From 5aa070ec228ce1c28e3f6b1eb359eedef8e09d7f Mon Sep 17 00:00:00 2001 From: Kaipeng Deng Date: Tue, 4 Aug 2020 15:18:52 +0800 Subject: [PATCH] polish AP description (#1152) * polish AP description --- configs/ppyolo/README.md | 58 ++++++++++++++++++------------------- configs/ppyolo/README_cn.md | 58 ++++++++++++++++++------------------- 2 files changed, 58 insertions(+), 58 deletions(-) diff --git a/configs/ppyolo/README.md b/configs/ppyolo/README.md index 5a10a4e6e..61afc5e6b 100644 --- a/configs/ppyolo/README.md +++ b/configs/ppyolo/README.md @@ -36,20 +36,20 @@ PP-YOLO improved performance and speed of YOLOv3 with following methods: ### PP-YOLO -| Model | GPU number | images/GPU | backbone | input shape | Box AP | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | download | config | -|:------------------------:|:----------:|:----------:|:----------:| :----------:| :----: | :------------: | :---------------------: | :------: | :-----: | -| YOLOv4(AlexyAB) | - | - | CSPDarknet | 608 | 43.5 | 62 | 105.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov4_cspdarknet.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov4/yolov4_csdarknet.yml) | -| YOLOv4(AlexyAB) | - | - | CSPDarknet | 512 | 43.0 | 83 | 138.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov4_cspdarknet.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov4/yolov4_csdarknet.yml) | -| YOLOv4(AlexyAB) | - | - | CSPDarknet | 416 | 41.2 | 96 | 164.0 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov4_cspdarknet.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov4/yolov4_csdarknet.yml) | -| YOLOv4(AlexyAB) | - | - | CSPDarknet | 320 | 38.0 | 123 | 199.0 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov4_cspdarknet.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov4/yolov4_csdarknet.yml) | -| PP-YOLO | 8 | 24 | ResNet50vd | 608 | 45.2 | 72.9 | 155.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | -| PP-YOLO | 8 | 24 | ResNet50vd | 512 | 44.4 | 89.9 | 188.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | -| PP-YOLO | 8 | 24 | ResNet50vd | 416 | 42.5 | 109.1 | 215.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | -| PP-YOLO | 8 | 24 | ResNet50vd | 320 | 39.3 | 132.2 | 242.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | +| Model | GPU number | images/GPU | backbone | input shape | Box APtest | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | download | config | +|:------------------------:|:----------:|:----------:|:----------:| :----------:| :-------------------: | :------------: | :---------------------: | :------: | :-----: | +| YOLOv4(AlexyAB) | - | - | CSPDarknet | 608 | 43.5 | 62 | 105.5 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov4_cspdarknet.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov4/yolov4_csdarknet.yml) | +| YOLOv4(AlexyAB) | - | - | CSPDarknet | 512 | 43.0 | 83 | 138.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov4_cspdarknet.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov4/yolov4_csdarknet.yml) | +| YOLOv4(AlexyAB) | - | - | CSPDarknet | 416 | 41.2 | 96 | 164.0 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov4_cspdarknet.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov4/yolov4_csdarknet.yml) | +| YOLOv4(AlexyAB) | - | - | CSPDarknet | 320 | 38.0 | 123 | 199.0 | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov4_cspdarknet.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/yolov4/yolov4_csdarknet.yml) | +| PP-YOLO | 8 | 24 | ResNet50vd | 608 | 45.2 | 72.9 | 155.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | +| PP-YOLO | 8 | 24 | ResNet50vd | 512 | 44.4 | 89.9 | 188.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | +| PP-YOLO | 8 | 24 | ResNet50vd | 416 | 42.5 | 109.1 | 215.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | +| PP-YOLO | 8 | 24 | ResNet50vd | 320 | 39.3 | 132.2 | 242.2 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | **Notes:** -- PP-YOLO is trained on COCO train2017 datast and evaluated on test-dev2017 dataset，`Box AP` is evaluation results as `mAP(IoU=0.5:0.95)`. +- PP-YOLO is trained on COCO train2017 datast and evaluated on 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](../../docs/FAQ.md). - PP-YOLO inference speed is tesed on single Tesla V100 with batch size as 1, CUDA 10.2, CUDNN 7.5.1, TensorRT 5.1.2.2 in TensorRT mode. - PP-YOLO FP32 inference speed testing uses inference model exported by `tools/export_model.py` and benchmarked by running `depoly/python/infer.py` with `--run_benchmark`. All testing results do not contains the time cost of data reading and post-processing(NMS), which is same as [YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet) in testing method. @@ -59,12 +59,12 @@ PP-YOLO improved performance and speed of YOLOv3 with following methods: ### PP-YOLO tiny -| Model | GPU number | images/GPU | backbone | input shape | Box AP | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | download | config | -|:------------------------:|:----------:|:----------:|:----------:| :----------:| :----: | :------------: | :---------------------: | :------: | :-----: | -| PP-YOLO tiny | 4 | 32 | ResNet18vd | 416 | 47.0 | 401.6 | 724.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_tiny.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_tiny.yml) | -| PP-YOLO tiny | 4 | 32 | ResNet18vd | 320 | 43.7 | 478.5 | 791.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_tiny.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_tiny.yml) | +| Model | GPU number | images/GPU | backbone | input shape | Box AP50val | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | download | config | +|:------------------------:|:----------:|:----------:|:----------:| :----------:| :--------------------: | :------------: | :---------------------: | :------: | :-----: | +| PP-YOLO tiny | 4 | 32 | ResNet18vd | 416 | 47.0 | 401.6 | 724.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_tiny.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_tiny.yml) | +| PP-YOLO tiny | 4 | 32 | ResNet18vd | 320 | 43.7 | 478.5 | 791.3 | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_tiny.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_tiny.yml) | -- PP-YOLO tiny is trained on COCO train2017 datast and evaluated on val2017 dataset，`Box AP` is evaluation results as `mAP(IoU=0.5)`. +- PP-YOLO tiny is trained on COCO train2017 datast and evaluated on val2017 dataset，Box AP50val is evaluation results of `mAP(IoU=0.5)`. - PP-YOLO tiny 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](../../docs/FAQ.md). - PP-YOLO tiny inference speeding testing environment and configuration is same as PP-YOLO above. @@ -150,22 +150,22 @@ CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output/ppyolo - Optimizing method and ablation experiments of PP-YOLO compared with YOLOv3. -| NO. | Model | Box AP | Params(M) | FLOPs(G) | V100 FP32 FPS | -| :--: | :--------------------------- | :----: | :-------: | :------: | :-----------: | -| A | YOLOv3-DarkNet53 | 38.9 | 59.13 | 65.52 | 58.2 | -| B | YOLOv3-ResNet50vd-DCN | 39.1 | 43.89 | 44.71 | 79.2 | -| C | B + LB + EMA + DropBlock | 41.4 | 43.89 | 44.71 | 79.2 | -| D | C + IoU Loss | 41.9 | 43.89 | 44.71 | 79.2 | -| E | D + IoU Aware | 42.5 | 43.90 | 44.71 | 74.9 | -| F | E + Grid Sensitive | 42.8 | 43.90 | 44.71 | 74.8 | -| G | F + Matrix NMS | 43.5 | 43.90 | 44.71 | 74.8 | -| H | G + CoordConv | 44.0 | 43.93 | 44.76 | 74.1 | -| I | H + SPP | 44.3 | 44.93 | 45.12 | 72.9 | -| J | I + Better ImageNet Pretrain | 44.6 | 44.93 | 45.12 | 72.9 | +| NO. | Model | Box APval | Box APtest | Params(M) | FLOPs(G) | V100 FP32 FPS | +| :--: | :--------------------------- | :------------------: |:--------------------: | :-------: | :------: | :-----------: | +| A | YOLOv3-DarkNet53 | 38.9 | - | 59.13 | 65.52 | 58.2 | +| B | YOLOv3-ResNet50vd-DCN | 39.1 | - | 43.89 | 44.71 | 79.2 | +| C | B + LB + EMA + DropBlock | 41.4 | - | 43.89 | 44.71 | 79.2 | +| D | C + IoU Loss | 41.9 | - | 43.89 | 44.71 | 79.2 | +| E | D + IoU Aware | 42.5 | - | 43.90 | 44.71 | 74.9 | +| F | E + Grid Sensitive | 42.8 | - | 43.90 | 44.71 | 74.8 | +| G | F + Matrix NMS | 43.5 | - | 43.90 | 44.71 | 74.8 | +| H | G + CoordConv | 44.0 | - | 43.93 | 44.76 | 74.1 | +| I | H + SPP | 44.3 | 45.2 | 44.93 | 45.12 | 72.9 | +| J | I + Better ImageNet Pretrain | 44.6 | 45.2 | 44.93 | 45.12 | 72.9 | **Notes:** - Performance and inference spedd are measure with input shape as 608 -- All models are trained on COCO train2017 datast and evaluated on val2017 dataset，`Box AP` is evaluation results as `mAP(IoU=0.5:0.95)`. +- All models are trained on COCO train2017 datast and evaluated on val2017 & test-dev2017 dataset，`Box AP` is evaluation results as `mAP(IoU=0.5:0.95)`. - Inference speed is tested on single Tesla V100 with batch size as 1 following test method and environment configuration in benchmark above. - [YOLOv3-DarkNet53](../yolov3_darknet.yml) with mAP as 38.9 is optimized YOLOv3 model in PaddleDetection，see [Model Zoo](../../docs/MODEL_ZOO.md) for details. diff --git a/configs/ppyolo/README_cn.md b/configs/ppyolo/README_cn.md index dbd8e2ead..c05900521 100644 --- a/configs/ppyolo/README_cn.md +++ b/configs/ppyolo/README_cn.md @@ -36,20 +36,20 @@ PP-YOLO从如下方面优化和提升YOLOv3模型的精度和速度： ### PP-YOLO模型 -| 模型 | GPU个数 | 每GPU图片个数 | 骨干网络 | 输入尺寸 | Box AP | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | 模型下载 | 配置文件 | -|:------------------------:|:-------:|:-------------:|:----------:| :-------:| :----: | :------------: | :---------------------: | :------: | :------: | -| YOLOv4(AlexyAB) | - | - | CSPDarknet | 608 | 43.5 | 62 | 105.5 | [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_csdarknet.yml) | -| YOLOv4(AlexyAB) | - | - | CSPDarknet | 512 | 43.0 | 83 | 138.4 | [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_csdarknet.yml) | -| YOLOv4(AlexyAB) | - | - | CSPDarknet | 416 | 41.2 | 96 | 164.0 | [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_csdarknet.yml) | -| YOLOv4(AlexyAB) | - | - | CSPDarknet | 320 | 38.0 | 123 | 199.0 | [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_csdarknet.yml) | -| PP-YOLO | 8 | 24 | ResNet50vd | 608 | 45.2 | 72.9 | 155.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | -| PP-YOLO | 8 | 24 | ResNet50vd | 512 | 44.4 | 89.9 | 188.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | -| PP-YOLO | 8 | 24 | ResNet50vd | 416 | 42.5 | 109.1 | 215.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | -| PP-YOLO | 8 | 24 | ResNet50vd | 320 | 39.3 | 132.2 | 242.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | +| 模型 | GPU个数 | 每GPU图片个数 | 骨干网络 | 输入尺寸 | Box APtest | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | 模型下载 | 配置文件 | +|:------------------------:|:-------:|:-------------:|:----------:| :-------:| :-------------------: | :------------: | :---------------------: | :------: | :------: | +| YOLOv4(AlexyAB) | - | - | CSPDarknet | 608 | 43.5 | 62 | 105.5 | [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_csdarknet.yml) | +| YOLOv4(AlexyAB) | - | - | CSPDarknet | 512 | 43.0 | 83 | 138.4 | [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_csdarknet.yml) | +| YOLOv4(AlexyAB) | - | - | CSPDarknet | 416 | 41.2 | 96 | 164.0 | [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_csdarknet.yml) | +| YOLOv4(AlexyAB) | - | - | CSPDarknet | 320 | 38.0 | 123 | 199.0 | [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_csdarknet.yml) | +| PP-YOLO | 8 | 24 | ResNet50vd | 608 | 45.2 | 72.9 | 155.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | +| PP-YOLO | 8 | 24 | ResNet50vd | 512 | 44.4 | 89.9 | 188.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | +| PP-YOLO | 8 | 24 | ResNet50vd | 416 | 42.5 | 109.1 | 215.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | +| PP-YOLO | 8 | 24 | ResNet50vd | 320 | 39.3 | 132.2 | 242.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo.yml) | **注意:** -- PP-YOLO模型使用COCO数据集中train2017作为训练集，使用test-dev2017作为测试集，`Box AP`为`mAP(IoU=0.5:0.95)`评估结果。 +- PP-YOLO模型使用COCO数据集中train2017作为训练集，使用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](../../docs/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)。 @@ -60,12 +60,12 @@ PP-YOLO从如下方面优化和提升YOLOv3模型的精度和速度： ### PP-YOLO tiny模型 -| 模型 | GPU个数 | 每GPU图片个数 | 骨干网络 | 输入尺寸 | Box AP | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | 模型下载 | 配置文件 | -|:------------------------:|:-------:|:-------------:|:----------:| :-------:| :----: | :------------: | :---------------------: | :------: | :------: | -| PP-YOLO tiny | 4 | 32 | ResNet18vd | 416 | 47.0 | 401.6 | 724.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_tiny.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_tiny.yml) | -| PP-YOLO tiny | 4 | 32 | ResNet18vd | 320 | 43.7 | 478.5 | 791.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_tiny.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_tiny.yml) | +| 模型 | GPU个数 | 每GPU图片个数 | 骨干网络 | 输入尺寸 | Box AP50val | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | 模型下载 | 配置文件 | +|:------------------------:|:-------:|:-------------:|:----------:| :-------:| :------------------: | :------------: | :---------------------: | :------: | :------: | +| PP-YOLO tiny | 4 | 32 | ResNet18vd | 416 | 47.0 | 401.6 | 724.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_tiny.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_tiny.yml) | +| PP-YOLO tiny | 4 | 32 | ResNet18vd | 320 | 43.7 | 478.5 | 791.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_tiny.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_tiny.yml) | -- PP-YOLO tiny模型使用COCO数据集中train2017作为训练集，使用val2017左右测试集，`Box AP`为`mAP(IoU=0.5)`评估结果。 +- PP-YOLO tiny模型使用COCO数据集中train2017作为训练集，使用val2017作为测试集，Box AP50val为`mAP(IoU=0.5)`评估结果。 - PP-YOLO tiny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](../../docs/FAQ.md)调整学习率和迭代次数。 - PP-YOLO tiny模型推理速度测试环境配置和测试方法与PP-YOLO模型一致。 @@ -151,22 +151,22 @@ CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output/ppyolo - PP-YOLO模型相对于YOLOv3模型优化项消融实验数据如下表所示。 -| 序号 | 模型 | Box AP | 参数量(M) | FLOPs(G) | V100 FP32 FPS | -| :--: | :--------------------------- | :----: | :-------: | :------: | :-----------: | -| A | YOLOv3-DarkNet53 | 38.9 | 59.13 | 65.52 | 58.2 | -| B | YOLOv3-ResNet50vd-DCN | 39.1 | 43.89 | 44.71 | 79.2 | -| C | B + LB + EMA + DropBlock | 41.4 | 43.89 | 44.71 | 79.2 | -| D | C + IoU Loss | 41.9 | 43.89 | 44.71 | 79.2 | -| E | D + IoU Aware | 42.5 | 43.90 | 44.71 | 74.9 | -| F | E + Grid Sensitive | 42.8 | 43.90 | 44.71 | 74.8 | -| G | F + Matrix NMS | 43.5 | 43.90 | 44.71 | 74.8 | -| H | G + CoordConv | 44.0 | 43.93 | 44.76 | 74.1 | -| I | H + SPP | 44.3 | 44.93 | 45.12 | 72.9 | -| J | I + Better ImageNet Pretrain | 44.6 | 44.93 | 45.12 | 72.9 | +| 序号 | 模型 | Box APval | Box APtest | 参数量(M) | FLOPs(G) | V100 FP32 FPS | +| :--: | :--------------------------- | :------------------: | :-------------------: | :-------: | :------: | :-----------: | +| A | YOLOv3-DarkNet53 | 38.9 | - | 59.13 | 65.52 | 58.2 | +| B | YOLOv3-ResNet50vd-DCN | 39.1 | - | 43.89 | 44.71 | 79.2 | +| C | B + LB + EMA + DropBlock | 41.4 | - | 43.89 | 44.71 | 79.2 | +| D | C + IoU Loss | 41.9 | - | 43.89 | 44.71 | 79.2 | +| E | D + IoU Aware | 42.5 | - | 43.90 | 44.71 | 74.9 | +| F | E + Grid Sensitive | 42.8 | - | 43.90 | 44.71 | 74.8 | +| G | F + Matrix NMS | 43.5 | - | 43.90 | 44.71 | 74.8 | +| H | G + CoordConv | 44.0 | - | 43.93 | 44.76 | 74.1 | +| I | H + SPP | 44.3 | 45.2 | 44.93 | 45.12 | 72.9 | +| J | I + Better ImageNet Pretrain | 44.6 | 45.2 | 44.93 | 45.12 | 72.9 | **注意:** - 精度与推理速度数据均为使用输入图像尺寸为608的测试结果 -- Box AP为在COCO train2017数据集训练，val2017数据集上评估数据 +- Box AP为在COCO train2017数据集训练，val2017和test-dev2017数据集上评估`mAP(IoU=0.5:0.95)`数据 - 推理速度为单卡V100上，batch size=1, 使用上述benchmark测试方法的测试结果，测试环境配置为CUDA 10.2，CUDNN 7.5.1 - [YOLOv3-DarkNet53](../yolov3_darknet.yml)精度38.9为PaddleDetection优化后的YOLOv3模型，可参见[模型库](../../docs/MODEL_ZOO_cn.md) -- GitLab