From d85b8341d1fdf1a0843474197b210e3b1c3ef7dc Mon Sep 17 00:00:00 2001 From: Feng Ni Date: Sat, 17 Apr 2021 22:49:09 +0800 Subject: [PATCH] fix release/2.0 modelzoo link(#2678) --- configs/fcos/README.md | 7 ++--- configs/ppyolo/README.md | 4 +-- configs/ppyolo/README_cn.md | 18 +++++++++-- configs/ssd/README.md | 4 +-- configs/yolov3/README.md | 60 ++++++++++++++++++------------------- 5 files changed, 53 insertions(+), 40 deletions(-) diff --git a/configs/fcos/README.md b/configs/fcos/README.md index 3ccd445ca..c852d09dc 100644 --- a/configs/fcos/README.md +++ b/configs/fcos/README.md @@ -12,10 +12,9 @@ FCOS (Fully Convolutional One-Stage Object Detection) is a fast anchor-free obje | 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-FPN | FCOS | 2 | 1x | ---- | 39.6 | [下载链接](https://paddledet.bj.bcebos.com/models/fcos_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/fcos/fcos_r50_fpn_1x_coco.yml) | -| ResNet50-FPN | FCOS+DCN | 2 | 1x | ---- | 44.3 | [下载链接](https://paddledet.bj.bcebos.com/models/fcos_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/fcos/fcos_dcn_r50_fpn_1x_coco.yml) | -| ResNet50-FPN | FCOS+multiscale_train | 2 | 2x | ---- | 41.8 | [下载链接](https://paddledet.bj.bcebos.com/models/fcos_r50_fpn_multiscale_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/fcos/fcos_r50_fpn_multiscale_2x_coco.yml) | - +| ResNet50-FPN | FCOS | 2 | 1x | ---- | 39.6 | [下载链接](https://paddledet.bj.bcebos.com/models/fcos_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/fcos/fcos_r50_fpn_1x_coco.yml) | +| ResNet50-FPN | FCOS+DCN | 2 | 1x | ---- | 44.3 | [下载链接](https://paddledet.bj.bcebos.com/models/fcos_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/fcos/fcos_dcn_r50_fpn_1x_coco.yml) | +| ResNet50-FPN | FCOS+multiscale_train | 2 | 2x | ---- | 41.8 | [下载链接](https://paddledet.bj.bcebos.com/models/fcos_r50_fpn_multiscale_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/fcos/fcos_r50_fpn_multiscale_2x_coco.yml) | **Notes:** - FCOS is trained on COCO train2017 dataset and evaluated on val2017 results of `mAP(IoU=0.5:0.95)`. diff --git a/configs/ppyolo/README.md b/configs/ppyolo/README.md index 21207c8ca..b1490180e 100644 --- a/configs/ppyolo/README.md +++ b/configs/ppyolo/README.md @@ -70,7 +70,7 @@ PP-YOLO improved performance and speed of YOLOv3 with following methods: **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 is trained on COCO train2017 datast and evaluated on val2017 dataset，Box APval is evaluation results of `mAP(IoU=0.5:0.95)`, Box AP50val 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/release/2.0/static/docs/FAQ.md). - PP-YOLO_MobileNetV3 inference speed is tested on Kirin 990 with 1 thread. @@ -83,7 +83,7 @@ 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 is trained on COCO train2017 datast and evaluated on val2017 dataset，Box APval is evaluation results of `mAP(IoU=0.5:0.95)`. - 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/release/2.0/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/configs/ppyolo/README_cn.md b/configs/ppyolo/README_cn.md index d7762b99c..f5a6b18e4 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/release/2.0/static/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)。 - 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)。 @@ -69,9 +69,23 @@ 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/release/2.0/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/release/2.0/static/docs/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 | GPU个数 | 每GPU图片个数 | 模型体积 | 量化后模型体积 | 输入尺寸 | Box APval | Kirin 990 4xCore(FPS) | 模型下载 | 配置文件 | 量化后模型下载 | +|:---------:|:-------:|:---------:|:---------:| :-------------------: | :---------: | :------------------: | :-------------------: | :------: | :----: | :--------------: | +| PP-YOLO tiny | 8 | 32 | 4.2MB | **1.3M** | 320 | 20.6 | 92.3 | [下载链接](https://paddledet.bj.bcebos.com/models/ppyolo_tiny_650e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/ppyolo/ppyolo_tiny_650e_coco.yml) | [推理模型](https://paddledet.bj.bcebos.com/models/ppyolo_tiny_quant.tar) | +| PP-YOLO tiny | 8 | 32 | 4.2MB | **1.3M** | 416 | 22.7 | 65.4 | [下载链接](https://paddledet.bj.bcebos.com/models/ppyolo_tiny_650e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/ppyolo/ppyolo_tiny_650e_coco.yml) | [推理模型](https://paddledet.bj.bcebos.com/models/ppyolo_tiny_quant.tar) | + +**注意:** + +- PP-YOLO-tiny 在COCO train2017数据集上进行训练，在val2017数据集上进行评估，Box APval 是`mAP(IoU=0.5:0.95)`的评估结果。 +- PP-YOLO-tiny 使用8个GPU进行训练，每个GPU上的batch size为32，如果GPU数量和最小批量大小发生变化，则应根据[FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.0/static/docs/FAQ.md)调整学习速率和迭代次数。 +- PP-YOLO-tiny 是利用arm8在Kirin 990上4个线程来测试推理速度的。 +- 我们还提供了PP-YOLO-tiny 量化后的推理模型, 它可以将模型压缩到**1.3MB**，并且几乎不需要对推理速度和性能进行任何推理。 + ### Pascal VOC数据集上的PP-YOLO PP-YOLO在Pascal VOC数据集上训练模型如下: diff --git a/configs/ssd/README.md b/configs/ssd/README.md index 1ebc45866..b2bcd67d1 100644 --- a/configs/ssd/README.md +++ b/configs/ssd/README.md @@ -6,8 +6,8 @@ | 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 | | :-------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: | -| VGG | SSD | 8 | 240e | ---- | 77.8 | [下载链接](https://paddledet.bj.bcebos.com/models/ssd_vgg16_300_240e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ssd/ssd_vgg16_300_240e_voc.yml) | -| MobileNet v1 | SSD | 32 | 120e | ---- | 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) | +| VGG | SSD | 8 | 240e | ---- | 77.8 | [下载链接](https://paddledet.bj.bcebos.com/models/ssd_vgg16_300_240e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/ssd/ssd_vgg16_300_240e_voc.yml) | +| MobileNet v1 | SSD | 32 | 120e | ---- | 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/release/2.0/configs/ssd/ssd_mobilenet_v1_300_120e_voc.yml) | **注意：** SSD-VGG使用4GPU在总batch size为32下训练240个epoch。SSD-MobileNetv1使用2GPU在总batch size为64下训练120周期。 diff --git a/configs/yolov3/README.md b/configs/yolov3/README.md index bdf5de599..e4408c566 100644 --- a/configs/yolov3/README.md +++ b/configs/yolov3/README.md @@ -9,41 +9,41 @@ | DarkNet53(paper) | 608 | 8 | 270e | ---- | 33.0 | - | - | | DarkNet53(paper) | 416 | 8 | 270e | ---- | 31.0 | - | - | | DarkNet53(paper) | 320 | 8 | 270e | ---- | 28.2 | - | - | -| DarkNet53 | 608 | 8 | 270e | ---- | 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) | -| DarkNet53 | 416 | 8 | 270e | ---- | 37.5 | [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) | -| DarkNet53 | 320 | 8 | 270e | ---- | 34.6 | [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) | -| ResNet50_vd | 608 | 8 | 270e | ---- | 39.1 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_r50vd_dcn_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_r50vd_dcn_270e_coco.yml) | -| ResNet50_vd | 416 | 8 | 270e | ---- | 36.6 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_r50vd_dcn_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_r50vd_dcn_270e_coco.yml) | -| ResNet50_vd | 320 | 8 | 270e | ---- | 33.6 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_r50vd_dcn_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_r50vd_dcn_270e_coco.yml) | -| ResNet34 | 608 | 8 | 270e | ---- | 36.2 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_r34_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_r34_270e_coco.yml) | -| ResNet34 | 416 | 8 | 270e | ---- | 34.3 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_r34_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_r34_270e_coco.yml) | -| ResNet34 | 320 | 8 | 270e | ---- | 31.2 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_r34_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_r34_270e_coco.yml) | -| MobileNet-V1 | 608 | 8 | 270e | ---- | 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) | -| MobileNet-V1 | 416 | 8 | 270e | ---- | 29.3 | [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) | -| MobileNet-V1 | 320 | 8 | 270e | ---- | 27.2 | [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) | -| MobileNet-V3 | 608 | 8 | 270e | ---- | 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) | -| MobileNet-V3 | 416 | 8 | 270e | ---- | 29.6 | [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) | -| MobileNet-V3 | 320 | 8 | 270e | ---- | 27.1 | [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) | -| MobileNet-V1-SSLD | 608 | 8 | 270e | ---- | 31.0 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_ssld_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_ssld_270e_coco.yml) | -| MobileNet-V1-SSLD | 416 | 8 | 270e | ---- | 30.6 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_ssld_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_ssld_270e_coco.yml) | -| MobileNet-V1-SSLD | 320 | 8 | 270e | ---- | 28.4 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_ssld_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_ssld_270e_coco.yml) | +| DarkNet53 | 608 | 8 | 270e | ---- | 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/release/2.0/configs/yolov3/yolov3_darknet53_270e_coco.yml) | +| DarkNet53 | 416 | 8 | 270e | ---- | 37.5 | [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/release/2.0/configs/yolov3/yolov3_darknet53_270e_coco.yml) | +| DarkNet53 | 320 | 8 | 270e | ---- | 34.6 | [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/release/2.0/configs/yolov3/yolov3_darknet53_270e_coco.yml) | +| ResNet50_vd | 608 | 8 | 270e | ---- | 39.1 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_r50vd_dcn_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_r50vd_dcn_270e_coco.yml) | +| ResNet50_vd | 416 | 8 | 270e | ---- | 36.6 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_r50vd_dcn_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_r50vd_dcn_270e_coco.yml) | +| ResNet50_vd | 320 | 8 | 270e | ---- | 33.6 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_r50vd_dcn_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_r50vd_dcn_270e_coco.yml) | +| ResNet34 | 608 | 8 | 270e | ---- | 36.2 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_r34_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_r34_270e_coco.yml) | +| ResNet34 | 416 | 8 | 270e | ---- | 34.3 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_r34_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_r34_270e_coco.yml) | +| ResNet34 | 320 | 8 | 270e | ---- | 31.2 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_r34_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_r34_270e_coco.yml) | +| MobileNet-V1 | 608 | 8 | 270e | ---- | 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/release/2.0/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | +| MobileNet-V1 | 416 | 8 | 270e | ---- | 29.3 | [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/release/2.0/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | +| MobileNet-V1 | 320 | 8 | 270e | ---- | 27.2 | [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/release/2.0/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) | +| MobileNet-V3 | 608 | 8 | 270e | ---- | 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/release/2.0/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml) | +| MobileNet-V3 | 416 | 8 | 270e | ---- | 29.6 | [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/release/2.0/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml) | +| MobileNet-V3 | 320 | 8 | 270e | ---- | 27.1 | [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/release/2.0/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml) | +| MobileNet-V1-SSLD | 608 | 8 | 270e | ---- | 31.0 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_ssld_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_mobilenet_v1_ssld_270e_coco.yml) | +| MobileNet-V1-SSLD | 416 | 8 | 270e | ---- | 30.6 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_ssld_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_mobilenet_v1_ssld_270e_coco.yml) | +| MobileNet-V1-SSLD | 320 | 8 | 270e | ---- | 28.4 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_ssld_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_mobilenet_v1_ssld_270e_coco.yml) | ### YOLOv3 on Pasacl VOC | 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 | 608 | 8 | 270e | - | 75.2 | [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) | -| MobileNet-V1 | 416 | 8 | 270e | - | 76.2 | [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) | -| MobileNet-V1 | 320 | 8 | 270e | - | 74.3 | [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) | -| MobileNet-V3 | 608 | 8 | 270e | - | 79.6 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v3_large_270e_voc.yml) | -| MobileNet-V3 | 416 | 8 | 270e | - | 78.6 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v3_large_270e_voc.yml) | -| MobileNet-V3 | 320 | 8 | 270e | - | 76.4 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v3_large_270e_voc.yml) | -| MobileNet-V1-SSLD | 608 | 8 | 270e | - | 78.3 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_ssld_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_ssld_270e_voc.yml) | -| MobileNet-V1-SSLD | 416 | 8 | 270e | - | 79.6 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_ssld_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_ssld_270e_voc.yml) | -| MobileNet-V1-SSLD | 320 | 8 | 270e | - | 77.3 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_ssld_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v1_ssld_270e_voc.yml) | -| MobileNet-V3-SSLD | 608 | 8 | 270e | - | 80.4 | [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 | 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) | +| MobileNet-V1 | 608 | 8 | 270e | - | 75.2 | [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/release/2.0/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml) | +| MobileNet-V1 | 416 | 8 | 270e | - | 76.2 | [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/release/2.0/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml) | +| MobileNet-V1 | 320 | 8 | 270e | - | 74.3 | [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/release/2.0/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml) | +| MobileNet-V3 | 608 | 8 | 270e | - | 79.6 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_mobilenet_v3_large_270e_voc.yml) | +| MobileNet-V3 | 416 | 8 | 270e | - | 78.6 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_mobilenet_v3_large_270e_voc.yml) | +| MobileNet-V3 | 320 | 8 | 270e | - | 76.4 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_mobilenet_v3_large_270e_voc.yml) | +| MobileNet-V1-SSLD | 608 | 8 | 270e | - | 78.3 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_ssld_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_mobilenet_v1_ssld_270e_voc.yml) | +| MobileNet-V1-SSLD | 416 | 8 | 270e | - | 79.6 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_ssld_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_mobilenet_v1_ssld_270e_voc.yml) | +| MobileNet-V1-SSLD | 320 | 8 | 270e | - | 77.3 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v1_ssld_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/yolov3/yolov3_mobilenet_v1_ssld_270e_voc.yml) | +| MobileNet-V3-SSLD | 608 | 8 | 270e | - | 80.4 | [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/release/2.0/configs/yolov3/yolov3_mobilenet_v3_large_ssld_270e_voc.yml) | +| 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/release/2.0/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/release/2.0/configs/yolov3/yolov3_mobilenet_v3_large_ssld_270e_voc.yml) | **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 -- GitLab