From f0bf5be8d401334ff755725354c5990e2d132166 Mon Sep 17 00:00:00 2001 From: Feng Ni Date: Sat, 17 Apr 2021 22:48:20 +0800 Subject: [PATCH] add bias test doc for yolo ppyolo pafnet(#2675) --- configs/ppyolo/README.md | 22 +++++++++++++++++++++- configs/ppyolo/README_cn.md | 22 +++++++++++++++++++++- configs/ttfnet/README.md | 7 ++++++- configs/yolov3/README.md | 11 ++++++++++- 4 files changed, 58 insertions(+), 4 deletions(-) diff --git a/configs/ppyolo/README.md b/configs/ppyolo/README.md index c7384705b..6067db40e 100644 --- a/configs/ppyolo/README.md +++ b/configs/ppyolo/README.md @@ -132,7 +132,27 @@ CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_test.yml -o Evaluation results will be saved in `bbox.json`, compress it into a `zip` package and upload to [COCO dataset evaluation](https://competitions.codalab.org/competitions/20794#participate) to evaluate. -**NOTE:** `configs/ppyolo/ppyolo_test.yml` is only used for evaluation on COCO test-dev2017 dataset, could not be used for training or COCO val2017 dataset evaluating. +**NOTE 1:** `configs/ppyolo/ppyolo_test.yml` is only used for evaluation on COCO test-dev2017 dataset, could not be used for training or COCO val2017 dataset evaluating. + +**NOTE 2:** Due to the overall upgrade of the dynamic graph framework, the following weight models published by paddledetection need to be evaluated by adding the -- bias field, such as + +```bash +# use weights released in PaddleDetection model zoo +CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --bias +``` +These models are: + +1.ppyolo_r50vd_dcn_1x_coco + +2.ppyolo_r50vd_dcn_voc + +3.ppyolo_r18vd_coco + +4.ppyolo_mbv3_large_coco + +5.ppyolo_mbv3_small_coco + +6.ppyolo_tiny_650e_coco ### 3. Inference diff --git a/configs/ppyolo/README_cn.md b/configs/ppyolo/README_cn.md index e683af99b..1a9af6da5 100644 --- a/configs/ppyolo/README_cn.md +++ b/configs/ppyolo/README_cn.md @@ -116,7 +116,27 @@ CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_test.yml -o 评估结果保存于`bbox.json`中，将其压缩为zip包后通过[COCO数据集评估页](https://competitions.codalab.org/competitions/20794#participate)提交评估。 -**注意:** `configs/ppyolo/ppyolo_test.yml`仅用于评估COCO test-dev数据集，不用于训练和评估COCO val2017数据集。 +**注意1:** `configs/ppyolo/ppyolo_test.yml`仅用于评估COCO test-dev数据集，不用于训练和评估COCO val2017数据集。 + +**注意2:** 由于动态图框架整体升级，以下几个PaddleDetection发布的权重模型评估时需要添加--bias字段, 例如 + +```bash +# 使用PaddleDetection发布的权重 +CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --bias +``` +主要有: + +1.ppyolo_r50vd_dcn_1x_coco + +2.ppyolo_r50vd_dcn_voc + +3.ppyolo_r18vd_coco + +4.ppyolo_mbv3_large_coco + +5.ppyolo_mbv3_small_coco + +6.ppyolo_tiny_650e_coco ### 3. 推理 diff --git a/configs/ttfnet/README.md b/configs/ttfnet/README.md index 7c89ca2b0..6f5a73e0c 100644 --- a/configs/ttfnet/README.md +++ b/configs/ttfnet/README.md @@ -40,7 +40,7 @@ PAFNet系列模型从如下方面优化TTFNet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 | 下载 | 配置文件 | | :-------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: | -| ResNet50vd | PAFNet | 18 | 10x | ---- | 42.2 | [下载链接](https://paddledet.bj.bcebos.com/models/pafnet_10x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ttfnet/pafnet_10x_coco.yml) | +| ResNet50vd | PAFNet | 18 | 10x | ---- | 39.8 | [下载链接](https://paddledet.bj.bcebos.com/models/pafnet_10x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ttfnet/pafnet_10x_coco.yml) | @@ -50,7 +50,12 @@ PAFNet系列模型从如下方面优化TTFNet模型： | :-------------- | :------------- | :-----: | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: | | MobileNetv3 | PAFNet-Lite | 12 | 20x | 23.9 | 26.00 | 14 | [下载链接](https://paddledet.bj.bcebos.com/models/pafnet_lite_mobilenet_v3_20x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ttfnet/pafnet_lite_mobilenet_v3_20x_coco.yml) | +**注意：** 由于动态图框架整体升级，PAFNet的PaddleDetection发布的权重模型评估时需要添加--bias字段, 例如 +```bash +# 使用PaddleDetection发布的权重 +CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/pafnet_10x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/pafnet_10x_coco.pdparams --bias +``` ## Citations ``` diff --git a/configs/yolov3/README.md b/configs/yolov3/README.md index fff7935e3..af4d07ce1 100644 --- a/configs/yolov3/README.md +++ b/configs/yolov3/README.md @@ -45,8 +45,17 @@ | MobileNet-V3-SSLD | 416 | 8 | 270e | - | 79.2 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v3_large_ssld_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v3_large_ssld_270e_voc.yml) | | MobileNet-V3-SSLD | 320 | 8 | 270e | - | 77.3 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v3_large_ssld_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v3_large_ssld_270e_voc.yml) | -**注意：** YOLOv3均使用8GPU训练，训练270个epoch +**注意：** YOLOv3均使用8GPU训练，训练270个epoch。由于动态图框架整体升级，以下几个PaddleDetection发布的权重模型评估时需要添加--bias字段, 例如 +```bash +# 使用PaddleDetection发布的权重 +CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/yolov3_darknet53_270e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/yolov3_darknet53_270e_coco.pdparams --bias +``` +主要有: + +1.yolov3_darknet53_270e_coco + +2.yolov3_r50vd_dcn_270e_coco ## Citations ``` -- GitLab