diff --git a/configs/centernet/README.md b/configs/centernet/README.md index b7fffff4f48b133035f74ebc4bed18a2083b4946..6dd52cd32608d6e76f08e50bbda8f3c2f4190418 100644 --- a/configs/centernet/README.md +++ b/configs/centernet/README.md @@ -18,12 +18,13 @@ English | [简体中文](README_cn.md) | backbone | input shape | mAP | FPS | download | config | | :--------------| :------- | :----: | :------: | :----: |:-----: | | DLA-34(paper) | 512x512 | 37.4 | - | - | - | -| DLA-34 | 512x512 | 37.6 | - | [model](https://bj.bcebos.com/v1/paddledet/models/centernet_dla34_140e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/centernet/centernet_dla34_140e_coco.yml) | -| ResNet50 + DLAUp | 512x512 | 38.9 | - | [model](https://bj.bcebos.com/v1/paddledet/models/centernet_r50_140e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/centernet/centernet_r50_140e_coco.yml) | -| MobileNetV1_1x + DLAUp | 512x512 | 28.2 | - | [model](https://paddledet.bj.bcebos.com/models/centernet_mbv1_x1_0_140e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/centernet/centernet_mbv1_1x_140e_coco.yml) | -| MobileNetV3_small_x1_0 + DLAUp | 512x512 | 17 | - | [model](https://paddledet.bj.bcebos.com/models/centernet_mbv3_small_1x_140e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/centernet/centernet_mbv3_small_1x_140e_coco.yml) | -| MobileNetV3_large_x1_0 + DLAUp | 512x512 | 27.1 | - | [model](https://paddledet.bj.bcebos.com/models/centernet_mbv3_large_x1_0_140e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/centernet/centernet_mbv3_large_1x_140e_coco.yml) | -| ShuffleNetV2_x1_0 + DLAUp | 512x512 | 23.8 | - | [model](https://paddledet.bj.bcebos.com/models/centernet_shufflenetv2_1x_140e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/centernet/centernet_shufflenetv2_1x_140e_coco.yml) | +| DLA-34 | 512x512 | 37.6 | - | [model](https://bj.bcebos.com/v1/paddledet/models/centernet_dla34_140e_coco.pdparams) | [config](./centernet_dla34_140e_coco.yml) | +| ResNet50 + DLAUp | 512x512 | 38.9 | - | [model](https://bj.bcebos.com/v1/paddledet/models/centernet_r50_140e_coco.pdparams) | [config](./centernet_r50_140e_coco.yml) | +| MobileNetV1 + DLAUp | 512x512 | 28.2 | - | [model](https://bj.bcebos.com/v1/paddledet/models/centernet_mbv1_140e_coco.pdparams) | [config](./centernet_mbv1_140e_coco.yml) | +| MobileNetV3_small + DLAUp | 512x512 | 17 | - | [model](https://bj.bcebos.com/v1/paddledet/models/centernet_mbv3_small_140e_coco.pdparams) | [config](./centernet_mbv3_small_140e_coco.yml) | +| MobileNetV3_large + DLAUp | 512x512 | 27.1 | - | [model](https://bj.bcebos.com/v1/paddledet/models/centernet_mbv3_large_140e_coco.pdparams) | [config](./centernet_mbv3_large_140e_coco.yml) | +| ShuffleNetV2 + DLAUp | 512x512 | 23.8 | - | [model](https://bj.bcebos.com/v1/paddledet/models/centernet_shufflenetv2_140e_coco.pdparams) | [config](./centernet_shufflenetv2_140e_coco.yml) | + ## Citations ``` diff --git a/configs/centernet/README_cn.md b/configs/centernet/README_cn.md index 2f0dfd1771bfb436b193a8687f7df26d2cd7840b..d78cd40e3d3d8751422d3d6bde078ff21d08223d 100644 --- a/configs/centernet/README_cn.md +++ b/configs/centernet/README_cn.md @@ -18,12 +18,12 @@ | 骨干网络 | 输入尺寸 | mAP | FPS | 下载链接 | 配置文件 | | :--------------| :------- | :----: | :------: | :----: |:-----: | | DLA-34(paper) | 512x512 | 37.4 | - | - | - | -| DLA-34 | 512x512 | 37.6 | - | [下载链接](https://bj.bcebos.com/v1/paddledet/models/centernet_dla34_140e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/centernet/centernet_dla34_140e_coco.yml) | -| ResNet50 + DLAUp | 512x512 | 38.9 | - | [下载链接](https://bj.bcebos.com/v1/paddledet/models/centernet_r50_140e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/centernet/centernet_r50_140e_coco.yml) | -| MobileNetV1_1x + DLAUp | 512x512 | 28.2 | - | [下载链接](https://paddledet.bj.bcebos.com/models/centernet_mbv1_x1_0_140e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/centernet/centernet_mbv1_1x_140e_coco.yml) | -| MobileNetV3_small_x1_0 + DLAUp | 512x512 | 17 | - | [下载链接](https://paddledet.bj.bcebos.com/models/centernet_mbv3_small_1x_140e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/centernet/centernet_mbv3_small_1x_140e_coco.yml) | -| MobileNetV3_large_x1_0 + DLAUp | 512x512 | 27.1 | - | [下载链接](https://paddledet.bj.bcebos.com/models/centernet_mbv3_large_x1_0_140e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/centernet/centernet_mbv3_large_1x_140e_coco.yml) | -| ShuffleNetV2_x1_0 + DLAUp | 512x512 | 23.8 | - | [下载链接](https://paddledet.bj.bcebos.com/models/centernet_shufflenetv2_1x_140e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/centernet/centernet_shufflenetv2_1x_140e_coco.yml) | +| DLA-34 | 512x512 | 37.6 | - | [下载链接](https://bj.bcebos.com/v1/paddledet/models/centernet_dla34_140e_coco.pdparams) | [配置文件](./centernet_dla34_140e_coco.yml) | +| ResNet50 + DLAUp | 512x512 | 38.9 | - | [下载链接](https://bj.bcebos.com/v1/paddledet/models/centernet_r50_140e_coco.pdparams) | [配置文件](./centernet_r50_140e_coco.yml) | +| MobileNetV1 + DLAUp | 512x512 | 28.2 | - | [下载链接](https://bj.bcebos.com/v1/paddledet/models/centernet_mbv1_140e_coco.pdparams) | [配置文件](./centernet_mbv1_140e_coco.yml) | +| MobileNetV3_small + DLAUp | 512x512 | 17 | - | [下载链接](https://bj.bcebos.com/v1/paddledet/models/centernet_mbv3_small_140e_coco.pdparams) | [配置文件](./centernet_mbv3_small_140e_coco.yml) | +| MobileNetV3_large + DLAUp | 512x512 | 27.1 | - | [下载链接](https://bj.bcebos.com/v1/paddledet/models/centernet_mbv3_large_140e_coco.pdparams) | [配置文件](./centernet_mbv3_large_140e_coco.yml) | +| ShuffleNetV2 + DLAUp | 512x512 | 23.8 | - | [下载链接](https://bj.bcebos.com/v1/paddledet/models/centernet_shufflenetv2_140e_coco.pdparams) | [配置文件](./centernet_shufflenetv2_140e_coco.yml) | ## 引用 ``` diff --git a/configs/centernet/centernet_mbv1_1x_140e_coco.yml b/configs/centernet/centernet_mbv1_140e_coco.yml similarity index 84% rename from configs/centernet/centernet_mbv1_1x_140e_coco.yml rename to configs/centernet/centernet_mbv1_140e_coco.yml index d5878106739c90ff92d5451179cbdff7ab14ce5a..48429a1dd9ced07b4e906304a199a8e2193e235d 100644 --- a/configs/centernet/centernet_mbv1_1x_140e_coco.yml +++ b/configs/centernet/centernet_mbv1_140e_coco.yml @@ -3,7 +3,7 @@ _BASE_: [ ] pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/MobileNetV1_pretrained.pdparams -weights: output/centernet_mbv1_1x_140e_coco/model_final +weights: output/centernet_mbv1_140e_coco/model_final CenterNet: backbone: MobileNet @@ -18,4 +18,4 @@ MobileNet: feature_maps: [3, 5, 11, 13] TrainReader: - batch_size: 32 \ No newline at end of file + batch_size: 32 diff --git a/configs/centernet/centernet_mbv3_large_1x_140e_coco.yml b/configs/centernet/centernet_mbv3_large_140e_coco.yml similarity index 84% rename from configs/centernet/centernet_mbv3_large_1x_140e_coco.yml rename to configs/centernet/centernet_mbv3_large_140e_coco.yml index 2852b6fb6cc3b4ec5712953966d4489432f07ef0..57830a9b5ab3c4124138a1283f964ae62fa2c00e 100644 --- a/configs/centernet/centernet_mbv3_large_1x_140e_coco.yml +++ b/configs/centernet/centernet_mbv3_large_140e_coco.yml @@ -3,7 +3,7 @@ _BASE_: [ ] pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/MobileNetV3_large_x1_0_ssld_pretrained.pdparams -weights: output/centernet_mbv3_large_1x_140e_coco/model_final +weights: output/centernet_mbv3_large_140e_coco/model_final CenterNet: backbone: MobileNetV3 @@ -19,4 +19,4 @@ MobileNetV3: feature_maps: [4, 7, 13, 16] TrainReader: - batch_size: 32 \ No newline at end of file + batch_size: 32 diff --git a/configs/centernet/centernet_mbv3_small_1x_140e_coco.yml b/configs/centernet/centernet_mbv3_small_140e_coco.yml similarity index 89% rename from configs/centernet/centernet_mbv3_small_1x_140e_coco.yml rename to configs/centernet/centernet_mbv3_small_140e_coco.yml index 211814cfabc811b32918efbfd232b53497b22a0e..de73f1b2f4023ecb9bfee96436403192b7f6d80f 100644 --- a/configs/centernet/centernet_mbv3_small_1x_140e_coco.yml +++ b/configs/centernet/centernet_mbv3_small_140e_coco.yml @@ -3,7 +3,7 @@ _BASE_: [ ] pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/MobileNetV3_small_x1_0_ssld_pretrained.pdparams -weights: output/centernet_mbv3_small_1x_140e_coco/model_final +weights: output/centernet_mbv3_small_140e_coco/model_final CenterNet: backbone: MobileNetV3 @@ -24,6 +24,5 @@ CenterNetDLAFPN: down_ratio: 8 dcn_v2: False - TrainReader: batch_size: 32 diff --git a/configs/centernet/centernet_shufflenetv2_1x_140e_coco.yml b/configs/centernet/centernet_shufflenetv2_140e_coco.yml similarity index 89% rename from configs/centernet/centernet_shufflenetv2_1x_140e_coco.yml rename to configs/centernet/centernet_shufflenetv2_140e_coco.yml index 9362ccdc482ad76b0c8394b6f5e4d09006c3fa44..9ccdae16400c77c0c7f2775db531e4687379f545 100644 --- a/configs/centernet/centernet_shufflenetv2_1x_140e_coco.yml +++ b/configs/centernet/centernet_shufflenetv2_140e_coco.yml @@ -3,7 +3,7 @@ _BASE_: [ ] pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ShuffleNetV2_x1_0_pretrained.pdparams -weights: output/centernet_shufflenetv2_1x_140e_coco/model_final +weights: output/centernet_shufflenetv2_140e_coco/model_final CenterNet: backbone: ShuffleNetV2 @@ -30,4 +30,4 @@ TestReader: - Decode: {} - WarpAffine: {keep_res: False, input_h: 512, input_w: 512} - NormalizeImage: {mean: [0.40789655, 0.44719303, 0.47026116], std: [0.2886383 , 0.27408165, 0.27809834]} - - Permute: {} \ No newline at end of file + - Permute: {} diff --git a/configs/faster_rcnn/README.md b/configs/faster_rcnn/README.md index 33a34d4de72ce5221624aaab48fd6b4f47124d3b..da495599ce180b80ce019ff1828ae63c1140a7ff 100644 --- a/configs/faster_rcnn/README.md +++ b/configs/faster_rcnn/README.md @@ -4,26 +4,26 @@ | 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 | 下载 | 配置文件 | | :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: | -| ResNet50 | Faster | 1 | 1x | ---- | 36.7 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_1x_coco.yml) | -| ResNet50-vd | Faster | 1 | 1x | ---- | 37.6 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_vd_1x_coco.yml) | -| ResNet101 | Faster | 1 | 1x | ---- | 39.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r101_1x_coco.yml) | -| ResNet34-FPN | Faster | 1 | 1x | ---- | 37.8 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r34_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r34_fpn_1x_coco.yml) | -| ResNet34-FPN-MultiScaleTest | Faster | 1 | 1x | ---- | 38.2 | - | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r34_fpn_multiscaletest_1x_coco.yml) | -| ResNet34-vd-FPN | Faster | 1 | 1x | ---- | 38.5 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r34_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r34_vd_fpn_1x_coco.yml) | -| ResNet50-FPN | Faster | 1 | 1x | ---- | 38.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.yml) | -| ResNet50-FPN | Faster | 1 | 2x | ---- | 40.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_fpn_2x_coco.yml) | -| ResNet50-vd-FPN | Faster | 1 | 1x | ---- | 39.5 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_vd_fpn_1x_coco.yml) | -| ResNet50-vd-FPN | Faster | 1 | 2x | ---- | 40.8 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_vd_fpn_2x_coco.yml) | -| ResNet101-FPN | Faster | 1 | 2x | ---- | 41.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r101_fpn_2x_coco.yml) | -| ResNet101-vd-FPN | Faster | 1 | 1x | ---- | 42.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r101_vd_fpn_1x_coco.yml) | -| ResNet101-vd-FPN | Faster | 1 | 2x | ---- | 43.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r101_vd_fpn_2x_coco.yml) | -| ResNeXt101-vd-FPN | Faster | 1 | 1x | ---- | 43.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_x101_vd_64x4d_fpn_1x_coco.yml) | -| ResNeXt101-vd-FPN | Faster | 1 | 2x | ---- | 44.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_x101_vd_64x4d_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_x101_vd_64x4d_fpn_2x_coco.yml) | -| ResNet50-vd-SSLDv2-FPN | Faster | 1 | 1x | ---- | 41.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_ssld_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_vd_fpn_ssld_1x_coco.yml) | -| ResNet50-vd-SSLDv2-FPN | Faster | 1 | 2x | ---- | 42.3 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_ssld_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_vd_ssld_fpn_2x_coco.yml) | -| Swin-Tiny-FPN | Faster | 2 | 1x | ---- | 42.6 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_swin_tiny_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_swin_tiny_1x_coco.yml) | -| Swin-Tiny-FPN | Faster | 2 | 2x | ---- | 44.8 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_swin_tiny_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_swin_tiny_2x_coco.yml) | -| Swin-Tiny-FPN | Faster | 2 | 3x | ---- | 45.3 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_swin_tiny_fpn_3x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_swin_tiny_3x_coco.yml) | +| ResNet50 | Faster | 1 | 1x | ---- | 36.7 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_1x_coco.pdparams) | [配置文件](./faster_rcnn_r50_1x_coco.yml) | +| ResNet50-vd | Faster | 1 | 1x | ---- | 37.6 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_1x_coco.pdparams) | [配置文件](./faster_rcnn_r50_vd_1x_coco.yml) | +| ResNet101 | Faster | 1 | 1x | ---- | 39.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_1x_coco.pdparams) | [配置文件](./faster_rcnn_r101_1x_coco.yml) | +| ResNet34-FPN | Faster | 1 | 1x | ---- | 37.8 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r34_fpn_1x_coco.pdparams) | [配置文件](./faster_rcnn_r34_fpn_1x_coco.yml) | +| ResNet34-FPN-MultiScaleTest | Faster | 1 | 1x | ---- | 38.2 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r34_fpn_multiscaletest_1x_coco.pdparams) | [配置文件](./faster_rcnn_r34_fpn_multiscaletest_1x_coco.yml) | +| ResNet34-vd-FPN | Faster | 1 | 1x | ---- | 38.5 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r34_vd_fpn_1x_coco.pdparams) | [配置文件](./faster_rcnn_r34_vd_fpn_1x_coco.yml) | +| ResNet50-FPN | Faster | 1 | 1x | ---- | 38.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](./faster_rcnn_r50_fpn_1x_coco.yml) | +| ResNet50-FPN | Faster | 1 | 2x | ---- | 40.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_fpn_2x_coco.pdparams) | [配置文件](./faster_rcnn_r50_fpn_2x_coco.yml) | +| ResNet50-vd-FPN | Faster | 1 | 1x | ---- | 39.5 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_1x_coco.pdparams) | [配置文件](./faster_rcnn_r50_vd_fpn_1x_coco.yml) | +| ResNet50-vd-FPN | Faster | 1 | 2x | ---- | 40.8 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](./faster_rcnn_r50_vd_fpn_2x_coco.yml) | +| ResNet101-FPN | Faster | 1 | 2x | ---- | 41.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_fpn_2x_coco.pdparams) | [配置文件](./faster_rcnn_r101_fpn_2x_coco.yml) | +| ResNet101-vd-FPN | Faster | 1 | 1x | ---- | 42.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](./faster_rcnn_r101_vd_fpn_1x_coco.yml) | +| ResNet101-vd-FPN | Faster | 1 | 2x | ---- | 43.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_vd_fpn_2x_coco.pdparams) | [配置文件](./faster_rcnn_r101_vd_fpn_2x_coco.yml) | +| ResNeXt101-vd-FPN | Faster | 1 | 1x | ---- | 43.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](./faster_rcnn_x101_vd_64x4d_fpn_1x_coco.yml) | +| ResNeXt101-vd-FPN | Faster | 1 | 2x | ---- | 44.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_x101_vd_64x4d_fpn_2x_coco.pdparams) | [配置文件](./faster_rcnn_x101_vd_64x4d_fpn_2x_coco.yml) | +| ResNet50-vd-SSLDv2-FPN | Faster | 1 | 1x | ---- | 41.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_ssld_1x_coco.pdparams) | [配置文件](./faster_rcnn_r50_vd_fpn_ssld_1x_coco.yml) | +| ResNet50-vd-SSLDv2-FPN | Faster | 1 | 2x | ---- | 42.3 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_ssld_2x_coco.pdparams) | [配置文件](./faster_rcnn_r50_vd_fpn_ssld_2x_coco.yml) | +| Swin-Tiny-FPN | Faster | 2 | 1x | ---- | 42.6 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_swin_tiny_fpn_1x_coco.pdparams) | [配置文件](./faster_rcnn_swin_tiny_fpn_1x_coco.yml) | +| Swin-Tiny-FPN | Faster | 2 | 2x | ---- | 44.8 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_swin_tiny_fpn_2x_coco.pdparams) | [配置文件](./faster_rcnn_swin_tiny_fpn_2x_coco.yml) | +| Swin-Tiny-FPN | Faster | 2 | 3x | ---- | 45.3 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_swin_tiny_fpn_3x_coco.pdparams) | [配置文件](./faster_rcnn_swin_tiny_fpn_3x_coco.yml) | ## Citations ``` diff --git a/configs/ppyolo/README.md b/configs/ppyolo/README.md index 6b3e5fc61d5abb80b25179e9a5be3683a86de70a..754fdd434a6722b640e441e6b565b8593bf86004 100644 --- a/configs/ppyolo/README.md +++ b/configs/ppyolo/README.md @@ -59,7 +59,7 @@ PP-YOLO and PP-YOLOv2 improved performance and speed of YOLOv3 with following me **Notes:** - PP-YOLO is trained on COCO train2017 dataset and evaluated on val2017 & test-dev2017 dataset，Box APtest is evaluation results of `mAP(IoU=0.5:0.95)`. -- PP-YOLO used 8 GPUs for training and mini-batch size as 24 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ.md). +- PP-YOLO used 8 GPUs for training and mini-batch size as 24 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ). - PP-YOLO inference speed is tesed on single Tesla V100 with batch size as 1, CUDA 10.2, CUDNN 7.5.1, TensorRT 5.1.2.2 in TensorRT mode. - PP-YOLO FP32 inference speed testing uses inference model exported by `tools/export_model.py` and benchmarked by running `depoly/python/infer.py` with `--run_benchmark`. All testing results do not contains the time cost of data reading and post-processing(NMS), which is same as [YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet) in testing method. - TensorRT FP16 inference speed testing exclude the time cost of bounding-box decoding(`yolo_box`) part comparing with FP32 testing above, which means that data reading, bounding-box decoding and post-processing(NMS) is excluded(test method same as [YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet) too) @@ -75,7 +75,7 @@ PP-YOLO and PP-YOLOv2 improved performance and speed of YOLOv3 with following me **Notes:** - PP-YOLO_MobileNetV3 is trained on COCO train2017 datast and evaluated on val2017 dataset，Box APval is evaluation results of `mAP(IoU=0.5:0.95)`, Box APval is evaluation results of `mAP(IoU=0.5)`. -- PP-YOLO_MobileNetV3 used 4 GPUs for training and mini-batch size as 32 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ.md). +- PP-YOLO_MobileNetV3 used 4 GPUs for training and mini-batch size as 32 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ). - PP-YOLO_MobileNetV3 inference speed is tested on Kirin 990 with 1 thread. ### PP-YOLO tiny diff --git a/configs/ppyolo/README_cn.md b/configs/ppyolo/README_cn.md index 8ef2dbc7fb7ae261bfeaeb7e21efdc38c104accd..f4b4c19af515977a365f07203cc5fbea83b49692 100644 --- a/configs/ppyolo/README_cn.md +++ b/configs/ppyolo/README_cn.md @@ -58,7 +58,7 @@ PP-YOLO和PP-YOLOv2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/develop/docs/tutorials/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)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)。 @@ -71,7 +71,7 @@ PP-YOLO和PP-YOLOv2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/develop/docs/tutorials/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)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/test_tipc/README.md b/test_tipc/README.md index befe05f5b03b821c15dff849d5635f36a451f6ac..097b61cd38bf707a01b2f795639b154040fdc8a7 100644 --- a/test_tipc/README.md +++ b/test_tipc/README.md @@ -106,6 +106,6 @@ bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/yolov3/yolov3_ 各功能测试中涉及混合精度、裁剪、量化等训练相关，及mkldnn、Tensorrt等多种预测相关参数配置，请点击下方相应链接了解更多细节和使用教程： - [test_train_inference_python 使用](docs/test_train_inference_python.md) ：测试基于Python的模型训练、评估、推理等基本功能，包括裁剪、量化、蒸馏。 - [test_inference_cpp 使用](docs/test_inference_cpp.md)：测试基于C++的模型推理。 -- [test_serving 使用](docs/test_serving.md)：测试基于Paddle Serving的服务化部署功能。 -- [test_lite_arm_cpu_cpp 使用](docs/test_lite_arm_cpu_cpp.md)：测试基于Paddle-Lite的ARM CPU端c++预测部署功能。 -- [test_paddle2onnx 使用](docs/test_paddle2onnx.md)：测试Paddle2ONNX的模型转化功能，并验证正确性。 +- [test_serving 使用](./)：测试基于Paddle Serving的服务化部署功能。 +- [test_lite_arm_cpu_cpp 使用](./)：测试基于Paddle-Lite的ARM CPU端c++预测部署功能。 +- [test_paddle2onnx 使用](./)：测试Paddle2ONNX的模型转化功能，并验证正确性。 diff --git a/test_tipc/docs/test_train_inference_python.md b/test_tipc/docs/test_train_inference_python.md index 63327ebbc7f9c22b4565491ed8ad8a3134d33604..10459b84346352e1f13c846919574f908b6be2da 100644 --- a/test_tipc/docs/test_train_inference_python.md +++ b/test_tipc/docs/test_train_inference_python.md @@ -2,8 +2,8 @@ Linux端基础训练预测功能测试的主程序为`test_train_inference_python.sh`，可以测试基于Python的模型训练、评估、推理等基本功能，包括裁剪、量化、蒸馏。 -- Mac端基础训练预测功能测试参考[链接](./mac_test_train_inference_python.md) -- Windows端基础训练预测功能测试参考[链接](./win_test_train_inference_python.md) +- Mac端基础训练预测功能测试参考[链接](./) +- Windows端基础训练预测功能测试参考[链接](./) ## 1. 测试结论汇总