mobilenet_v3_large_fpn.yml) | +| GhostNet | 320 | 64 | Cosine decay(40w) | - | 23.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_ghostnet.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssdlite_ghostnet.yml) | **Notes:** `SSDLite` is trained in 8 GPU with total batch size as 512 and uses cosine decay strategy to train. @@ -210,8 +210,8 @@ results of image size 608/416/320 above. Deformable conv is added on stage 5 of | Backbone | Size | Image/gpu | Lr schd | Inf time (fps) | Box AP | Download | Configs | | :------: | :--: | :-------: | :-----: | :------------: | :----: | :----------------------------------------------------------: | :----: | -| VGG16 | 300 | 8 | 40w | 81.613 | 25.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_300.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssd_vgg16_300.yml) | -| VGG16 | 512 | 8 | 40w | 46.007 | 29.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_512.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssd_vgg16_512.yml) | +| VGG16 | 300 | 8 | 40w | 81.613 | 25.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_300.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssd_vgg16_300.yml) | +| VGG16 | 512 | 8 | 40w | 46.007 | 29.1 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_512.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssd_vgg16_512.yml) | **Notes:** VGG-SSD is trained in 4 GPU with total batch size as 32 and trained 400000 iters. @@ -219,9 +219,9 @@ results of image size 608/416/320 above. Deformable conv is added on stage 5 of | Backbone | Size | Image/gpu | Lr schd | Inf time (fps) | Box AP(0.5) | Download | Configs | | :----------- | :--: | :-------: | :-----: | :------------: | :----: | :----------------------------------------------------------: | :----: | -| MobileNet v1 | 300 | 32 | 120e | 159.543 | 73.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_mobilenet_v1_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssd_mobilenet_v1_voc.yml) | -| VGG16 | 300 | 8 | 240e | 117.279 | 77.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_300_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssd_vgg16_300_voc.yml) | -| VGG16 | 512 | 8 | 240e | 65.975 | 80.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_512_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssd_vgg16_512_voc.yml) | +| MobileNet v1 | 300 | 32 | 120e | 159.543 | 73.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_mobilenet_v1_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssd_mobilenet_v1_voc.yml) | +| VGG16 | 300 | 8 | 240e | 117.279 | 77.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_300_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssd_vgg16_300_voc.yml) | +| VGG16 | 512 | 8 | 240e | 65.975 | 80.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_512_voc.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssd_vgg16_512_voc.yml) | **NOTE**: MobileNet-SSD is trained in 2 GPU with totoal batch size as 64 and trained 120 epoches. VGG-SSD is trained in 4 GPU with total batch size as 32 and trained 240 epoches. SSD training data augmentations: randomly color distortion, randomly cropping, randomly expansion, randomly flipping. diff --git a/static/docs/MODEL_ZOO_cn.md b/static/docs/MODEL_ZOO_cn.md index 65444bef4e68554650121d0cb50190cccd613655..7f6f9ce41c4103fcc34a0f7dfcd8b85d78ebb773 100644 --- a/static/docs/MODEL_ZOO_cn.md +++ b/static/docs/MODEL_ZOO_cn.md @@ -33,95 +33,95 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型 | 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP | 下载 | 配置文件 | | :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: | -| ResNet50 | Faster | 1 | 1x | 12.747 | 35.2 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r50_1x.yml) | -| ResNet50 | Faster | 1 | 2x | 12.686 | 37.1 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r50_2x.yml) | -| ResNet50 | Mask | 1 | 1x | 11.615 | 36.5 | 32.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_r50_1x.yml) | -| ResNet50 | Mask | 1 | 2x | 11.494 | 38.2 | 33.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_r50_2x.yml) | -| ResNet50-vd | Faster | 1 | 1x | 12.575 | 36.4 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r50_vd_1x.yml) | -| ResNet34-FPN | Faster | 2 | 1x | - | 36.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r34_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r34_fpn_1x.yml) | -| ResNet34-vd-FPN | Faster | 2 | 1x | - | 37.4 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r34_vd_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r34_vd_fpn_1x.yml) | -| ResNet50-FPN | Faster | 2 | 1x | 22.273 | 37.2 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r50_fpn_1x.yml) | -| ResNet50-FPN | Faster | 2 | 2x | 22.297 | 37.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r50_fpn_2x.yml) | -| ResNet50-FPN | Mask | 1 | 1x | 15.184 | 37.9 | 34.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_r50_fpn_1x.yml) | -| ResNet50-FPN | Mask | 1 | 2x | 15.881 | 38.7 | 34.7 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_r50_fpn_2x.yml) | -| ResNet50-FPN | Cascade Faster | 2 | 1x | 17.507 | 40.9 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/cascade_rcnn_r50_fpn_1x.yml) | -| ResNet50-FPN | Cascade Mask | 1 | 1x | 12.43 | 41.3 | 35.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_mask_rcnn_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/cascade_mask_rcnn_r50_fpn_1x.yml) | -| ResNet50-vd-FPN | Faster | 2 | 2x | 21.847 | 38.9 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r50_vd_fpn_2x.yml) | -| ResNet50-vd-FPN | Mask | 1 | 2x | 15.825 | 39.8 | 35.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_r50_vd_fpn_2x.yml) | -| CBResNet50-vd-FPN | Faster | 2 | 1x | - | 39.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_cbr50_vd_dual_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_cbr50_vd_dual_fpn_1x.yml) | -| ResNet101 | Faster | 1 | 1x | 9.316 | 38.3 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r101_1x.yml) | -| ResNet101-FPN | Faster | 1 | 1x | 17.297 | 38.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r101_fpn_1x.yml) | -| ResNet101-FPN | Faster | 1 | 2x | 17.246 | 39.1 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r101_fpn_2x.yml) | -| ResNet101-FPN | Mask | 1 | 1x | 12.983 | 39.5 | 35.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r101_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_r101_fpn_1x.yml) | -| ResNet101-vd-FPN | Faster | 1 | 1x | 17.011 | 40.5 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_vd_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r101_vd_fpn_1x.yml) | -| ResNet101-vd-FPN | Faster | 1 | 2x | 16.934 | 40.8 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_vd_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_r101_vd_fpn_2x.yml) | -| ResNet101-vd-FPN | Mask | 1 | 1x | 13.105 | 41.4 | 36.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r101_vd_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_r101_vd_fpn_1x.yml) | -| CBResNet101-vd-FPN | Faster | 2 | 1x | - | 42.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_cbr101_vd_dual_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_cbr101_vd_dual_fpn_1x.yml) | -| ResNeXt101-vd-FPN | Faster | 1 | 1x | 8.815 | 42.2 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_x101_vd_64x4d_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml) | -| ResNeXt101-vd-FPN | Faster | 1 | 2x | 8.809 | 41.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_x101_vd_64x4d_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_x101_vd_64x4d_fpn_2x.yml) | -| ResNeXt101-vd-FPN | Mask | 1 | 1x | 7.689 | 42.9 | 37.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_x101_vd_64x4d_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_x101_vd_64x4d_fpn_1x.yml) | -| ResNeXt101-vd-FPN | Mask | 1 | 2x | 7.859 | 42.6 | 37.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_x101_vd_64x4d_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_x101_vd_64x4d_fpn_2x.yml) | -| SENet154-vd-FPN | Faster | 1 | 1.44x | 3.408 | 42.9 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_se154_vd_fpn_s1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/faster_rcnn_se154_vd_fpn_s1x.yml) | -| SENet154-vd-FPN | Mask | 1 | 1.44x | 3.233 | 44.0 | 38.7 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_se154_vd_fpn_s1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/mask_rcnn_se154_vd_fpn_s1x.yml) | -| ResNet101-vd-FPN | CascadeClsAware Faster | 2 | 1x | - | 44.7(softnms) | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.yml) | -| ResNet101-vd-FPN | CascadeClsAware Faster | 2 | 1x | - | 46.5(multi-scale test) | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.yml) | +| ResNet50 | Faster | 1 | 1x | 12.747 | 35.2 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r50_1x.yml) | +| ResNet50 | Faster | 1 | 2x | 12.686 | 37.1 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r50_2x.yml) | +| ResNet50 | Mask | 1 | 1x | 11.615 | 36.5 | 32.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_r50_1x.yml) | +| ResNet50 | Mask | 1 | 2x | 11.494 | 38.2 | 33.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_r50_2x.yml) | +| ResNet50-vd | Faster | 1 | 1x | 12.575 | 36.4 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r50_vd_1x.yml) | +| ResNet34-FPN | Faster | 2 | 1x | - | 36.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r34_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r34_fpn_1x.yml) | +| ResNet34-vd-FPN | Faster | 2 | 1x | - | 37.4 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r34_vd_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r34_vd_fpn_1x.yml) | +| ResNet50-FPN | Faster | 2 | 1x | 22.273 | 37.2 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r50_fpn_1x.yml) | +| ResNet50-FPN | Faster | 2 | 2x | 22.297 | 37.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r50_fpn_2x.yml) | +| ResNet50-FPN | Mask | 1 | 1x | 15.184 | 37.9 | 34.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_r50_fpn_1x.yml) | +| ResNet50-FPN | Mask | 1 | 2x | 15.881 | 38.7 | 34.7 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_r50_fpn_2x.yml) | +| ResNet50-FPN | Cascade Faster | 2 | 1x | 17.507 | 40.9 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/cascade_rcnn_r50_fpn_1x.yml) | +| ResNet50-FPN | Cascade Mask | 1 | 1x | 12.43 | 41.3 | 35.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_mask_rcnn_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/cascade_mask_rcnn_r50_fpn_1x.yml) | +| ResNet50-vd-FPN | Faster | 2 | 2x | 21.847 | 38.9 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r50_vd_fpn_2x.yml) | +| ResNet50-vd-FPN | Mask | 1 | 2x | 15.825 | 39.8 | 35.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_r50_vd_fpn_2x.yml) | +| CBResNet50-vd-FPN | Faster | 2 | 1x | - | 39.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_cbr50_vd_dual_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_cbr50_vd_dual_fpn_1x.yml) | +| ResNet101 | Faster | 1 | 1x | 9.316 | 38.3 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r101_1x.yml) | +| ResNet101-FPN | Faster | 1 | 1x | 17.297 | 38.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r101_fpn_1x.yml) | +| ResNet101-FPN | Faster | 1 | 2x | 17.246 | 39.1 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r101_fpn_2x.yml) | +| ResNet101-FPN | Mask | 1 | 1x | 12.983 | 39.5 | 35.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r101_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_r101_fpn_1x.yml) | +| ResNet101-vd-FPN | Faster | 1 | 1x | 17.011 | 40.5 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_vd_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r101_vd_fpn_1x.yml) | +| ResNet101-vd-FPN | Faster | 1 | 2x | 16.934 | 40.8 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_vd_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_r101_vd_fpn_2x.yml) | +| ResNet101-vd-FPN | Mask | 1 | 1x | 13.105 | 41.4 | 36.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r101_vd_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_r101_vd_fpn_1x.yml) | +| CBResNet101-vd-FPN | Faster | 2 | 1x | - | 42.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_cbr101_vd_dual_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_cbr101_vd_dual_fpn_1x.yml) | +| ResNeXt101-vd-FPN | Faster | 1 | 1x | 8.815 | 42.2 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_x101_vd_64x4d_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml) | +| ResNeXt101-vd-FPN | Faster | 1 | 2x | 8.809 | 41.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_x101_vd_64x4d_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_x101_vd_64x4d_fpn_2x.yml) | +| ResNeXt101-vd-FPN | Mask | 1 | 1x | 7.689 | 42.9 | 37.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_x101_vd_64x4d_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_x101_vd_64x4d_fpn_1x.yml) | +| ResNeXt101-vd-FPN | Mask | 1 | 2x | 7.859 | 42.6 | 37.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_x101_vd_64x4d_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_x101_vd_64x4d_fpn_2x.yml) | +| SENet154-vd-FPN | Faster | 1 | 1.44x | 3.408 | 42.9 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_se154_vd_fpn_s1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/faster_rcnn_se154_vd_fpn_s1x.yml) | +| SENet154-vd-FPN | Mask | 1 | 1.44x | 3.233 | 44.0 | 38.7 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_se154_vd_fpn_s1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/mask_rcnn_se154_vd_fpn_s1x.yml) | +| ResNet101-vd-FPN | CascadeClsAware Faster | 2 | 1x | - | 44.7(softnms) | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.yml) | +| ResNet101-vd-FPN | CascadeClsAware Faster | 2 | 1x | - | 46.5(multi-scale test) | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/cascade_rcnn_cls_aware_r101_vd_fpn_1x_softnms.yml) | ### Deformable 卷积网络v2 | 骨架网络 | 网络类型 | 卷积 | 每张GPU图片个数 | 学习率策略 |推理时间(fps)| Box AP | Mask AP | 下载 | 配置文件 | | :------------------- | :------------- | :-----: |:--------: | :-----: | :-----------: |:----: | :-----: | :----------------------------------------------------------: | :----: | -| ResNet50-FPN | Faster | c3-c5 | 2 | 1x | 19.978 | 41.0 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/faster_rcnn_dcn_r50_fpn_1x.yml) | -| ResNet50-vd-FPN | Faster | c3-c5 | 2 | 2x | 19.222 | 42.4 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_vd_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_2x.yml) | -| ResNet101-vd-FPN | Faster | c3-c5 | 2 | 1x | 14.477 | 44.1 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r101_vd_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/faster_rcnn_dcn_r101_vd_fpn_1x.yml) | -| ResNeXt101-vd-FPN | Faster | c3-c5 | 1 | 1x | 7.209 | 45.2 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) |[配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) | -| ResNet50-FPN | Mask | c3-c5 | 1 | 1x | 14.53 | 41.9 | 37.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/mask_rcnn_dcn_r50_fpn_1x.yml) | -| ResNet50-vd-FPN | Mask | c3-c5 | 1 | 2x | 14.832 | 42.9 | 38.0 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r50_vd_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/mask_rcnn_dcn_r50_vd_fpn_2x.yml) | -| ResNet101-vd-FPN | Mask | c3-c5 | 1 | 1x | 11.546 | 44.6 | 39.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r101_vd_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x.yml) | -| ResNeXt101-vd-FPN | Mask | c3-c5 | 1 | 1x | 6.45 | 46.2 | 40.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) | -| ResNet50-FPN | Cascade Faster | c3-c5 | 2 | 1x | - | 44.2 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/cascade_rcnn_dcn_r50_fpn_1x.yml) | -| ResNet101-vd-FPN | Cascade Faster | c3-c5 | 2 | 1x | - | 46.4 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r101_vd_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/cascade_rcnn_dcn_r101_vd_fpn_1x.yml) | -| ResNeXt101-vd-FPN | Cascade Faster | c3-c5 | 2 | 1x | - | 47.3 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) | -| SENet154-vd-FPN | Cascade Mask | c3-c5 | 1 | 1.44x | - | 51.9 | 43.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_mask_rcnn_dcnv2_se154_vd_fpn_gn_s1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/cascade_mask_rcnn_dcnv2_se154_vd_fpn_gn_s1x.yml) | -| ResNet200-vd-FPN-Nonlocal | CascadeClsAware Faster | c3-c5 | 1 | 2.5x | 3.103 | 51.7%(softnms) | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.yml) | -| CBResNet200-vd-FPN-Nonlocal | Cascade Faster | c3-c5 | 1 | 2.5x | 1.68 | 53.3%(softnms) | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cbr200_vd_fpn_dcnv2_nonlocal_softnms.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/cascade_rcnn_cbr200_vd_fpn_dcnv2_nonlocal_softnms.yml) | +| ResNet50-FPN | Faster | c3-c5 | 2 | 1x | 19.978 | 41.0 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/faster_rcnn_dcn_r50_fpn_1x.yml) | +| ResNet50-vd-FPN | Faster | c3-c5 | 2 | 2x | 19.222 | 42.4 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r50_vd_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_2x.yml) | +| ResNet101-vd-FPN | Faster | c3-c5 | 2 | 1x | 14.477 | 44.1 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_r101_vd_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/faster_rcnn_dcn_r101_vd_fpn_1x.yml) | +| ResNeXt101-vd-FPN | Faster | c3-c5 | 1 | 1x | 7.209 | 45.2 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) |[配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) | +| ResNet50-FPN | Mask | c3-c5 | 1 | 1x | 14.53 | 41.9 | 37.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/mask_rcnn_dcn_r50_fpn_1x.yml) | +| ResNet50-vd-FPN | Mask | c3-c5 | 1 | 2x | 14.832 | 42.9 | 38.0 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r50_vd_fpn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/mask_rcnn_dcn_r50_vd_fpn_2x.yml) | +| ResNet101-vd-FPN | Mask | c3-c5 | 1 | 1x | 11.546 | 44.6 | 39.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r101_vd_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x.yml) | +| ResNeXt101-vd-FPN | Mask | c3-c5 | 1 | 1x | 6.45 | 46.2 | 40.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) | +| ResNet50-FPN | Cascade Faster | c3-c5 | 2 | 1x | - | 44.2 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/cascade_rcnn_dcn_r50_fpn_1x.yml) | +| ResNet101-vd-FPN | Cascade Faster | c3-c5 | 2 | 1x | - | 46.4 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r101_vd_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/cascade_rcnn_dcn_r101_vd_fpn_1x.yml) | +| ResNeXt101-vd-FPN | Cascade Faster | c3-c5 | 2 | 1x | - | 47.3 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) | +| SENet154-vd-FPN | Cascade Mask | c3-c5 | 1 | 1.44x | - | 51.9 | 43.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_mask_rcnn_dcnv2_se154_vd_fpn_gn_s1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/cascade_mask_rcnn_dcnv2_se154_vd_fpn_gn_s1x.yml) | +| ResNet200-vd-FPN-Nonlocal | CascadeClsAware Faster | c3-c5 | 1 | 2.5x | 3.103 | 51.7%(softnms) | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.yml) | +| CBResNet200-vd-FPN-Nonlocal | Cascade Faster | c3-c5 | 1 | 2.5x | 1.68 | 53.3%(softnms) | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cbr200_vd_fpn_dcnv2_nonlocal_softnms.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/cascade_rcnn_cbr200_vd_fpn_dcnv2_nonlocal_softnms.yml) | **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/PaddleDetection/blob/master/configs/dcn) +- 详细的配置文件在[configs/dcn](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/dcn) ### HRNet -* 详情见[HRNet模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/hrnet/)。 +* 详情见[HRNet模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/hrnet/)。 ### Res2Net -* 详情见[Res2Net模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/res2net/)。 +* 详情见[Res2Net模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/res2net/)。 ### IOU loss -* 目前模型库中包括GIOU loss和DIOU loss，详情见[IOU loss模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/master//configs/iou_loss/). +* 目前模型库中包括GIOU loss和DIOU loss，详情见[IOU loss模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static//configs/iou_loss/). ### GCNet -* 详情见[GCNet模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/gcnet/). +* 详情见[GCNet模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/gcnet/). ### Libra R-CNN -* 详情见[Libra R-CNN模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/libra_rcnn/). +* 详情见[Libra R-CNN模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/libra_rcnn/). ### Auto Augmentation -* 详情见[Auto Augmentation模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/autoaugment/). +* 详情见[Auto Augmentation模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/autoaugment/). ### 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 | 配置文件 | | :------------------- | :------------- |:--------: | :-----: | :----: | :-----: | :----------------------------------------------------------: | :----: | -| ResNet50-FPN | Faster | 2 | 2x | 39.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_gn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/gn/faster_rcnn_r50_fpn_gn_2x.yml) | -| ResNet50-FPN | Mask | 1 | 2x | 40.1 | 35.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_gn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/gn/mask_rcnn_r50_fpn_gn_2x.yml) | +| ResNet50-FPN | Faster | 2 | 2x | 39.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_gn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/gn/faster_rcnn_r50_fpn_gn_2x.yml) | +| ResNet50-FPN | Mask | 1 | 2x | 40.1 | 35.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_gn_2x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/gn/mask_rcnn_r50_fpn_gn_2x.yml) | **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/PaddleDetection/blob/master/configs/gn) +- 详细的配置文件在[configs/gn](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/gn) ### YOLO v3 @@ -130,35 +130,35 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型 | DarkNet53 (paper) | ImageNet | 608 | 否 | 8 | 270e | - | 33.0 | - | - | | DarkNet53 (paper) | ImageNet | 416 | 否 | 8 | 270e | - | 31.0 | - | - | | DarkNet53 (paper) | ImageNet | 320 | 否 | 8 | 270e | - | 28.2 | - | - | -| DarkNet53 | ImageNet | 608 | 否 | 8 | 270e | 45.571 | 38.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet.yml) | -| DarkNet53 | ImageNet | 416 | 否 | 8 | 270e | - | 37.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet.yml) | -| DarkNet53 | ImageNet | 320 | 否 | 8 | 270e | - | 34.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet.yml) | -| MobileNet-V1 | ImageNet | 608 | 否 | 8 | 270e | 78.302 | 29.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v1.yml) | -| MobileNet-V1 | ImageNet | 416 | 否 | 8 | 270e | - | 29.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v1.yml) | -| MobileNet-V1 | ImageNet | 320 | 否 | 8 | 270e | - | 27.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v1.yml) | -| MobileNet-V3 | ImageNet | 608 | 否 | 8 | 270e | - | 31.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v3.yml) | -| MobileNet-V3 | ImageNet | 416 | 否 | 8 | 270e | - | 29.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v3.yml) | -| MobileNet-V3 | ImageNet | 320 | 否 | 8 | 270e | - | 27.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v3.yml) | -| ResNet34 | ImageNet | 608 | 否 | 8 | 270e | 63.356 | 36.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_r34.yml) | -| ResNet34 | ImageNet | 416 | 否 | 8 | 270e | - | 34.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_r34.yml) | -| ResNet34 | ImageNet | 320 | 否 | 8 | 270e | - | 31.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_r34.yml) | -| ResNet50_vd | ImageNet | 608 | 是 | 8 | 270e | - | 39.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/yolov3_r50vd_dcn.yml) | -| ResNet50_vd | Object365 | 608 | 是 | 8 | 270e | - | 41.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_obj365_pretrained_coco.tar) |[配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/yolov3_r50vd_dcn_obj365_pretrained_coco.yml) | +| DarkNet53 | ImageNet | 608 | 否 | 8 | 270e | 45.571 | 38.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet.yml) | +| DarkNet53 | ImageNet | 416 | 否 | 8 | 270e | - | 37.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet.yml) | +| DarkNet53 | ImageNet | 320 | 否 | 8 | 270e | - | 34.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet.yml) | +| MobileNet-V1 | ImageNet | 608 | 否 | 8 | 270e | 78.302 | 29.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v1.yml) | +| MobileNet-V1 | ImageNet | 416 | 否 | 8 | 270e | - | 29.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v1.yml) | +| MobileNet-V1 | ImageNet | 320 | 否 | 8 | 270e | - | 27.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v1.yml) | +| MobileNet-V3 | ImageNet | 608 | 否 | 8 | 270e | - | 31.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v3.yml) | +| MobileNet-V3 | ImageNet | 416 | 否 | 8 | 270e | - | 29.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v3.yml) | +| MobileNet-V3 | ImageNet | 320 | 否 | 8 | 270e | - | 27.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v3.yml) | +| ResNet34 | ImageNet | 608 | 否 | 8 | 270e | 63.356 | 36.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_r34.yml) | +| ResNet34 | ImageNet | 416 | 否 | 8 | 270e | - | 34.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_r34.yml) | +| ResNet34 | ImageNet | 320 | 否 | 8 | 270e | - | 31.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_r34.yml) | +| ResNet50_vd | ImageNet | 608 | 是 | 8 | 270e | - | 39.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/yolov3_r50vd_dcn.yml) | +| ResNet50_vd | Object365 | 608 | 是 | 8 | 270e | - | 41.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_obj365_pretrained_coco.tar) |[配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/yolov3_r50vd_dcn_obj365_pretrained_coco.yml) | ### YOLO v3 基于Pasacl VOC数据集 | 骨架网络 | 输入尺寸 | 每张GPU图片个数 | 学习率策略 |推理时间(fps)| Box AP | 下载 | 配置文件 | | :----------- | :--: | :-----: | :-----: |:------------: |:----: | :-------: | :----: | -| DarkNet53 | 608 | 8 | 270e | 54.977 | 83.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet_voc.yml) | -| DarkNet53 | 416 | 8 | 270e | - | 83.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet_voc.yml) | -| DarkNet53 | 320 | 8 | 270e | - | 82.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet_voc.yml) | -| DarkNet53 Diou-Loss | 608 | 8 | 270e | - | 83.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc_diouloss.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet_voc_diouloss.yml) | -| MobileNet-V1 | 608 | 8 | 270e | 104.291 | 76.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v1_voc.yml) | -| MobileNet-V1 | 416 | 8 | 270e | - | 76.7 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v1_voc.yml) | -| MobileNet-V1 | 320 | 8 | 270e | - | 75.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_mobilenet_v1_voc.yml) | -| ResNet34 | 608 | 8 | 270e | 82.247 | 82.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_r34_voc.yml) | -| ResNet34 | 416 | 8 | 270e | - | 81.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_r34_voc.yml) | -| ResNet34 | 320 | 8 | 270e | - | 80.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_r34_voc.yml) | +| DarkNet53 | 608 | 8 | 270e | 54.977 | 83.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet_voc.yml) | +| DarkNet53 | 416 | 8 | 270e | - | 83.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet_voc.yml) | +| DarkNet53 | 320 | 8 | 270e | - | 82.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet_voc.yml) | +| DarkNet53 Diou-Loss | 608 | 8 | 270e | - | 83.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet_voc_diouloss.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet_voc_diouloss.yml) | +| MobileNet-V1 | 608 | 8 | 270e | 104.291 | 76.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v1_voc.yml) | +| MobileNet-V1 | 416 | 8 | 270e | - | 76.7 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v1_voc.yml) | +| MobileNet-V1 | 320 | 8 | 270e | - | 75.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_mobilenet_v1_voc.yml) | +| ResNet34 | 608 | 8 | 270e | 82.247 | 82.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_r34_voc.yml) | +| ResNet34 | 416 | 8 | 270e | - | 81.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_r34_voc.yml) | +| ResNet34 | 320 | 8 | 270e | - | 80.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_r34_voc.yml) | **注意事项:** @@ -171,9 +171,9 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型 | 骨架网络 | 每张GPU图片个数 | 学习率策略 | 推理时间(fps) | Box AP | 下载 | 配置文件 | | :---------------: | :-----: | :-----: | :----: | :----: | :-------: | :----: | -| ResNet50-FPN | 2 | 1x | - | 36.0 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/retinanet_r50_fpn_1x.yml) | -| ResNet101-FPN | 2 | 1x | - | 37.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r101_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/retinanet_r101_fpn_1x.yml) | -| ResNeXt101-vd-FPN | 1 | 1x | - | 40.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_x101_vd_64x4d_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/retinanet_x101_vd_64x4d_fpn_1x.yml) | +| ResNet50-FPN | 2 | 1x | - | 36.0 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r50_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/retinanet_r50_fpn_1x.yml) | +| ResNet101-FPN | 2 | 1x | - | 37.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r101_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/retinanet_r101_fpn_1x.yml) | +| ResNeXt101-vd-FPN | 1 | 1x | - | 40.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_x101_vd_64x4d_fpn_1x.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/retinanet_x101_vd_64x4d_fpn_1x.yml) | **注意事项:** RetinaNet系列模型中，在总batch size为16下情况下，初始学习率改为0.01。 @@ -181,7 +181,7 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型 | 尺度 | 每张GPU图片个数 | 学习率策略 | Box AP | 下载 | 配置文件 | | :---------------: | :-----: | :-----: | :----: | :-------: | :----: | -| EfficientDet-D0 | 16 | 300 epochs | 33.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/efficientdet_d0.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/efficientdet_d0.yml) | +| EfficientDet-D0 | 16 | 300 epochs | 33.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/efficientdet_d0.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/efficientdet_d0.yml) | **注意事项:** 在总batch size为128(8x16)时，基础学习率改为0.16。 @@ -189,12 +189,12 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型 | 骨架网络 | 输入尺寸 | 每张GPU图片个数 | 学习率策略|推理时间(fps) | Box AP | 下载 | 配置文件 | | :----------: | :--: | :-----: | :-----: |:------------: |:----: | :-------: | :----: | -| MobileNet_v1 | 300 | 64 | Cosine decay(40w) | - | 23.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ssdlite_mobilenet_v1.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssdlite_mobilenet_v1.yml) | -| MobileNet_v3 small | 320 | 64 | Cosine decay(40w) | - | 16.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_small.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssdlite_mobilenet_v3_small.yml) | -| MobileNet_v3 large | 320 | 64 | Cosine decay(40w) | - | 23.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_large.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssdlite_mobilenet_v3_large.yml) | -| MobileNet_v3 small w/ FPN | 320 | 64 | Cosine decay(40w) | - | 18.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_small_fpn.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssdlite_mobilenet_v3_small_fpn.yml) | -| MobileNet_v3 large w/ FPN | 320 | 64 | Cosine decay(40w) | - | 24.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_large_fpn.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssdlite_mobilenet_v3_large_fpn.yml) | -| GhostNet | 320 | 64 | Cosine decay(40w) | - | 23.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_ghostnet.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssdlite_ghostnet.yml) | +| MobileNet_v1 | 300 | 64 | Cosine decay(40w) | - | 23.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ssdlite_mobilenet_v1.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssdlite_mobilenet_v1.yml) | +| MobileNet_v3 small | 320 | 64 | Cosine decay(40w) | - | 16.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_small.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssdlite_mobilenet_v3_small.yml) | +| MobileNet_v3 large | 320 | 64 | Cosine decay(40w) | - | 23.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_large.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssdlite_mobilenet_v3_large.yml) | +| MobileNet_v3 small w/ FPN | 320 | 64 | Cosine decay(40w) | - | 18.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_small_fpn.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssdlite_mobilenet_v3_small_fpn.yml) | +| MobileNet_v3 large w/ FPN | 320 | 64 | Cosine decay(40w) | - | 24.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_large_fpn.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssdlite_mobilenet_v3_large_fpn.yml) | +| GhostNet | 320 | 64 | Cosine decay(40w) | - | 23.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_ghostnet.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssdlite_ghostnet.yml) | **注意事项:** SSDLite模型使用学习率余弦衰减策略在8卡GPU下总batch size为512。 @@ -202,8 +202,8 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型 | 骨架网络 | 输入尺寸 | 每张GPU图片个数 | 学习率策略|推理时间(fps) | Box AP | 下载 | 配置文件 | | :----------: | :--: | :-----: | :-----: |:------------: |:----: | :-------: | :----: | -| VGG16 | 300 | 8 | 40万 | 81.613 | 25.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_300.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssd_vgg16_300.yml) | -| VGG16 | 512 | 8 | 40万 | 46.007 | 29.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_512.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssd_vgg16_512.yml) | +| VGG16 | 300 | 8 | 40万 | 81.613 | 25.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_300.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssd_vgg16_300.yml) | +| VGG16 | 512 | 8 | 40万 | 46.007 | 29.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_512.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssd_vgg16_512.yml) | **注意事项:** VGG-SSD在总batch size为32下训练40万轮。 @@ -211,9 +211,9 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型 | 骨架网络 | 输入尺寸 | 每张GPU图片个数 | 学习率策略 |推理时间(fps)| Box AP | 下载 | 配置文件 | | :----------- | :--: | :-----: | :-----: | :------------: | :----: | :-------: | :----: | -| MobileNet v1 | 300 | 32 | 120e | 159.543 | 73.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ssd_mobilenet_v1_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssd_mobilenet_v1_voc.yml) | -| VGG16 | 300 | 8 | 240e | 117.279 | 77.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_300_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssd_vgg16_300_voc.yml) | -| VGG16 | 512 | 8 | 240e | 65.975 | 80.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_512_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ssd/ssd_vgg16_512_voc.yml) | +| MobileNet v1 | 300 | 32 | 120e | 159.543 | 73.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ssd_mobilenet_v1_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssd_mobilenet_v1_voc.yml) | +| VGG16 | 300 | 8 | 240e | 117.279 | 77.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_300_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssd_vgg16_300_voc.yml) | +| VGG16 | 512 | 8 | 240e | 65.975 | 80.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_512_voc.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/ssd/ssd_vgg16_512_voc.yml) | **注意事项:** MobileNet-SSD在2卡，总batch size为64下训练120周期。VGG-SSD在总batch size为32下训练240周期。数据增强包括：随机颜色失真，随机剪裁，随机扩张，随机翻转。 diff --git a/static/docs/advanced_tutorials/MODEL_TECHNICAL.md b/static/docs/advanced_tutorials/MODEL_TECHNICAL.md index b5068838bff51f40fd4148442a1bc61d96d0425f..80b02bdd0ef84502adb61ecc55785a3e9b8abcbd 100644 --- a/static/docs/advanced_tutorials/MODEL_TECHNICAL.md +++ b/static/docs/advanced_tutorials/MODEL_TECHNICAL.md @@ -34,7 +34,7 @@ PaddleDetection的网络模型模块所有代码逻辑在`ppdet/modeling/`中， ![](../images/models_figure.png) ## 新增模型 -我们以单阶段检测器YOLOv3为例，结合[yolov3_darknet.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/yolov3_darknet.yml)配置文件，对建立模型过程进行详细描述， +我们以单阶段检测器YOLOv3为例，结合[yolov3_darknet.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/yolov3_darknet.yml)配置文件，对建立模型过程进行详细描述， 按照此思路您可以快速搭建新的模型。 搭建新模型的一般步骤是：Backbone编写、检测组件编写与模型组网这三个步骤，下面为您详细介绍： diff --git a/static/docs/advanced_tutorials/READER.md b/static/docs/advanced_tutorials/READER.md index 836ef0a5c2054e8d33b31a2293d3e1bacb929446..704321ae66b73d43a6fee7a0175c375c247296e8 100644 --- a/static/docs/advanced_tutorials/READER.md +++ b/static/docs/advanced_tutorials/READER.md @@ -392,7 +392,7 @@ EvalReader： `DataLoader`的API详见[fluid.io.DataLoader](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api_cn/io_cn/DataLoader_cn.html#dataloader)。 具体步骤如下： -- 在[train.py](https://github.com/PaddlePaddle/PaddleDetection/blob/master/tools/train.py)、[eval.py](https://github.com/PaddlePaddle/PaddleDetection/blob/master/tools/eval.py)和[infer.py](https://github.com/PaddlePaddle/PaddleDetection/blob/master/tools/infer.py)里创建训练时的Reader： +- 在[train.py](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/tools/train.py)、[eval.py](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/tools/eval.py)和[infer.py](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/tools/infer.py)里创建训练时的Reader： ```python # 创建DataLoader对象 inputs_def = cfg['TestReader']['inputs_def'] diff --git a/static/docs/advanced_tutorials/TRANSFER_LEARNING.md b/static/docs/advanced_tutorials/TRANSFER_LEARNING.md index 407379a4cd1c72b469ad3381d52622edfb3a5fb6..69bb5bcf9ed072138a09187b0bfa361ea7366cee 100644 --- a/static/docs/advanced_tutorials/TRANSFER_LEARNING.md +++ b/static/docs/advanced_tutorials/TRANSFER_LEARNING.md @@ -11,7 +11,7 @@ In transfer learning, if different dataset and the number of classes is used, th Transfer learning needs custom dataset and annotation in COCO-format and VOC-format is supported now. The script converts the annotation from voc, labelme or cityscape to COCO is provided in ```tools/x2coco.py```. More details please refer to [READER](READER.md). After data preparation, update the data parameters in configuration file. -1. COCO-format dataset, take [yolov3\_darknet.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/yolov3_darknet.yml#L66) for example, modify the COCODataSet in yolov3\_reader: +1. COCO-format dataset, take [yolov3\_darknet.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/yolov3_darknet.yml#L66) for example, modify the COCODataSet in yolov3\_reader: ```yml dataset: @@ -22,7 +22,7 @@ Transfer learning needs custom dataset and annotation in COCO-format and VOC-for with_background: false ``` -2. VOC-format dataset, take [yolov3\_darknet\_voc.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/yolov3_darknet_voc.yml#L67) for example, modify the VOCDataSet in the configuration: +2. VOC-format dataset, take [yolov3\_darknet\_voc.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/yolov3_darknet_voc.yml#L67) for example, modify the VOCDataSet in the configuration: ```yml dataset: @@ -52,7 +52,7 @@ python -u tools/train.py -c configs/faster_rcnn_r50_1x.yml \ The parameters which need to ignore can be specified explicitly as well and arbitrary parameter names can be added to `finetune_exclude_pretrained_params`. For this purpose, several methods can be used as follwed: -- Set `finetune_exclude_pretrained_params` in YAML configuration files. Please refer to [configure file](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/yolov3_mobilenet_v1_fruit.yml#L15) +- Set `finetune_exclude_pretrained_params` in YAML configuration files. Please refer to [configure file](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/yolov3_mobilenet_v1_fruit.yml#L15) - Set `finetune_exclude_pretrained_params` in command line. For example: ```python diff --git a/static/docs/advanced_tutorials/TRANSFER_LEARNING_cn.md b/static/docs/advanced_tutorials/TRANSFER_LEARNING_cn.md index 022ef0c96c52ac5764e26835715f459b5a61b0a6..208f9b842c57d8e16c46dd89e16036c81ef713ba 100644 --- a/static/docs/advanced_tutorials/TRANSFER_LEARNING_cn.md +++ b/static/docs/advanced_tutorials/TRANSFER_LEARNING_cn.md @@ -9,7 +9,7 @@ 迁移学习需要使用自己的数据集，目前已支持COCO和VOC的数据标注格式，在```tools/x2coco.py```中给出了voc、labelme和cityscape标注格式转换为COCO格式的脚本，具体使用方式可以参考[自定义数据源](READER.md)。数据准备完成后，在配置文件中配置数据路径，对应修改reader中的路径参数即可。 -1. COCO数据集需要修改COCODataSet中的参数，以[yolov3\_darknet.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/yolov3_darknet.yml#L66)为例，修改yolov3\_reader中的配置： +1. COCO数据集需要修改COCODataSet中的参数，以[yolov3\_darknet.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/yolov3_darknet.yml#L66)为例，修改yolov3\_reader中的配置： ```yml dataset: @@ -20,7 +20,7 @@ with_background: false ``` -2. VOC数据集需要修改VOCDataSet中的参数，以[yolov3\_darknet\_voc.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/yolov3_darknet_voc.yml#L67)为例： +2. VOC数据集需要修改VOCDataSet中的参数，以[yolov3\_darknet\_voc.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/yolov3_darknet_voc.yml#L67)为例： ```yml dataset: @@ -56,7 +56,7 @@ python -u tools/train.py -c configs/faster_rcnn_r50_1x.yml \ 可以显示的指定训练过程中忽略参数的名字，任何参数名均可加入`finetune_exclude_pretrained_params`中，为实现这一目的，可通过如下方式实现： -1. 在 YMAL 配置文件中通过设置`finetune_exclude_pretrained_params`字段。可参考[配置文件](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/yolov3_mobilenet_v1_fruit.yml#L15) +1. 在 YMAL 配置文件中通过设置`finetune_exclude_pretrained_params`字段。可参考[配置文件](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/yolov3_mobilenet_v1_fruit.yml#L15) 2. 在 train.py的启动参数中设置`finetune_exclude_pretrained_params`。例如： ```python diff --git a/static/docs/advanced_tutorials/deploy/docs/windows_vs2015_build.md b/static/docs/advanced_tutorials/deploy/docs/windows_vs2015_build.md index 2d24ff1d70a64a1fd8cfcfa30dfc2a7a0f1caeea..0d81a514236fc8977c8775713df1588423679a0b 100644 --- a/static/docs/advanced_tutorials/deploy/docs/windows_vs2015_build.md +++ b/static/docs/advanced_tutorials/deploy/docs/windows_vs2015_build.md @@ -1,6 +1,6 @@ # Windows平台使用 Visual Studio 2015 编译指南 -本文档步骤，我们同时在`Visual Studio 2015` 和 `Visual Studio 2019 Community` 两个版本进行了测试，我们推荐使用[`Visual Studio 2019`直接编译`CMake`项目](https://github.com/PaddlePaddle/PaddleDetection/blob/master/deploy/cpp/docs/windows_vs2019_build.md)。 +本文档步骤，我们同时在`Visual Studio 2015` 和 `Visual Studio 2019 Community` 两个版本进行了测试，我们推荐使用[`Visual Studio 2019`直接编译`CMake`项目](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/deploy/cpp/docs/windows_vs2019_build.md)。 ## 前置条件 diff --git a/static/docs/conf.py b/static/docs/conf.py index 7e10175f97e3e5702f17ae197f2a1695444bf707..08e62a4cfc28a881d31bc5db555b0333a186d51d 100644 --- a/static/docs/conf.py +++ b/static/docs/conf.py @@ -162,7 +162,7 @@ texinfo_documents = [ def url_resolver(url): if ".html" not in url: url = url.replace("../", "") - return "https://github.com/PaddlePaddle/PaddleDetection/tree/master" + url + return "https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static" + url else: if DEPLOY: return "http://paddledetection.readthedocs.io/" + url diff --git a/static/docs/featured_model/CONTRIB.md b/static/docs/featured_model/CONTRIB.md index f5630d32afc66f9391b1282d28e72bb16c3c0aa5..b1f0c1cf5fcd03b4c928f9d1a0549473232def45 100644 --- a/static/docs/featured_model/CONTRIB.md +++ b/static/docs/featured_model/CONTRIB.md @@ -5,8 +5,8 @@ We provide some models implemented by PaddlePaddle to detect objects in specific | Task | Algorithm | Box AP | Download | Configs | |:---------------------|:---------:|:------:| :-------------------------------------------------------------------------------------: |:------:| -| Vehicle Detection | YOLOv3 | 54.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/vehicle_yolov3_darknet.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/contrib/VehicleDetection/vehicle_yolov3_darknet.yml) | -| Pedestrian Detection | YOLOv3 | 51.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/pedestrian_yolov3_darknet.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/contrib/PedestrianDetection/pedestrian_yolov3_darknet.yml) | +| Vehicle Detection | YOLOv3 | 54.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/vehicle_yolov3_darknet.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/contrib/VehicleDetection/vehicle_yolov3_darknet.yml) | +| Pedestrian Detection | YOLOv3 | 51.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/pedestrian_yolov3_darknet.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/contrib/PedestrianDetection/pedestrian_yolov3_darknet.yml) | ## Vehicle Detection @@ -18,7 +18,7 @@ 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_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: +PaddleDetection provides users with a configuration file [yolov3_darknet.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/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_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: +PaddleDetection provides users with a configuration file [yolov3_darknet.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/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/static/docs/featured_model/CONTRIB_cn.md b/static/docs/featured_model/CONTRIB_cn.md index dbc9f19263ec8bd544e4b1454bda1a1fdb7e7d2b..5bfa00eeb1fff08f21f6645a906410521ca62fed 100644 --- a/static/docs/featured_model/CONTRIB_cn.md +++ b/static/docs/featured_model/CONTRIB_cn.md @@ -5,8 +5,8 @@ | 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://paddlemodels.bj.bcebos.com/object_detection/vehicle_yolov3_darknet.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/contrib/VehicleDetection/vehicle_yolov3_darknet.yml) | -| 行人检测 | YOLOv3 | 51.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/pedestrian_yolov3_darknet.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/contrib/PedestrianDetection/pedestrian_yolov3_darknet.yml) | +| 车辆检测 | YOLOv3 | 54.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/vehicle_yolov3_darknet.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/contrib/VehicleDetection/vehicle_yolov3_darknet.yml) | +| 行人检测 | YOLOv3 | 51.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/pedestrian_yolov3_darknet.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/contrib/PedestrianDetection/pedestrian_yolov3_darknet.yml) | ## 车辆检测（Vehicle Detection） @@ -19,7 +19,7 @@ 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/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： +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/develop/static/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_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： +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/develop/static/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/static/docs/featured_model/FACE_DETECTION.md b/static/docs/featured_model/FACE_DETECTION.md index 19db65d3f0469433e37ceda9a8ab3151fa363985..eda990a549fc0cb2e10faf598073490559018f5b 100644 --- a/static/docs/featured_model/FACE_DETECTION.md +++ b/static/docs/featured_model/FACE_DETECTION.md @@ -34,16 +34,16 @@ FaceDetection的目标是提供高效、高速的人脸检测解决方案，包 | 网络结构 | 类型 | 输入尺寸 | 图片个数/GPU | 学习率策略 | Easy Set | Medium Set | Hard Set | 下载 | 配置文件 | |:------------:|:--------:|:----:|:-------:|:-------:|:---------:|:----------:|:---------:|:--------:|:--------:| -| BlazeFace | 原始版本 | 640 | 8 | 32w | **0.915** | **0.892** | **0.797** | [模型](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_original.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/face_detection/blazeface.yml) | -| BlazeFace | Lite版本 | 640 | 8 | 32w | 0.909 | 0.885 | 0.781 | [模型](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_lite.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/face_detection/blazeface.yml) | -| BlazeFace | NAS版本 | 640 | 8 | 32w | 0.837 | 0.807 | 0.658 | [模型](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/face_detection/blazeface_nas.yml) | -| BlazeFace | NAS_V2版本 | 640 | 8 | 32W | 0.870 | 0.837 | 0.685 | [模型](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas2.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/face_detection/blazeface_nas_v2.yml) | -| FaceBoxes | 原始版本 | 640 | 8 | 32w | 0.878 | 0.851 | 0.576 | [模型](https://paddlemodels.bj.bcebos.com/object_detection/faceboxes_original.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/face_detection/faceboxes.yml) | -| FaceBoxes | Lite版本 | 640 | 8 | 32w | 0.901 | 0.875 | 0.760 | [模型](https://paddlemodels.bj.bcebos.com/object_detection/faceboxes_lite.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/face_detection/faceboxes_lite.yml) | +| BlazeFace | 原始版本 | 640 | 8 | 32w | **0.915** | **0.892** | **0.797** | [模型](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_original.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/face_detection/blazeface.yml) | +| BlazeFace | Lite版本 | 640 | 8 | 32w | 0.909 | 0.885 | 0.781 | [模型](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_lite.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/face_detection/blazeface.yml) | +| BlazeFace | NAS版本 | 640 | 8 | 32w | 0.837 | 0.807 | 0.658 | [模型](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/face_detection/blazeface_nas.yml) | +| BlazeFace | NAS_V2版本 | 640 | 8 | 32W | 0.870 | 0.837 | 0.685 | [模型](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas2.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/face_detection/blazeface_nas_v2.yml) | +| FaceBoxes | 原始版本 | 640 | 8 | 32w | 0.878 | 0.851 | 0.576 | [模型](https://paddlemodels.bj.bcebos.com/object_detection/faceboxes_original.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/face_detection/faceboxes.yml) | +| FaceBoxes | Lite版本 | 640 | 8 | 32w | 0.901 | 0.875 | 0.760 | [模型](https://paddlemodels.bj.bcebos.com/object_detection/faceboxes_lite.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/face_detection/faceboxes_lite.yml) | **注意:** - 我们使用`tools/face_eval.py`中多尺度评估策略得到`Easy/Medium/Hard Set`里的mAP。具体细节请参考[在WIDER-FACE数据集上评估](#在WIDER-FACE数据集上评估)。 -- BlazeFace-Lite的训练与测试使用 [blazeface.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/face_detection/blazeface.yml)配置文件并且设置：`lite_edition: true`。 +- BlazeFace-Lite的训练与测试使用 [blazeface.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/face_detection/blazeface.yml)配置文件并且设置：`lite_edition: true`。 #### FDDB数据集上的mAP @@ -258,7 +258,7 @@ wget https://dataset.bj.bcebos.com/wider_face/wider_face_train_bbx_lmk_gt.txt | 网络结构 | 输入尺寸 | 图片个数/GPU | 学习率策略 | Easy Set | Medium Set | Hard Set | 下载 | 配置文件 | |:------------:|:----:|:-------:|:-------:|:---------:|:----------:|:---------:|:--------:|:--------:| -| BlazeFace Keypoint | 640 | 16 | 16w | 0.852 | 0.816 | 0.662 | [模型](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_keypoint.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/face_detection/blazeface_keypoint.yml) | +| BlazeFace Keypoint | 640 | 16 | 16w | 0.852 | 0.816 | 0.662 | [模型](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_keypoint.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/face_detection/blazeface_keypoint.yml) | ![](../images/12_Group_Group_12_Group_Group_12_84.jpg) @@ -292,7 +292,7 @@ wget https://dataset.bj.bcebos.com/wider_face/wider_face_train_bbx_lmk_gt.txt **版本信息:** - 原始版本: 参考原始论文进行修改； -- Lite版本: 使用更少的网络层数和通道数，具体可参考[代码](https://github.com/PaddlePaddle/PaddleDetection/blob/master/ppdet/modeling/architectures/faceboxes.py)。 +- Lite版本: 使用更少的网络层数和通道数，具体可参考[代码](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/ppdet/modeling/architectures/faceboxes.py)。 ## 如何贡献代码 diff --git a/static/docs/featured_model/FACE_DETECTION_en.md b/static/docs/featured_model/FACE_DETECTION_en.md index a2cb4a2d4c44533641b094e06c26e17a7837a0fd..cc7b6f26a9aa0af7c31376745a5a084d161e73a3 100644 --- a/static/docs/featured_model/FACE_DETECTION_en.md +++ b/static/docs/featured_model/FACE_DETECTION_en.md @@ -38,17 +38,17 @@ optimized network structure. | Architecture | Type | Size | Img/gpu | Lr schd | Easy Set | Medium Set | Hard Set | Download | Configs | |:------------:|:--------:|:----:|:-------:|:-------:|:---------:|:----------:|:---------:|:--------:|:--------:| -| BlazeFace | Original | 640 | 8 | 32w | **0.915** | **0.892** | **0.797** | [model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_original.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/face_detection/blazeface.yml) | -| BlazeFace | Lite | 640 | 8 | 32w | 0.909 | 0.885 | 0.781 | [model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_lite.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/face_detection/blazeface.yml) | -| BlazeFace | NAS | 640 | 8 | 32w | 0.837 | 0.807 | 0.658 | [model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/face_detection/blazeface_nas.yml) | -| BlazeFace | NAS_V2 | 640 | 8 | 32W | 0.870 | 0.837 | 0.685 | [model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas2.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/face_detection/blazeface_nas_v2.yml) | -| FaceBoxes | Original | 640 | 8 | 32w | 0.878 | 0.851 | 0.576 | [model](https://paddlemodels.bj.bcebos.com/object_detection/faceboxes_original.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/face_detection/faceboxes.yml) | -| FaceBoxes | Lite | 640 | 8 | 32w | 0.901 | 0.875 | 0.760 | [model](https://paddlemodels.bj.bcebos.com/object_detection/faceboxes_lite.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/face_detection/faceboxes_lite.yml) | +| BlazeFace | Original | 640 | 8 | 32w | **0.915** | **0.892** | **0.797** | [model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_original.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/face_detection/blazeface.yml) | +| BlazeFace | Lite | 640 | 8 | 32w | 0.909 | 0.885 | 0.781 | [model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_lite.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/face_detection/blazeface.yml) | +| BlazeFace | NAS | 640 | 8 | 32w | 0.837 | 0.807 | 0.658 | [model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/face_detection/blazeface_nas.yml) | +| BlazeFace | NAS_V2 | 640 | 8 | 32W | 0.870 | 0.837 | 0.685 | [model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas2.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/face_detection/blazeface_nas_v2.yml) | +| FaceBoxes | Original | 640 | 8 | 32w | 0.878 | 0.851 | 0.576 | [model](https://paddlemodels.bj.bcebos.com/object_detection/faceboxes_original.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/face_detection/faceboxes.yml) | +| FaceBoxes | Lite | 640 | 8 | 32w | 0.901 | 0.875 | 0.760 | [model](https://paddlemodels.bj.bcebos.com/object_detection/faceboxes_lite.tar) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/face_detection/faceboxes_lite.yml) | **NOTES:** - Get mAP in `Easy/Medium/Hard Set` by multi-scale evaluation in `tools/face_eval.py`. For details can refer to [Evaluation](#Evaluate-on-the-WIDER-FACE). -- BlazeFace-Lite Training and Testing ues [blazeface.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/face_detection/blazeface.yml) +- BlazeFace-Lite Training and Testing ues [blazeface.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/face_detection/blazeface.yml) configs file and set `lite_edition: true`. #### mAP in FDDB @@ -274,7 +274,7 @@ wget https://dataset.bj.bcebos.com/wider_face/wider_face_train_bbx_lmk_gt.txt | Architecture | Size | Img/gpu | Lr schd | Easy Set | Medium Set | Hard Set | Download | Configs | |:------------:|:----:|:-------:|:-------:|:---------:|:----------:|:---------:|:--------:|:--------:| -| BlazeFace Keypoint | 640 | 16 | 16w | 0.852 | 0.816 | 0.662 | [download](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_keypoint.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/face_detection/blazeface_keypoint.yml) | +| BlazeFace Keypoint | 640 | 16 | 16w | 0.852 | 0.816 | 0.662 | [download](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_keypoint.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/face_detection/blazeface_keypoint.yml) | ![](../images/12_Group_Group_12_Group_Group_12_84.jpg) diff --git a/static/docs/featured_model/LARGE_SCALE_DET_MODEL.md b/static/docs/featured_model/LARGE_SCALE_DET_MODEL.md index 47ce28289bddb8bd1e6f196eb9b1c42e5fe1b5cb..7b88cd11cd0ef96b8935c8d4570fad7889dca820 100644 --- a/static/docs/featured_model/LARGE_SCALE_DET_MODEL.md +++ b/static/docs/featured_model/LARGE_SCALE_DET_MODEL.md @@ -20,6 +20,6 @@ | 骨架网络 | 网络类型 | 下载 | 配置文件 | | :---------------| :---------------| :---------------| :--------------- -| ResNet50-vd-FPN-Dcnv2 | Cascade Faster | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_vd_fpn_gen_server_side.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/rcnn_enhance/generic/cascade_rcnn_dcn_r50_vd_fpn_gen_server_side.yml) | -| ResNet101-vd-FPN-Dcnv2 | Cascade Faster | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r101_vd_fpn_gen_server_side.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/rcnn_enhance/generic/cascade_rcnn_dcn_r101_vd_fpn_gen_server_side.yml) | -| CBResNet101-vd-FPN | Cascade Faster | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cbr101_vd_fpn_server_side.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/rcnn_enhance/generic/cascade_rcnn_cbr101_vd_fpn_server_side.yml) | +| ResNet50-vd-FPN-Dcnv2 | Cascade Faster | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_vd_fpn_gen_server_side.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/rcnn_enhance/generic/cascade_rcnn_dcn_r50_vd_fpn_gen_server_side.yml) | +| ResNet101-vd-FPN-Dcnv2 | Cascade Faster | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r101_vd_fpn_gen_server_side.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/rcnn_enhance/generic/cascade_rcnn_dcn_r101_vd_fpn_gen_server_side.yml) | +| CBResNet101-vd-FPN | Cascade Faster | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cbr101_vd_fpn_server_side.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/rcnn_enhance/generic/cascade_rcnn_cbr101_vd_fpn_server_side.yml) | diff --git a/static/docs/featured_model/LARGE_SCALE_DET_MODEL_en.md b/static/docs/featured_model/LARGE_SCALE_DET_MODEL_en.md index 463789cd2545f81d9a9beac47b0b51fa7560648a..1d06662d344c28212b009f271249e8f4044b0b83 100644 --- a/static/docs/featured_model/LARGE_SCALE_DET_MODEL_en.md +++ b/static/docs/featured_model/LARGE_SCALE_DET_MODEL_en.md @@ -18,6 +18,6 @@ There are relatively not enough categories in the above dataset (compared to 100 | Backbone | Type | Download | Configs | | :---------------| :---------------| :---------------| :--------------- -| ResNet50-vd-FPN-Dcnv2 | Cascade Faster | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_vd_fpn_gen_server_side.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/rcnn_enhance/generic/cascade_rcnn_dcn_r50_vd_fpn_gen_server_side.yml) | -| ResNet101-vd-FPN-Dcnv2 | Cascade Faster | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r101_vd_fpn_gen_server_side.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/rcnn_enhance/generic/cascade_rcnn_dcn_r101_vd_fpn_gen_server_side.yml) | -| CBResNet101-vd-FPN | Cascade Faster | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cbr101_vd_fpn_server_side.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/rcnn_enhance/generic/cascade_rcnn_cbr101_vd_fpn_server_side.yml) | +| ResNet50-vd-FPN-Dcnv2 | Cascade Faster | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_vd_fpn_gen_server_side.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/rcnn_enhance/generic/cascade_rcnn_dcn_r50_vd_fpn_gen_server_side.yml) | +| ResNet101-vd-FPN-Dcnv2 | Cascade Faster | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r101_vd_fpn_gen_server_side.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/rcnn_enhance/generic/cascade_rcnn_dcn_r101_vd_fpn_gen_server_side.yml) | +| CBResNet101-vd-FPN | Cascade Faster | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cbr101_vd_fpn_server_side.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/rcnn_enhance/generic/cascade_rcnn_cbr101_vd_fpn_server_side.yml) | diff --git a/static/docs/featured_model/YOLOv3_ENHANCEMENT.md b/static/docs/featured_model/YOLOv3_ENHANCEMENT.md index af09e6da37390e5753ba4f3c72dc170c7eb468ff..9824a65cc7b559d2a01c3f104a0c70c8b6131a63 100644 --- a/static/docs/featured_model/YOLOv3_ENHANCEMENT.md +++ b/static/docs/featured_model/YOLOv3_ENHANCEMENT.md @@ -43,12 +43,12 @@ python tools/train.py -c configs/dcn/yolov3_r50vd_dcn_db_iouloss_obj365_pretrain | 模型 | 预训练模型 | 验证集 mAP | V100 python 预测速度（FPS）[1](#1) | V100 paddle预测库速度（ms/image）[2](#2) | P4 paddle预测库速度(ms/image) [2](#2) | 下载 | 配置文件 | | :--------------------------------------: | :----------------------------------------------------------: | :--------: | :--------: | :------------------------------------: | :----------------------------------------------------------: | :--------: | :--------: | -| YOLOv3 DarkNet | [DarkNet pretrain](https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_pretrained.tar) | 38.9 | 48.55 | 原生：19.63
tensorRT-FP32: 18.01
tensorRT-FP16: 11.47 | 原生：54.10
tensorRT-FP32: 47.44 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov3_darknet.yml) | -| YOLOv3 ResNet50_vd DCN | [ImageNet pretrain](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar) | 39.1 | 50.80 | 原生：17.04
tensorRT-FP32: 16.28
tensorRT-FP16: 11.16 | 原生：40.01
tensorRT-FP32: 36.66 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_imagenet.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/yolov3_r50vd_dcn.yml) | -| YOLOv3 ResNet50_vd DCN | [Object365 pretrain](https://paddlemodels.bj.bcebos.com/object_detection/ResNet50_vd_dcn_db_obj365_pretrained.tar) | 42.5 | 50.41 | 原生：16.76
tensorRT-FP32: 16.04
tensorRT-FP16: 10.70 | 原生：39.64
tensorRT-FP32: 35.93 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_obj365_v2.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/yolov3_r50vd_dcn_obj365_pretrained_coco.yml) | -| YOLOv3 ResNet50_vd DCN DropBlock | [Object365 pretrain](https://paddlemodels.bj.bcebos.com/object_detection/ResNet50_vd_dcn_db_obj365_pretrained.tar) | 42.8 | 49.97 | 原生：16.55
tensorRT-FP32: 16.07
tensorRT-FP16: 10.69 | 原生：39.72
tensorRT-FP32: 35.98 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_obj365_dropblock.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/yolov3_r50vd_dcn_db_obj365_pretrained_coco.yml) | -| YOLOv3 ResNet50_vd DCN DropBlock IoULoss | [Object365 pretrain](https://paddlemodels.bj.bcebos.com/object_detection/ResNet50_vd_dcn_db_obj365_pretrained.tar) | 43.2 | 49.91 | 原生：16.46
tensorRT-FP32: 15.83
tensorRT-FP16: 10.80 | 原生：39.58
tensorRT-FP32: 35.61 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_obj365_dropblock_iouloss.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/yolov3_r50vd_dcn_db_iouloss_obj365_pretrained_coco.yml) | -| YOLOv3 ResNet50_vd DCN DropBlock IoU-Aware | [Object365 pretrain](https://paddlemodels.bj.bcebos.com/object_detection/ResNet50_vd_dcn_db_obj365_pretrained.tar) | 43.6 | 48.19 | 原生：17.74
tensorRT-FP32: 16.73
tensorRT-FP16: 11.74 | 原生：41.39
tensorRT-FP32: 37.75 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_db_iouaware_obj365_pretrained_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/yolov3_r50vd_dcn_db_iouaware_obj365_pretrained_coco.yml) | +| YOLOv3 DarkNet | [DarkNet pretrain](https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_pretrained.tar) | 38.9 | 48.55 | 原生：19.63
tensorRT-FP32: 18.01
tensorRT-FP16: 11.47 | 原生：54.10
tensorRT-FP32: 47.44 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/yolov3_darknet.yml) | +| YOLOv3 ResNet50_vd DCN | [ImageNet pretrain](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar) | 39.1 | 50.80 | 原生：17.04
tensorRT-FP32: 16.28
tensorRT-FP16: 11.16 | 原生：40.01
tensorRT-FP32: 36.66 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_imagenet.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/yolov3_r50vd_dcn.yml) | +| YOLOv3 ResNet50_vd DCN | [Object365 pretrain](https://paddlemodels.bj.bcebos.com/object_detection/ResNet50_vd_dcn_db_obj365_pretrained.tar) | 42.5 | 50.41 | 原生：16.76
tensorRT-FP32: 16.04
tensorRT-FP16: 10.70 | 原生：39.64
tensorRT-FP32: 35.93 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_obj365_v2.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/yolov3_r50vd_dcn_obj365_pretrained_coco.yml) | +| YOLOv3 ResNet50_vd DCN DropBlock | [Object365 pretrain](https://paddlemodels.bj.bcebos.com/object_detection/ResNet50_vd_dcn_db_obj365_pretrained.tar) | 42.8 | 49.97 | 原生：16.55
tensorRT-FP32: 16.07
tensorRT-FP16: 10.69 | 原生：39.72
tensorRT-FP32: 35.98 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_obj365_dropblock.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/yolov3_r50vd_dcn_db_obj365_pretrained_coco.yml) | +| YOLOv3 ResNet50_vd DCN DropBlock IoULoss | [Object365 pretrain](https://paddlemodels.bj.bcebos.com/object_detection/ResNet50_vd_dcn_db_obj365_pretrained.tar) | 43.2 | 49.91 | 原生：16.46
tensorRT-FP32: 15.83
tensorRT-FP16: 10.80 | 原生：39.58
tensorRT-FP32: 35.61 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_obj365_dropblock_iouloss.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/yolov3_r50vd_dcn_db_iouloss_obj365_pretrained_coco.yml) | +| YOLOv3 ResNet50_vd DCN DropBlock IoU-Aware | [Object365 pretrain](https://paddlemodels.bj.bcebos.com/object_detection/ResNet50_vd_dcn_db_obj365_pretrained.tar) | 43.6 | 48.19 | 原生：17.74
tensorRT-FP32: 16.73
tensorRT-FP16: 11.74 | 原生：41.39
tensorRT-FP32: 37.75 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_db_iouaware_obj365_pretrained_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/yolov3_r50vd_dcn_db_iouaware_obj365_pretrained_coco.yml) | [1]V100 python 预测速度是在一张Tesla V100的GPU上通过```tools/eval.py```测试所有验证集得到，单位是fps(图片数/秒), cuDNN版本是7.5，包括数据加载、网络前向执行和后处理, batch size是1。 diff --git a/static/docs/featured_model/champion_model/CACascadeRCNN.md b/static/docs/featured_model/champion_model/CACascadeRCNN.md index f1f19dc8b2a95a928380cec0001d98c1c724e58c..3813499e32f618aba32f12b284c7aafe74f82996 100644 --- a/static/docs/featured_model/champion_model/CACascadeRCNN.md +++ b/static/docs/featured_model/champion_model/CACascadeRCNN.md @@ -38,7 +38,7 @@ python tools/train.py -c configs/obj365/cascade_rcnn_dcnv2_se154_vd_fpn_gn_cas.y | 模型 | 验证集 mAP | 下载链接 | 配置文件 | | :-----------------: | :--------: | :----------------------------------------------------------: | :--------: | -| CACascadeRCNN SE154 | 31.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcnv2_se154_vd_fpn_gn_cas_obj365.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/obj365/cascade_rcnn_dcnv2_se154_vd_fpn_gn_cas.yml) | +| CACascadeRCNN SE154 | 31.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcnv2_se154_vd_fpn_gn_cas_obj365.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/obj365/cascade_rcnn_dcnv2_se154_vd_fpn_gn_cas.yml) | ## 模型效果 diff --git a/static/docs/featured_model/champion_model/OIDV5_BASELINE_MODEL.md b/static/docs/featured_model/champion_model/OIDV5_BASELINE_MODEL.md index a6d24bb7c52c1e9b104cd7afb34cbd62c7e935f3..c1c2f945461f2c13a2a390f8a60e3af5e3a58966 100644 --- a/static/docs/featured_model/champion_model/OIDV5_BASELINE_MODEL.md +++ b/static/docs/featured_model/champion_model/OIDV5_BASELINE_MODEL.md @@ -19,15 +19,15 @@ OIDV5模型训练结果如下。 | 模型结构 | Public/Private Score | 下载链接 | 配置文件 | | :-----------------: | :--------: | :----------------------------------------------------------: | :--------: | -| CascadeCARCNN-FPN-Dcnv2-Nonlocal ResNet200-vd | 0.62690/0.59459 | [模型](https://paddlemodels.bj.bcebos.com/object_detection/oidv5_cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/oidv5/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.yml) | +| CascadeCARCNN-FPN-Dcnv2-Nonlocal ResNet200-vd | 0.62690/0.59459 | [模型](https://paddlemodels.bj.bcebos.com/object_detection/oidv5_cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/oidv5/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.yml) | 此外，为验证模型的性能，PaddleDetection基于该模型结构，也训练了针对COCO2017和Objects365 Dataset的模型，模型和验证集指标如下表。 | 模型结构 | 数据集 | 验证集mAP | 下载链接 | 配置文件 | | :-----------------: | :--------: | :--------: | :----------------------------------------------------------: | :--------: | -| CascadeCARCNN-FPN-Dcnv2-Nonlocal ResNet200-vd | COCO2017 | 51.7% | [模型](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/dcn/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.yml) | -| CascadeCARCNN-FPN-Dcnv2-Nonlocal ResNet200-vd | Objects365 | 34.5% | [模型](https://paddlemodels.bj.bcebos.com/object_detection/obj365_cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/obj365/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.yml) | +| CascadeCARCNN-FPN-Dcnv2-Nonlocal ResNet200-vd | COCO2017 | 51.7% | [模型](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/dcn/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.yml) | +| CascadeCARCNN-FPN-Dcnv2-Nonlocal ResNet200-vd | Objects365 | 34.5% | [模型](https://paddlemodels.bj.bcebos.com/object_detection/obj365_cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs/obj365/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.yml) | COCO和Objects365 Dataset数据格式相同，目前只支持预测和评估。 diff --git a/static/docs/tutorials/INSTALL.md b/static/docs/tutorials/INSTALL.md index 573434ed81881d94c941642b878d0eafb0ea2312..5e9e304ee3e27e1e85612d07c8c877a3a063a489 100644 --- a/static/docs/tutorials/INSTALL.md +++ b/static/docs/tutorials/INSTALL.md @@ -106,7 +106,7 @@ git clone https://github.com/PaddlePaddle/PaddleDetection.git **Install Python dependencies:** -Required python packages are specified in [requirements.txt](https://github.com/PaddlePaddle/PaddleDetection/blob/master/requirements.txt), and can be installed with: +Required python packages are specified in [requirements.txt](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/requirements.txt), and can be installed with: ``` pip install -r requirements.txt diff --git a/static/slim/README.md b/static/slim/README.md index c60ebe61e253431d1e90e963028def23e4e08efe..cbd5c5521570fd7363bc371b03acf9b46728049e 100644 --- a/static/slim/README.md +++ b/static/slim/README.md @@ -81,7 +81,7 @@ ### 蒸馏通道剪裁模型 -可通过高精度模型蒸馏通道剪裁后模型的方式，训练方法及相关示例见[蒸馏通道剪裁模型](https://github.com/PaddlePaddle/PaddleDetection/blob/master/slim/extensions/distill_pruned_model/distill_pruned_model_demo.ipynb)。 +可通过高精度模型蒸馏通道剪裁后模型的方式，训练方法及相关示例见[蒸馏通道剪裁模型](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/slim/extensions/distill_pruned_model/distill_pruned_model_demo.ipynb)。 COCO数据集上蒸馏通道剪裁模型库如下。 diff --git a/static/slim/distillation/README.md b/static/slim/distillation/README.md index b984b4c724023d33b6d8848b567e9911f00ae88b..58345c25e664da9b07aeaade957ec26c54d98787 100644 --- a/static/slim/distillation/README.md +++ b/static/slim/distillation/README.md @@ -10,7 +10,7 @@ - [检测库的常规训练方法](https://github.com/PaddlePaddle/PaddleDetection) - [PaddleSlim蒸馏API文档](https://paddlepaddle.github.io/PaddleSlim/api/single_distiller_api/) -已发布蒸馏模型见[压缩模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/master/slim/README.md) +已发布蒸馏模型见[压缩模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/slim/README.md) ## 安装PaddleSlim 可按照[PaddleSlim使用文档](https://paddlepaddle.github.io/PaddleSlim/)中的步骤安装PaddleSlim @@ -89,7 +89,7 @@ yolo_output_names = [ ## 训练 -根据[PaddleDetection/tools/train.py](https://github.com/PaddlePaddle/PaddleDetection/blob/master/tools/train.py)编写压缩脚本`distill.py`。 +根据[PaddleDetection/tools/train.py](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/tools/train.py)编写压缩脚本`distill.py`。 在该脚本中定义了teacher_model和student_model，用teacher_model的输出指导student_model的训练 ### 执行示例 @@ -178,7 +178,7 @@ python -u slim/distillation/distill.py \ ## 评估 -每隔`snap_shot_iter`步后会保存一个checkpoint模型可以用于评估，使用PaddleDetection目录下[tools/eval.py](https://github.com/PaddlePaddle/PaddleDetection/blob/master/tools/eval.py)评估脚本，并指定`weights`为训练得到的模型路径 +每隔`snap_shot_iter`步后会保存一个checkpoint模型可以用于评估，使用PaddleDetection目录下[tools/eval.py](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/tools/eval.py)评估脚本，并指定`weights`为训练得到的模型路径 运行命令为： ```bash @@ -197,7 +197,7 @@ python -u tools/eval.py -c configs/yolov3_mobilenet_v1.yml \ ## 预测 -每隔`snap_shot_iter`步后保存的checkpoint模型也可以用于预测，使用PaddleDetection目录下[tools/infer.py](https://github.com/PaddlePaddle/PaddleDetection/blob/master/tools/infer.py)评估脚本，并指定`weights`为训练得到的模型路径 +每隔`snap_shot_iter`步后保存的checkpoint模型也可以用于预测，使用PaddleDetection目录下[tools/infer.py](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/tools/infer.py)评估脚本，并指定`weights`为训练得到的模型路径 ### Python预测 diff --git a/static/slim/nas/README.md b/static/slim/nas/README.md index f571979f08cfaf2874d19fda856c9b4aa98d24fe..be0fb9ecf8be7ae0ed8dcb05b2b37e1583d284cd 100644 --- a/static/slim/nas/README.md +++ b/static/slim/nas/README.md @@ -41,7 +41,7 @@ double_blaze_filters = [ [self.double_filter_num[tokens[2]], self.mid_filter_num[tokens[6]], self.double_filter_num[tokens[3]], 2], [self.double_filter_num[tokens[3]], self.mid_filter_num[tokens[7]], self.double_filter_num[tokens[3]]]] ``` -blaze_filters与double_blaze_filters字段请参考[blazenet.py](https://github.com/PaddlePaddle/PaddleDetection/blob/master/ppdet/modeling/backbones/blazenet.py)中定义。 +blaze_filters与double_blaze_filters字段请参考[blazenet.py](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/ppdet/modeling/backbones/blazenet.py)中定义。 初始化tokens为：[2, 1, 3, 8, 2, 1, 2, 1, 1]。 @@ -84,10 +84,10 @@ BlazeNet: - （2）训练、评估与预测： -启动完整的训练评估实验，可参考PaddleDetection的[训练、评估与预测流程](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/tutorials/GETTING_STARTED_cn.md) +启动完整的训练评估实验，可参考PaddleDetection的[训练、评估与预测流程](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/docs/tutorials/GETTING_STARTED_cn.md) ## 实验结果 -请参考[人脸检测模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/featured_model/FACE_DETECTION.md)中BlazeFace-NAS的实验结果。 +请参考[人脸检测模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/docs/featured_model/FACE_DETECTION.md)中BlazeFace-NAS的实验结果。 ## FAQ - 运行报错：`socket.error: [Errno 98] Address already in use`。 diff --git a/static/slim/prune/README.md b/static/slim/prune/README.md index f33954a99817d950547f381349cc77801f81c2bb..bcddfd77c7caff8cda986ecdf0fc60f8532469b6 100644 --- a/static/slim/prune/README.md +++ b/static/slim/prune/README.md @@ -1,6 +1,6 @@ # 卷积层通道剪裁教程 -请确保已正确[安装PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/tutorials/INSTALL_cn.md)及其依赖。 +请确保已正确[安装PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/docs/tutorials/INSTALL_cn.md)及其依赖。 该文档介绍如何使用[PaddleSlim](https://paddlepaddle.github.io/PaddleSlim)的卷积通道剪裁接口对检测库中的模型的卷积层的通道数进行剪裁。 @@ -8,15 +8,15 @@ 该教程中所示操作，如无特殊说明，均在`PaddleDetection/`路径下执行。 -已发布裁剪模型见[压缩模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/master/slim/README.md) +已发布裁剪模型见[压缩模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/slim/README.md) ## 1. 数据准备 -请参考检测库[数据下载](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/tutorials/INSTALL_cn.md)文档准备数据。 +请参考检测库[数据下载](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/docs/tutorials/INSTALL_cn.md)文档准备数据。 ## 2. 模型选择 -通过`-c`选项指定待裁剪模型的配置文件的相对路径，更多可选配置文件请参考: [检测库配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs) +通过`-c`选项指定待裁剪模型的配置文件的相对路径，更多可选配置文件请参考: [检测库配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/static/configs) 对于剪裁任务，原模型的权重不一定对剪裁后的模型训练的重训练有贡献，所以加载原模型的权重不是必需的步骤。 @@ -32,7 +32,7 @@ -o weights=output/yolov3_mobilenet_v1_voc/model_final ``` -官方已发布的模型请参考: [模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/MODEL_ZOO_cn.md) +官方已发布的模型请参考: [模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/docs/MODEL_ZOO_cn.md) ## 3. 确定待分析参数 @@ -49,7 +49,7 @@ python slim/prune/prune.py \ ## 4. 分析待剪裁参数敏感度 -可通过敏感度分析脚本分析待剪裁参数敏感度得到合适的剪裁率，敏感度分析工具见[敏感度分析](https://github.com/PaddlePaddle/PaddleDetection/blob/master/slim/sensitive/README.md)。 +可通过敏感度分析脚本分析待剪裁参数敏感度得到合适的剪裁率，敏感度分析工具见[敏感度分析](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/slim/sensitive/README.md)。 ## 5. 启动剪裁任务 @@ -97,16 +97,16 @@ python slim/prune/export_model.py \ **当前PaddleSlim的剪裁功能不支持剪裁循环体或条件判断语句块内的卷积层，请避免剪裁循环和判断语句块前的一个卷积和语句块内部的卷积。** -对于[faster_rcnn_r50](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/faster_rcnn_r50_1x.yml)或[mask_rcnn_r50](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/mask_rcnn_r50_1x.yml)网络，请剪裁卷积`res4f_branch2c`之前的卷积。 +对于[faster_rcnn_r50](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/faster_rcnn_r50_1x.yml)或[mask_rcnn_r50](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/mask_rcnn_r50_1x.yml)网络，请剪裁卷积`res4f_branch2c`之前的卷积。 -对[faster_rcnn_r50](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/faster_rcnn_r50_1x.yml)剪裁示例如下： +对[faster_rcnn_r50](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/faster_rcnn_r50_1x.yml)剪裁示例如下： ``` # demo for faster_rcnn_r50 python slim/prune/prune.py -c ./configs/faster_rcnn_r50_1x.yml --pruned_params "res4f_branch2b_weights,res4f_branch2a_weights" --pruned_ratios="0.3,0.4" --eval ``` -对[mask_rcnn_r50](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/mask_rcnn_r50_1x.yml)剪裁示例如下： +对[mask_rcnn_r50](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs/mask_rcnn_r50_1x.yml)剪裁示例如下： ``` # demo for mask_rcnn_r50 diff --git a/static/slim/quantization/README.md b/static/slim/quantization/README.md index 2d00f7e38129c108a94a60fa18fd9d131c042905..d1cfcf9b162697970548724542ab183bd0bf7934 100644 --- a/static/slim/quantization/README.md +++ b/static/slim/quantization/README.md @@ -19,7 +19,7 @@ ## 训练 -根据 [tools/train.py](https://github.com/PaddlePaddle/PaddleDetection/blob/master/tools/train.py) 编写压缩脚本train.py。脚本中量化的步骤如下。 +根据 [tools/train.py](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/tools/train.py) 编写压缩脚本train.py。脚本中量化的步骤如下。 ### 定义量化配置 config = { diff --git a/static/slim/sensitive/README.md b/static/slim/sensitive/README.md index e6a0795f37bd5dca9b2e33d9b5fdfb9b1dc930af..e7bade141154241fb5a0e3f8c0da30925892aec8 100644 --- a/static/slim/sensitive/README.md +++ b/static/slim/sensitive/README.md @@ -1,6 +1,6 @@ # 卷积层敏感度分析教程 -请确保已正确[安装PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/tutorials/INSTALL_cn.md)及其依赖。 +请确保已正确[安装PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/docs/tutorials/INSTALL_cn.md)及其依赖。 该文档介绍如何使用[PaddleSlim](https://paddlepaddle.github.io/PaddleSlim)的敏感度分析接口对检测库中的模型的卷积层进行敏感度分析。 @@ -10,11 +10,11 @@ ## 数据准备 -请参考检测库[数据模块](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/tutorials/INSTALL_cn.md)文档准备数据。 +请参考检测库[数据模块](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/docs/tutorials/INSTALL_cn.md)文档准备数据。 ## 模型选择 -通过`-c`选项指定待分析模型的配置文件的相对路径，更多可选配置文件请参考: [检测库配置文件](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs) +通过`-c`选项指定待分析模型的配置文件的相对路径，更多可选配置文件请参考: [检测库配置文件](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/configs) 通过`-o weights`指定模型的权重，可以指定url或本地文件系统的路径。如下所示： @@ -28,7 +28,7 @@ -o weights=output/yolov3_mobilenet_v1_voc/model_final ``` -官方已发布的模型请参考: [模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/MODEL_ZOO_cn.md) +官方已发布的模型请参考: [模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/docs/MODEL_ZOO_cn.md) ## 确定待分析参数