Skip to content

P
PaddleDetection

PaddlePaddle / PaddleDetection
1 年多 前同步成功

通知 696
Star 11112
Fork 2696
P
PaddleDetection
未验证 提交 80f1f748 编写于 作者: G Guanghua Yu 提交者： GitHub
浏览文件
操作

update slim models and benchmark (#3077) 

* update slim models and benchmark
上级 571dcb34
隐藏空白更改
内联 并排
Showing with 183 addition and 29 deletion
configs/slim/README.md
浏览文件 @ 80f1f748
......@@ -13,7 +13,7 @@
- Python 3.7+
- PaddlePaddle >= 2.1.0
- PaddleSlim >= 2.0.0
- PaddleSlim >= 2.1.0
- CUDA 10.1+
- cuDNN >=7.6.5
......@@ -72,6 +72,8 @@ python tools/infer.py -c configs/{MODEL.yml} --slim_config configs/slim/{SLIM_CO
- `--infer_img`: 指定测试图像路径。
## 全链条部署
### 动转静导出模型
```shell
......@@ -82,6 +84,14 @@ python tools/export_model.py -c configs/{MODEL.yml} --slim_config configs/slim/{
- `--slim_config`: 指定压缩策略配置文件。
- `-o weights`: 指定压缩算法训好的模型路径。
### 部署预测
- Paddle-Inference预测：
- [Python部署](../../deploy/python/README.md)
- [C++部署](../../deploy/cpp/README.md)
- [TensorRT预测部署教程](../../deploy/TENSOR_RT.md)
- 服务器端部署：使用[PaddleServing](../../deploy/serving/README.md)部署。
- 手机移动端部署：使用[Paddle-Lite](../../deploy/lite/README.md) 在手机移动端部署。
## Benchmark
......@@ -89,31 +99,51 @@ python tools/export_model.py -c configs/{MODEL.yml} --slim_config configs/slim/{
#### Pascal VOC上benchmark
| 模型 | 压缩策略 | GFLOPs | 模型体积(MB) | 输入尺寸 | 预测时延（SD855）| Box AP | 下载 | 模型配置文件 | 压缩算法配置文件 |
| :----------------| :-------: | :------------: | :-------------: | :------: | :--------: | :------: | :-----------------------------------------------------: |:-------------: | :------: |
| YOLOv3-MobileNetV1 | baseline | 24.13 | 93 | 608 | 289.9ms | 75.1 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml) | - |
| 模型 | 压缩策略 | GFLOPs | 模型体积(MB) | 输入尺寸 | 预测时延(SD855) | Box AP | 下载 | 模型配置文件 | 压缩算法配置文件 |
| :---------: | :-------: | :------------: |:-------------: | :------: | :-------------: | :------: | :-----------------------------------------------------: |:-------------: | :------: |
| YOLOv3-MobileNetV1 | baseline | 24.13 | 93 | 608 | 332.0ms | 75.1 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml) | - |
| YOLOv3-MobileNetV1 | 剪裁-l1_norm(sensity) | 15.78(-34.49%) | 66(-29%) | 608 | - | 78.4(+3.3) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_mobilenet_v1_voc_prune_l1_norm.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/prune/yolov3_prune_l1_norm.yml) |
- 目前剪裁支持YOLO系列、SSD、TTFNet、BlazeFace，其余模型正在开发支持中。
#### COCO上benchmark
| 模型 | 压缩策略 | GFLOPs | 模型体积(MB) | 输入尺寸 | 预测时延(SD855) | Box AP | 下载 | 模型配置文件 | 压缩算法配置文件 |
| :---------: | :-------: | :------------: |:-------------: | :------: | :-------------: | :------: | :-----------------------------------------------------: |:-------------: | :------: |
| PP-YOLO-MobileNetV3_large | baseline | -- | 18.5 | 608 | 25.1ms | 24.3 | [下载链接](https://paddledet.bj.bcebos.com/models/ppyolo_mbv3_large_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_mbv3_large_coco.yml) | - |
| PP-YOLO-MobileNetV3_large | 剪裁-FPGM | -37% | 12.6 | 608 | - | 22.3 | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ppyolo_mbv3_large_prune_fpgm.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_mbv3_large_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/prune/ppyolo_mbv3_large_prune_fpgm.yml) |
| YOLOv3-DarkNet53 | baseline | -- | 238.2 | 608 | - | 39.0 | [下载链接](https://paddledet.bj.bcebos.com/models/ppyolo_mbv3_large_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_darknet53_270e_coco.yml) | - |
| YOLOv3-DarkNet53 | 剪裁-FPGM | -24% | - | 608 | - | 37.6 | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_darknet_prune_fpgm.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_darknet53_270e_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/prune/yolov3_darknet_prune_fpgm.yml) |
| PP-YOLO_R50vd | baseline | -- | 183.3 | 608 | - | 44.8 | [下载链接](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml) | - |
| PP-YOLO_R50vd | 剪裁-FPGM | -35% | - | 608 | - | 42.1 | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ppyolo_r50vd_prune_fpgm.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/prune/ppyolo_r50vd_prune_fpgm.yml) |
说明：
- 目前剪裁除RCNN系列模型外，其余模型均已支持。
- SD855预测时延为使用PaddleLite部署，使用arm8架构并使用4线程(4 Threads)推理时延。
### 量化
#### COCO上benchmark
| 模型 | 压缩策略 | 输入尺寸 | Box AP | 下载 | 模型配置文件 | 压缩算法配置文件 |
| ------------------ | ------------ | -------- | :---------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
| YOLOv3-MobileNetV1 | baseline | 608 | 28.8 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | - |
| YOLOv3-MobileNetV1 | 普通在线量化 | 608 | 30.5 (+1.7) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_mobilenet_v1_coco_qat.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/quant/yolov3_mobilenet_v1_qat.yml) |
| YOLOv3-MobileNetV3 | baseline | 608 | 31.4 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml) | - |
| YOLOv3-MobileNetV3 | PACT在线量化 | 608 | 29.1 (-2.3) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_mobilenet_v3_coco_qat.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/quant/yolov3_mobilenet_v3_qat.yml) |
| YOLOv3-DarkNet53 | baseline | 608 | 39.0 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_darknet53_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_darknet53_270e_coco.yml) | - |
| YOLOv3-DarkNet53 | 普通在线量化 | 608 | 38.8 (-0.2) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_darknet_coco_qat.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_darknet53_270e_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/quant/yolov3_darknet_qat.yml) |
| SSD-MobileNet_v1 | baseline | 300 | 73.8 | [下载链接](https://paddledet.bj.bcebos.com/models/ssd_mobilenet_v1_300_120e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ssd/ssd_mobilenet_v1_300_120e_voc.yml) | - |
| SSD-MobileNet_v1 | 普通在线量化 | 300 | 72.9(-0.9) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ssd_mobilenet_v1_300_voc_qat.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ssd/ssd_mobilenet_v1_300_120e_voc.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/quant/ssd_mobilenet_v1_qat.yml) |
| Mask-ResNet50-FPN | baseline | (800, 1333) | 39.2/35.6 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.yml) | - |
| Mask-ResNet50-FPN | 普通在线量化 | (800, 1333) | 39.7(+0.5)/35.9(+0.3) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/mask_rcnn_r50_fpn_1x_qat.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/quant/mask_rcnn_r50_fpn_1x_qat.yml) |
| 模型 | 压缩策略 | 输入尺寸 | 模型体积(MB) | 预测时延(V100) | 预测时延(SD855) | Box AP | 下载 | Inference模型下载 | 模型配置文件 | 压缩算法配置文件 |
| ------------------ | ------------ | -------- | :---------: | :---------: |:---------: | :---------: | :----------------------------------------------: | :----------------------------------------------: |:------------------------------------------: | :------------------------------------: |
| PP-YOLOv2_R50vd | baseline | 640 | 208.6 | 19.1ms | -- | 49.1 | [下载链接](https://paddledet.bj.bcebos.com/models/ppyolov2_r50vd_dcn_365e_coco.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ppyolov2_r50vd_dcn_365e_coco.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml) | - |
| PP-YOLOv2_R50vd | PACT在线量化 | 640 | -- | 17.3ms | -- | 48.1 | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ppyolov2_r50vd_dcn_qat.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ppyolov2_r50vd_dcn_qat.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/quant/ppyolov2_r50vd_dcn_qat.yml) |
| PP-YOLO_R50vd | baseline | 608 | 183.3 | 17.4ms | -- | 44.8 | [下载链接](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ppyolo_r50vd_dcn_1x_coco.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml) | - |
| PP-YOLO_R50vd | PACT在线量化 | 608 | 67.3 | 13.8ms | -- | 44.3 | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ppyolo_r50vd_qat_pact.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ppyolo_r50vd_qat_pact.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/quant/ppyolo_r50vd_qat_pact.yml) |
| PP-YOLO-MobileNetV3_large | baseline | 320 | 18.5 | 2.7ms | 27.9ms | 23.2 | [下载链接](https://paddledet.bj.bcebos.com/models/ppyolo_mbv3_large_coco.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ppyolo_mbv3_large_coco.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_mbv3_large_coco.yml) | - |
| PP-YOLO-MobileNetV3_large | 普通在线量化 | 320 | 5.6 | -- | 25.1ms | 24.3 | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ppyolo_mbv3_large_qat.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ppyolo_mbv3_large_qat.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_mbv3_large_coco.yml) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/quant/ppyolo_mbv3_large_qat.yml) |
| YOLOv3-MobileNetV1 | baseline | 608 | 94.2 | 8.9ms | 332ms | 29.4 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_270e_coco.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_mobilenet_v1_270e_coco.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | - |
| YOLOv3-MobileNetV1 | 普通在线量化 | 608 | 25.4 | 6.6ms | 248ms | 30.5 | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_mobilenet_v1_coco_qat.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_mobilenet_v1_coco_qat.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/quant/yolov3_mobilenet_v1_qat.yml) |
| YOLOv3-MobileNetV3 | baseline | 608 | 90.3 | 9.4ms | 367.2ms | 31.4 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_mobilenet_v3_large_270e_coco.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml) | - |
| YOLOv3-MobileNetV3 | PACT在线量化 | 608 | 24.4 | 8.0ms | 280.0ms | 31.1 | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_mobilenet_v3_coco_qat.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_mobilenet_v3_coco_qat.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/quant/yolov3_mobilenet_v3_qat.yml) |
| YOLOv3-DarkNet53 | baseline | 608 | 238.2 | 16.0ms | -- | 39.0 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_darknet53_270e_coco.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_darknet53_270e_coco.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_darknet53_270e_coco.yml) | - |
| YOLOv3-DarkNet53 | 普通在线量化 | 608 | 78.8 | 12.4ms | -- | 38.8 | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_darknet_coco_qat.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_darknet_coco_qat.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_darknet53_270e_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/quant/yolov3_darknet_qat.yml) |
| SSD-MobileNet_v1 | baseline | 300 | 22.5 | 4.4ms | 26.6ms | 73.8 | [下载链接](https://paddledet.bj.bcebos.com/models/ssd_mobilenet_v1_300_120e_voc.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ssd_mobilenet_v1_300_120e_voc.tar) |[配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ssd/ssd_mobilenet_v1_300_120e_voc.yml) | - |
| SSD-MobileNet_v1 | 普通在线量化 | 300 | 7.1 | -- | 21.5ms | 72.9 | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ssd_mobilenet_v1_300_voc_qat.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/ssd_mobilenet_v1_300_voc_qat.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ssd/ssd_mobilenet_v1_300_120e_voc.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/quant/ssd_mobilenet_v1_qat.yml) |
| Mask-ResNet50-FPN | baseline | (800, 1333) | 174.1 | 359.5ms | -- | 39.2/35.6 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_fpn_1x_coco.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/mask_rcnn_r50_fpn_1x_coco.tar) |[配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.yml) | - |
| Mask-ResNet50-FPN | 普通在线量化 | (800, 1333) | -- | -- | -- | 39.7(+0.5)/35.9(+0.3) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/mask_rcnn_r50_fpn_1x_qat.pdparams) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/mask_rcnn_r50_fpn_1x_qat.tar) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/quant/mask_rcnn_r50_fpn_1x_qat.yml) |
说明：
- 上述V100预测时延非量化模型均是使用TensorRT-FP32测试，量化模型均使用TensorRT-INT8测试，并且都包含NMS耗时。
- SD855预测时延为使用PaddleLite部署，使用arm8架构并使用4线程(4 Threads)推理时延。
### 蒸馏
......@@ -130,7 +160,7 @@ python tools/export_model.py -c configs/{MODEL.yml} --slim_config configs/slim/{
#### COCO上benchmark
| 模型 | 压缩策略 | 输入尺寸 | GFLOPs | 模型体积(MB) | Box AP | 下载 | 模型配置文件 | 压缩算法配置文件 |
| ------------------ | ------------ | -------- | :---------: |:---------: | :---------: |:----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
| YOLOv3-MobileNetV1 | baseline | 608 | 24.65 | 94.6 | 29.4 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | - |
| YOLOv3-MobileNetV1 | 蒸馏+剪裁 | 608 | 7.54(-69.4%) | 32.0(-66.0%) | 28.4(-1.0) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_mobilenet_v1_coco_distill_prune.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/extensions/yolov3_mobilenet_v1_coco_distill_prune.yml) |
| 模型 | 压缩策略 | 输入尺寸 | GFLOPs | 模型体积(MB) | 预测时延(SD855) | Box AP | 下载 | 模型配置文件 | 压缩算法配置文件 |
| ------------------ | ------------ | -------- | :---------: |:---------: |:---------: | :---------: |:----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
| YOLOv3-MobileNetV1 | baseline | 608 | 24.65 | 94.2 | 332.0ms | 29.4 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | - |
| YOLOv3-MobileNetV1 | 蒸馏+剪裁 | 608 | 7.54(-69.4%) | 30.9(-67.2%) | 166.1ms | 28.4(-1.0) | [下载链接](https://paddledet.bj.bcebos.com/models/slim/yolov3_mobilenet_v1_coco_distill_prune.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | [slim配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim/extensions/yolov3_mobilenet_v1_coco_distill_prune.yml) |
configs/slim/prune/ppyolo_mbv3_large_prune_fpgm.yml 0 → 100644
浏览文件 @ 80f1f748
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyolo_mbv3_large_coco.pdparams
slim: Pruner
Pruner:
criterion: fpgm
pruned_params: ['conv2d_62.w_0', 'conv2d_63.w_0', 'conv2d_64.w_0',
'conv2d_65.w_0', 'conv2d_66.w_0', 'conv2d_67.w_0']
pruned_ratios: [0.75, 0.75, 0.75, 0.75, 0.75, 0.75]
print_params: True
configs/slim/prune/ppyolo_r50vd_prune_fpgm.yml 0 → 100644
浏览文件 @ 80f1f748
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams
slim: Pruner
Pruner:
criterion: fpgm
pruned_params: ['conv2d_56.w_0', 'conv2d_57.w_0', 'conv2d_58.w_0',
'conv2d_59.w_0', 'conv2d_60.w_0', 'conv2d_61.w_0',
'conv2d_63.w_0', 'conv2d_64.w_0', 'conv2d_65.w_0',
'conv2d_66.w_0', 'conv2d_67.w_0', 'conv2d_68.w_0',
'conv2d_70.w_0', 'conv2d_71.w_0', 'conv2d_72.w_0',
'conv2d_73.w_0', 'conv2d_74.w_0', 'conv2d_75.w_0']
pruned_ratios: [0.75,0.75,0.75,0.75,0.75,0.75,0.75,0.75,0.75,0.75,0.75,0.75,0.875,0.875,0.875,0.875,0.875,0.875]
print_params: False
configs/slim/prune/yolov3_darknet_prune_fpgm.yml 0 → 100644
浏览文件 @ 80f1f748
pretrain_weights: https://paddledet.bj.bcebos.com/models/yolov3_darknet53_270e_coco.pdparams
slim: Pruner
Pruner:
criterion: fpgm
pruned_params: ['conv2d_52.w_0', 'conv2d_53.w_0', 'conv2d_54.w_0',
'conv2d_55.w_0', 'conv2d_56.w_0', 'conv2d_57.w_0',
'conv2d_59.w_0', 'conv2d_60.w_0', 'conv2d_61.w_0',
'conv2d_62.w_0', 'conv2d_63.w_0', 'conv2d_64.w_0',
'conv2d_66.w_0', 'conv2d_67.w_0', 'conv2d_68.w_0',
'conv2d_69.w_0', 'conv2d_70.w_0', 'conv2d_71.w_0']
pruned_ratios: [0.75,0.75,0.75,0.75,0.75,0.75,0.75,0.75,0.75,0.75,0.75,0.75,0.875,0.875,0.875,0.875,0.875,0.875]
print_params: True
configs/slim/quant/ppyolo_mbv3_large_qat.yml 0 → 100644
浏览文件 @ 80f1f748
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyolo_mbv3_large_coco.pdparams
slim: QAT
QAT:
quant_config: {
'weight_quantize_type': 'channel_wise_abs_max', 'activation_quantize_type': 'moving_average_abs_max',
'weight_bits': 8, 'activation_bits': 8, 'dtype': 'int8', 'window_size': 10000, 'moving_rate': 0.99,
'quantizable_layer_type': ['Conv2D', 'Linear']}
print_model: True
PPYOLOFPN:
in_channels: [160, 368]
coord_conv: true
conv_block_num: 0
spp: true
drop_block: false
configs/slim/quant/ppyolo_r50vd_qat_pact.yml 0 → 100644
浏览文件 @ 80f1f748
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams
slim: QAT
QAT:
quant_config: {
'activation_preprocess_type': 'PACT',
'weight_quantize_type': 'channel_wise_abs_max', 'activation_quantize_type': 'moving_average_abs_max',
'weight_bits': 8, 'activation_bits': 8, 'dtype': 'int8', 'window_size': 10000, 'moving_rate': 0.9,
'quantizable_layer_type': ['Conv2D', 'Linear']}
print_model: True
epoch: 50
LearningRate:
base_lr: 0.0005
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones:
- 30
- 45
- !LinearWarmup
start_factor: 0.
steps: 1000
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
PPYOLOFPN:
coord_conv: true
block_size: 3
keep_prob: 0.9
spp: true
drop_block: false
configs/slim/quant/ppyolov2_r50vd_dcn_qat.yml 0 → 100644
浏览文件 @ 80f1f748
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyolov2_r50vd_dcn_365e_coco.pdparams
slim: QAT
QAT:
quant_config: {
'activation_preprocess_type': 'PACT',
'weight_quantize_type': 'channel_wise_abs_max', 'activation_quantize_type': 'moving_average_abs_max',
'weight_bits': 8, 'activation_bits': 8, 'dtype': 'int8', 'window_size': 10000, 'moving_rate': 0.9,
'quantizable_layer_type': ['Conv2D', 'Linear']}
print_model: True
epoch: 50
snapshot_epoch: 8
LearningRate:
base_lr: 0.0005
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones:
- 30
- 45
- !LinearWarmup
start_factor: 0.
steps: 2000
TrainReader:
batch_size: 8
PPYOLOPAN:
drop_block: false
block_size: 3
keep_prob: 0.9
spp: true
configs/slim/quant/yolov3_mobilenet_v3_qat.yml
浏览文件 @ 80f1f748
......@@ -4,21 +4,21 @@ slim: QAT
QAT:
quant_config: {
'weight_preprocess_type': 'PACT',
'activation_preprocess_type': 'PACT',
'weight_quantize_type': 'channel_wise_abs_max', 'activation_quantize_type': 'moving_average_abs_max',
'weight_bits': 8, 'activation_bits': 8, 'dtype': 'int8', 'window_size': 10000, 'moving_rate': 0.9,
'quantizable_layer_type': ['Conv2D', 'Linear']}
print_model: True
epoch: 30
epoch: 50
LearningRate:
base_lr: 0.0001
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones:
- 25
- 28
- 35
- 45
- !LinearWarmup
start_factor: 0.
steps: 2000
steps: 1000
deploy/README.md
浏览文件 @ 80f1f748
......@@ -6,7 +6,7 @@
- `C++`语言部署 ，支持`CPU`、`GPU`和`XPU`环境，支持在`Linux`、`Windows`系统下部署，支持`NV Jetson`嵌入式设备上部署。请参考文档[C++部署](cpp/README.md)。
- `TensorRT`加速：请参考文档[TensorRT预测部署教程](TENSOR_RT.md)
- 服务器端部署：使用[PaddleServing](./serving/README.md)部署。
- 手机移动端部署：使用[Paddle-Lite](https://github.com/PaddlePaddle/Paddle-Lite) 在手机移动端部署。
- 手机移动端部署：使用[Paddle-Lite](./lite/README.md) 在手机移动端部署。
## 1.模型导出
......
ppdet/engine/trainer.py
浏览文件 @ 80f1f748
......@@ -498,7 +498,7 @@ class Trainer(object):
}]
# dy2st and save model
if 'slim' not in self.cfg or self.cfg['slim'] != 'QAT':
if 'slim' not in self.cfg or self.cfg['slim_type'] != 'QAT':
static_model = paddle.jit.to_static(
self.model, input_spec=input_spec)
# NOTE: dy2st do not pruned program, but jit.save will prune program
......
ppdet/slim/__init__.py
浏览文件 @ 80f1f748
......@@ -53,6 +53,7 @@ def build_slim_model(cfg, slim_cfg, mode='train'):
if mode == 'train':
load_pretrain_weight(model, cfg.pretrain_weights)
slim = create(cfg.slim)
cfg['slim_type'] = cfg.slim
cfg['model'] = slim(model)
cfg['slim'] = slim
if mode != 'train':
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或