未验证 提交 6ff6842b 编写于 作者: W wangxinxin08 提交者: GitHub

fix introduction of detection models (#5592)

* fix introduction of detection models

* add ppyolov2 infer result

* fix PP-YOLOE+ intro
上级 4e108cd5
...@@ -24,7 +24,7 @@ ...@@ -24,7 +24,7 @@
"## 2. 模型效果\n", "## 2. 模型效果\n",
"PP-Picodet与其他轻量级模型的精度速度对比图如下所示:\n", "PP-Picodet与其他轻量级模型的精度速度对比图如下所示:\n",
"<div align=\"center\">\n", "<div align=\"center\">\n",
" <img src=\"https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/docs/images/picodet_map.png\" width=500 />\n", " <img src=\"https://raw.githubusercontent.com/PaddlePaddle/PaddleDetection/release/2.5/docs/images/picodet_map.png\" width=500 />\n",
"</div>" "</div>"
] ]
}, },
...@@ -37,12 +37,19 @@ ...@@ -37,12 +37,19 @@
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "code",
"metadata": {}, "execution_count": null,
"metadata": {
"vscode": {
"languageId": "plaintext"
}
},
"outputs": [],
"source": [ "source": [
"%cd ~/work\n", "%cd ~/work\n",
"!git clone https://gitee.com/paddlepaddle/PaddleDetection\n", "!git clone https://gitee.com/paddlepaddle/PaddleDetection\n",
"%cd PaddleDetection" "%cd PaddleDetection\n",
"!pip install -r requirements.txt"
] ]
}, },
{ {
......
...@@ -23,7 +23,7 @@ ...@@ -23,7 +23,7 @@
"## 2. Model Effects\n", "## 2. Model Effects\n",
"The accuracy and speed comparison of PP-Picodet and other lightweight models is shown below:\n", "The accuracy and speed comparison of PP-Picodet and other lightweight models is shown below:\n",
"<div align=\"center\">\n", "<div align=\"center\">\n",
" <img src=\"https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/docs/images/picodet_map.png\" width=500 />\n", " <img src=\"https://raw.githubusercontent.com/PaddlePaddle/PaddleDetection/release/2.5/docs/images/picodet_map.png\" width=500 />\n",
"</div>" "</div>"
] ]
}, },
...@@ -47,7 +47,8 @@ ...@@ -47,7 +47,8 @@
"source": [ "source": [
"%cd ~/work\n", "%cd ~/work\n",
"!git clone https://gitee.com/paddlepaddle/PaddleDetection\n", "!git clone https://gitee.com/paddlepaddle/PaddleDetection\n",
"%cd PaddleDetection" "%cd PaddleDetection\n",
"!pip install -r requirements.txt"
] ]
}, },
{ {
......
...@@ -16,7 +16,7 @@ ...@@ -16,7 +16,7 @@
"PP-YOLO在[COCO](http://cocodataset.org) test-dev2017数据集上精度达到45.9%,在单卡V100上FP32推理速度为72.9 FPS, V100上开启TensorRT下FP16推理速度为155.6 FPS。\n", "PP-YOLO在[COCO](http://cocodataset.org) test-dev2017数据集上精度达到45.9%,在单卡V100上FP32推理速度为72.9 FPS, V100上开启TensorRT下FP16推理速度为155.6 FPS。\n",
"\n", "\n",
"<div align=\"center\">\n", "<div align=\"center\">\n",
" <img src=\"https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/docs/images/ppyolo_map_fps.png\" width=500 />\n", " <img src=\"https://raw.githubusercontent.com/PaddlePaddle/PaddleDetection/release/2.5/docs/images/ppyolo_map_fps.png\" width=500 />\n",
"</div>" "</div>"
] ]
}, },
...@@ -40,7 +40,8 @@ ...@@ -40,7 +40,8 @@
"source": [ "source": [
"%cd ~/work\n", "%cd ~/work\n",
"!git clone https://gitee.com/paddlepaddle/PaddleDetection\n", "!git clone https://gitee.com/paddlepaddle/PaddleDetection\n",
"%cd PaddleDetection" "%cd PaddleDetection\n",
"!pip install -r requirements.txt"
] ]
}, },
{ {
...@@ -61,7 +62,7 @@ ...@@ -61,7 +62,7 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"!python -m paddle.distributed.launch --log_dir=./ppyolo_dygraph/ --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml &>ppyolo_dygraph.log 2>&1 &" "!python -m paddle.distributed.launch --log_dir=./ppyolo_dygraph/ --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml"
] ]
}, },
{ {
......
...@@ -16,7 +16,7 @@ ...@@ -16,7 +16,7 @@
"PP-YOLO reached mmAP(IoU=0.5:0.95) as 45.9% on COCO test-dev2017 dataset, and inference speed of FP32 on single V100 is 72.9 FPS, inference speed of FP16 with TensorRT on single V100 is 155.6 FPS.\n", "PP-YOLO reached mmAP(IoU=0.5:0.95) as 45.9% on COCO test-dev2017 dataset, and inference speed of FP32 on single V100 is 72.9 FPS, inference speed of FP16 with TensorRT on single V100 is 155.6 FPS.\n",
"\n", "\n",
"<div align=\"center\">\n", "<div align=\"center\">\n",
" <img src=\"https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/docs/images/ppyolo_map_fps.png\" width=500 />\n", " <img src=\"https://raw.githubusercontent.com/PaddlePaddle/PaddleDetection/release/2.5/docs/images/ppyolo_map_fps.png\" width=500 />\n",
"</div>" "</div>"
] ]
}, },
...@@ -40,7 +40,8 @@ ...@@ -40,7 +40,8 @@
"source": [ "source": [
"%cd ~/work\n", "%cd ~/work\n",
"!git clone https://gitee.com/paddlepaddle/PaddleDetection\n", "!git clone https://gitee.com/paddlepaddle/PaddleDetection\n",
"%cd PaddleDetection" "%cd PaddleDetection\n",
"!pip install -r requirements.txt"
] ]
}, },
{ {
...@@ -61,7 +62,7 @@ ...@@ -61,7 +62,7 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"!python -m paddle.distributed.launch --log_dir=./ppyolo_dygraph/ --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml &>ppyolo_dygraph.log 2>&1 &" "!python -m paddle.distributed.launch --log_dir=./ppyolo_dygraph/ --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml"
] ]
}, },
{ {
......
...@@ -15,7 +15,7 @@ ...@@ -15,7 +15,7 @@
"## 2. 模型效果\n", "## 2. 模型效果\n",
"PP-YOLOE+_l在COCO test-dev2017达到了53.3的mAP, 同时其速度在Tesla V100上达到了78.1 FPS。如下图所示,PP-YOLOE+_s/m/x同样具有卓越的精度速度性价比。\n", "PP-YOLOE+_l在COCO test-dev2017达到了53.3的mAP, 同时其速度在Tesla V100上达到了78.1 FPS。如下图所示,PP-YOLOE+_s/m/x同样具有卓越的精度速度性价比。\n",
"<div align=\"center\">\n", "<div align=\"center\">\n",
" <img src=\"https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/docs/images/ppyoloe_plus_map_fps.png\" width=500 />\n", " <img src=\"https://raw.githubusercontent.com/PaddlePaddle/PaddleDetection/release/2.5/docs/images/ppyoloe_plus_map_fps.png\" width=500 />\n",
"</div>" "</div>"
] ]
}, },
...@@ -28,12 +28,19 @@ ...@@ -28,12 +28,19 @@
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "code",
"metadata": {}, "execution_count": null,
"metadata": {
"vscode": {
"languageId": "plaintext"
}
},
"outputs": [],
"source": [ "source": [
"%cd ~/work\n", "%cd ~/work\n",
"!git clone https://gitee.com/paddlepaddle/PaddleDetection\n", "!git clone https://gitee.com/paddlepaddle/PaddleDetection\n",
"%cd PaddleDetection" "%cd PaddleDetection\n",
"!pip install -r requirements.txt"
] ]
}, },
{ {
...@@ -114,10 +121,10 @@ ...@@ -114,10 +121,10 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"# 推理单张图片\n", "# 推理单张图片\n",
"CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_mode=trt_fp16\n", "!CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_mode=trt_fp16\n",
"\n", "\n",
"# 推理文件夹下的所有图片\n", "# 推理文件夹下的所有图片\n",
"CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_dir=demo/ --device=gpu --run_mode=trt_fp16" "!CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_dir=demo/ --device=gpu --run_mode=trt_fp16"
] ]
}, },
{ {
...@@ -168,10 +175,10 @@ ...@@ -168,10 +175,10 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"# 推理单张图片\n", "# 推理单张图片\n",
"CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_mode=paddle\n", "!CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_mode=paddle\n",
"\n", "\n",
"# 推理文件夹下的所有图片\n", "# 推理文件夹下的所有图片\n",
"CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_dir=demo/ --device=gpu --run_mode=paddle" "!CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_dir=demo/ --device=gpu --run_mode=paddle"
] ]
}, },
{ {
......
...@@ -15,7 +15,7 @@ ...@@ -15,7 +15,7 @@
"## 2. Model Effects\n", "## 2. Model Effects\n",
"PP-YOLOE+_l achieves 53.3 mAP on COCO test-dev2017 dataset with 78.1 FPS on Tesla V100. While using TensorRT FP16, PP-YOLOE+_l can be further accelerated to 149.2 FPS. PP-YOLOE+_s/m/x also have excellent accuracy and speed performance as shown below.\n", "PP-YOLOE+_l achieves 53.3 mAP on COCO test-dev2017 dataset with 78.1 FPS on Tesla V100. While using TensorRT FP16, PP-YOLOE+_l can be further accelerated to 149.2 FPS. PP-YOLOE+_s/m/x also have excellent accuracy and speed performance as shown below.\n",
"<div align=\"center\">\n", "<div align=\"center\">\n",
" <img src=\"https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/docs/images/ppyoloe_plus_map_fps.png\" width=500 />\n", " <img src=\"https://raw.githubusercontent.com/PaddlePaddle/PaddleDetection/release/2.5/docs/images/ppyoloe_plus_map_fps.png\" width=500 />\n",
"</div>" "</div>"
] ]
}, },
...@@ -39,7 +39,8 @@ ...@@ -39,7 +39,8 @@
"source": [ "source": [
"%cd ~/work\n", "%cd ~/work\n",
"!git clone https://gitee.com/paddlepaddle/PaddleDetection\n", "!git clone https://gitee.com/paddlepaddle/PaddleDetection\n",
"%cd PaddleDetection" "%cd PaddleDetection\n",
"!pip install -r requirements.txt"
] ]
}, },
{ {
...@@ -120,10 +121,10 @@ ...@@ -120,10 +121,10 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"# inference single image\n", "# inference single image\n",
"CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_mode=trt_fp16\n", "!CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_mode=trt_fp16\n",
"\n", "\n",
"# inference all images in the directory\n", "# inference all images in the directory\n",
"CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_dir=demo/ --device=gpu --run_mode=trt_fp16" "!CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_dir=demo/ --device=gpu --run_mode=trt_fp16"
] ]
}, },
{ {
...@@ -180,10 +181,10 @@ ...@@ -180,10 +181,10 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"# inference single image\n", "# inference single image\n",
"CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_mode=paddle\n", "!CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_mode=paddle\n",
"\n", "\n",
"# inference all images in the directory\n", "# inference all images in the directory\n",
"CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_dir=demo/ --device=gpu --run_mode=paddle" "!CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_dir=demo/ --device=gpu --run_mode=paddle"
] ]
}, },
{ {
......
...@@ -39,7 +39,8 @@ ...@@ -39,7 +39,8 @@
"source": [ "source": [
"%cd ~/work\n", "%cd ~/work\n",
"!git clone https://gitee.com/paddlepaddle/PaddleDetection\n", "!git clone https://gitee.com/paddlepaddle/PaddleDetection\n",
"%cd PaddleDetection" "%cd PaddleDetection\n",
"!pip install -r requirements.txt"
] ]
}, },
{ {
......
...@@ -40,7 +40,8 @@ ...@@ -40,7 +40,8 @@
"source": [ "source": [
"%cd ~/work\n", "%cd ~/work\n",
"!git clone https://gitee.com/paddlepaddle/PaddleDetection\n", "!git clone https://gitee.com/paddlepaddle/PaddleDetection\n",
"%cd PaddleDetection" "%cd PaddleDetection\n",
"!pip install -r requirements.txt"
] ]
}, },
{ {
......
...@@ -153,8 +153,8 @@ ...@@ -153,8 +153,8 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"# 在GPU上预测一张图片\n", "# 在GPU上预测一张图片\n",
"export CUDA_VISIBLE_DEVICES=0\n", "!export CUDA_VISIBLE_DEVICES=0\n",
"python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o use_gpu=true weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --infer_img=demo/000000014439.jpg" "!python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o use_gpu=true weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --infer_img=demo/000000014439.jpg"
] ]
}, },
{ {
...@@ -165,7 +165,7 @@ ...@@ -165,7 +165,7 @@
"\n", "\n",
"结果如下图:\n", "结果如下图:\n",
"<div align=\"center\">\n", "<div align=\"center\">\n",
"<img src=\"https://user-images.githubusercontent.com/23690325/198869627-6e303b4c-04f6-4a48-b807-3dabafe04749.png\" width = \"80%\" />\n", "<img src=\"https://bj.bcebos.com/v1/paddledet/modelcenter/images/ppyolov2_infer.jpg\" width = \"60%\" />\n",
"</div>\n", "</div>\n",
"\n", "\n",
"\n" "\n"
......
...@@ -145,8 +145,8 @@ ...@@ -145,8 +145,8 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"# Predict a picture on the GPU.\n", "# Predict a picture on the GPU.\n",
"export CUDA_VISIBLE_DEVICES=0\n", "!export CUDA_VISIBLE_DEVICES=0\n",
"python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o use_gpu=true weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --infer_img=demo/000000014439.jpg" "!python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o use_gpu=true weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --infer_img=demo/000000014439.jpg"
] ]
}, },
{ {
...@@ -156,8 +156,9 @@ ...@@ -156,8 +156,9 @@
"An image with the predicted result is generated under the output folder.\n", "An image with the predicted result is generated under the output folder.\n",
"\n", "\n",
"The result is as follows:\n", "The result is as follows:\n",
"\n", "<div align=\"center\">\n",
"![](https://ai-studio-static-online.cdn.bcebos.com/76fb0d0b60fe4fe39cc7302f4c25818133f970ebdf924d2d85f70f25a586aab9)\n" "<img src=\"https://bj.bcebos.com/v1/paddledet/modelcenter/images/ppyolov2_infer.jpg\" width = \"60%\" />\n",
"</div>\n"
] ]
}, },
{ {
......
Markdown is supported
0% .
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