diff --git a/configs/picodet/README.md b/configs/picodet/README.md index c9fc2548d806cc6f1d800264a3236d5dfa23309a..a91ac22cb7d75341d9ec532bd3bef2afb067b9e1 100644 --- a/configs/picodet/README.md +++ b/configs/picodet/README.md @@ -7,9 +7,9 @@ ## 最新动态 - 发布全新系列PP-PicoDet模型：**（2022.03.20）** - - (1)引入TAL及ETA Head，优化PAN等结构，精度大幅提升； - - (2)优化CPU端预测速度，同时训练速度大幅提升； - - (3)导出模型将后处理包含在网络中，预测直接输出box结果，无需二次开发，迁移成本更低。 + - (1)引入TAL及ETA Head，优化PAN等结构，精度提升2个点以上； + - (2)优化CPU端预测速度，同时训练速度提升一倍； + - (3)导出模型将后处理包含在网络中，预测直接输出box结果，无需二次开发，迁移成本更低，端到端预测速度提升10%-20%。 ## 历史版本模型 @@ -33,7 +33,7 @@ PP-PicoDet模型有如下特点： ## 基线 -| 模型 | 输入尺寸 | mAPval
0.5:0.95 | mAPval
0.5 | 参数量
(M) | FLOPS
(G) | 预测时延[CPU](#latency)
(ms) | 预测时延[Lite](#latency)
(ms) | 下载 | 配置文件 | 导出模型 | +| 模型 | 输入尺寸 | mAPval
0.5:0.95 | mAPval
0.5 | 参数量
(M) | FLOPS
(G) | 预测时延[CPU](#latency)
(ms) | 预测时延[Lite](#latency)
(ms) | 权重下载 | 配置文件 | 导出模型 | | :-------- | :--------: | :---------------------: | :----------------: | :----------------: | :---------------: | :-----------------------------: | :-----------------------------: | :----------------------------------------: | :--------------------------------------- | :--------------------------------------- | | PicoDet-XS | 320*320 | 23.5 | 36.1 | 0.70 | 0.67 | 3.9ms | 7.81ms | [model](https://paddledet.bj.bcebos.com/models/picodet_xs_320_coco_lcnet.pdparams) | [log](https://paddledet.bj.bcebos.com/logs/train_picodet_xs_320_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/picodet/picodet_xs_320_coco_lcnet.yml) | [w/ 后处理](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_xs_320_coco_lcnet.tar) | [w/o 后处理](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_xs_320_coco_lcnet_non_postprocess.tar) | | PicoDet-XS | 416*416 | 26.2 | 39.3 | 0.70 | 1.13 | 6.1ms | 12.38ms | [model](https://paddledet.bj.bcebos.com/models/picodet_xs_416_coco_lcnet.pdparams) | [log](https://paddledet.bj.bcebos.com/logs/train_picodet_xs_416_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/picodet/picodet_xs_416_coco_lcnet.yml) | [w/ 后处理](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_xs_416_coco_lcnet.tar) | [w/o 后处理](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_xs_416_coco_lcnet_non_postprocess.tar) | @@ -48,7 +48,7 @@ PP-PicoDet模型有如下特点：
注意事项: -- 时延测试： 我们所有的模型都在英特尔酷睿i7 10750H 的CPU 和`骁龙865(4xA77+4xA55)`的ARM CPU上测试(4线程，FP16预测)。上面表格中标有`CPU`的是使用OpenVINO测试，标有`Lite`的是使用[Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite)进行测试。 +- 时延测试： 我们所有的模型都在`英特尔酷睿i7 10750H`的CPU 和`骁龙865(4xA77+4xA55)`的ARM CPU上测试(4线程，FP16预测)。上面表格中标有`CPU`的是使用OpenVINO测试，标有`Lite`的是使用[Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite)进行测试。 - PicoDet在COCO train2017上训练，并且在COCO val2017上进行验证。使用4卡GPU训练，并且上表所有的预训练模型都是通过发布的默认配置训练得到。 - Benchmark测试：测试速度benchmark性能时，导出模型后处理不包含在网络中，需要设置`-o export.benchmark=True` 或手动修改[runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/configs/runtime.yml#L12)。 @@ -107,10 +107,12 @@ python tools/train.py -c configs/picodet/picodet_s_320_coco_lcnet.yml --eval ```shell # training on multi-GPU -export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 -python -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/picodet/picodet_s_320_coco_lcnet.yml --eval +export CUDA_VISIBLE_DEVICES=0,1,2,3 +python -m paddle.distributed.launch --gpus 0,1,2,3 tools/train.py -c configs/picodet/picodet_s_320_coco_lcnet.yml --eval ``` +**注意：**PicoDet所有模型均由4卡GPU训练得到，如果改变训练GPU卡数，需要按线性比例缩放学习率base_lr。 + - 评估: ```shell @@ -134,8 +136,8 @@ python tools/infer.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \ ### 导出及转换模型 -
-1. 导出模型 (点击展开) +
+1. 导出模型 ```shell cd PaddleDetection @@ -145,7 +147,7 @@ python tools/export_model.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \ ``` - 如无需导出后处理，请指定：`-o export.benchmark=True`（如果-o已出现过，此处删掉-o）或者手动修改[runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/configs/runtime.yml) 中相应字段。 -- 如无需导出NMS，请指定：`-o export.nms=False`或者手动修改[runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/configs/runtime.yml) 中相应字段。 +- 如无需导出NMS，请指定：`-o export.nms=False`或者手动修改[runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/configs/runtime.yml) 中相应字段。许多导出至ONNX场景只支持单输入及固定shape输出，所以如果导出至ONNX，推荐不导出NMS。
@@ -200,28 +202,34 @@ paddle2onnx --model_dir output_inference/picodet_s_320_coco_lcnet/ \ python -m onnxsim picodet_s_320_coco.onnx picodet_s_processed.onnx ``` + 如果模型包含所有后处理，简化模型时需要指定`dynamic-input-shape`： + ```shell + python -m onnxsim picodet_s_320_coco.onnx picodet_s_processed.onnx --dynamic-input-shape --input-shape image:1,3,320,320 + ``` +
- 部署用的模型 | 模型 | 输入尺寸 | ONNX( w/o 后处理) | Paddle Lite(fp32) | Paddle Lite(fp16) | | :-------- | :--------: | :---------------------: | :----------------: | :----------------: | -| PicoDet-XS | 320*320 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_320_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_320.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_320_fp16.tar) | -| PicoDet-XS | 416*416 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_416_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_416.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_416_fp16.tar) | -| PicoDet-S | 320*320 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_320_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_320.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_320_fp16.tar) | -| PicoDet-S | 416*416 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_416_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_fp16.tar) | -| PicoDet-M | 320*320 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_320_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_320.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_320_fp16.tar) | -| PicoDet-M | 416*416 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_416_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_416.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_416_fp16.tar) | -| PicoDet-L | 320*320 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_320_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_320.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_320_fp16.tar) | -| PicoDet-L | 416*416 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_416_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_416.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_416_fp16.tar) | -| PicoDet-L | 640*640 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_640_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_640_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_640.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_640_fp16.tar) | +| PicoDet-XS | 320*320 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_320_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_320_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_320_coco_lcnet_fp16.tar) | +| PicoDet-XS | 416*416 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_416_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_416_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_416_coco_lcnet_fp16.tar) | +| PicoDet-S | 320*320 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_320_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_320_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_320_coco_lcnet_fp16.tar) | +| PicoDet-S | 416*416 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_416_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_coco_lcnet_fp16.tar) | +| PicoDet-M | 320*320 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_320_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_320_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_320_coco_lcnet_fp16.tar) | +| PicoDet-M | 416*416 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_416_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_416_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_416_coco_lcnet_fp16.tar) | +| PicoDet-L | 320*320 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_320_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_320_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_320_coco_lcnet_fp16.tar) | +| PicoDet-L | 416*416 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_416_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_416_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_416_coco_lcnet_fp16.tar) | +| PicoDet-L | 640*640 | [( w/ 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_640_lcnet_postprocessed.onnx) | [( w/o 后处理)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_640_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_640_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_640_coco_lcnet_fp16.tar) | ### 部署 -- OpenVINO demo [Python](../../deploy/third_engine/demo/openvino/python) +- OpenVINO demo [Python](../../deploy/third_engine/demo_openvino/python) - [PaddleLite C++ demo](../../deploy/lite) - [Android demo(Paddle Lite)](https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/develop/object_detection/android/app/cxx/picodet_detection_demo) +- ONNXRuntime demo [Python](../../deploy/third_engine/demo_onnxruntime) - PaddleInference demo [Python](../../deploy/python) & [C++](../../deploy/cpp) @@ -272,7 +280,7 @@ python tools/train.py -c configs/picodet/picodet_s_416_coco_lcnet.yml \
教程: -训练及部署细节请参考[非结构化剪枝文档](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/picodet/pruner/README.md)。 +训练及部署细节请参考[非结构化剪枝文档](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/picodet/legacy_model/pruner/README.md)。
diff --git a/configs/picodet/README_en.md b/configs/picodet/README_en.md index 4874717290bf356126dd48ae1fb7ceb3e7bdf4bc..94072ffb41ec29a57129ad9e09a54f3e85ffa0d2 100644 --- a/configs/picodet/README_en.md +++ b/configs/picodet/README_en.md @@ -31,7 +31,7 @@ We release/2.4ed a series of lightweight models, named `PP-PicoDet`. Because of ## Benchmark -| Model | Input size | mAPval
0.5:0.95 | mAPval
0.5 | Params
(M) | FLOPS
(G) | Latency[CPU](#latency)
(ms) | Latency[Lite](#latency)
(ms) | Download | Config | Inference Model | +| Model | Input size | mAPval
0.5:0.95 | mAPval
0.5 | Params
(M) | FLOPS
(G) | Latency[CPU](#latency)
(ms) | Latency[Lite](#latency)
(ms) | Weight | Config | Inference Model | | :-------- | :--------: | :---------------------: | :----------------: | :----------------: | :---------------: | :-----------------------------: | :-----------------------------: | :----------------------------------------: | :--------------------------------------- | :--------------------------------------- | | PicoDet-XS | 320*320 | 23.5 | 36.1 | 0.70 | 0.67 | 3.9ms | 7.81ms | [model](https://paddledet.bj.bcebos.com/models/picodet_xs_320_coco_lcnet.pdparams) | [log](https://paddledet.bj.bcebos.com/logs/train_picodet_xs_320_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/picodet/picodet_xs_320_coco_lcnet.yml) | [w/ postprocess](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_xs_320_coco_lcnet.tar) | [w/o postprocess](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_xs_320_coco_lcnet_non_postprocess.tar) | | PicoDet-XS | 416*416 | 26.2 | 39.3 | 0.70 | 1.13 | 6.1ms | 12.38ms | [model](https://paddledet.bj.bcebos.com/models/picodet_xs_416_coco_lcnet.pdparams) | [log](https://paddledet.bj.bcebos.com/logs/train_picodet_xs_416_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/picodet/picodet_xs_416_coco_lcnet.yml) | [w/ postprocess](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_xs_416_coco_lcnet.tar) | [w/o postprocess](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_xs_416_coco_lcnet_non_postprocess.tar) | @@ -131,8 +131,8 @@ Detail also can refer to [Quick start guide](https://github.com/PaddlePaddle/Pad ### Export and Convert Model -
-1. Export model (click to expand) +
+1. Export model ```shell cd PaddleDetection @@ -142,7 +142,7 @@ python tools/export_model.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \ ``` - If no post processing is required, please specify: `-o export.benchmark=True` (if -o has already appeared, delete -o here) or manually modify corresponding fields in [runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/configs/runtime.yml). -- If no NMS is required, please specify: `-o export.nms=True` or manually modify corresponding fields in [runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/configs/runtime.yml). +- If no NMS is required, please specify: `-o export.nms=True` or manually modify corresponding fields in [runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/configs/runtime.yml). Many scenes exported to ONNX only support single input and fixed shape output, so if exporting to ONNX, it is recommended not to export NMS.
@@ -198,27 +198,33 @@ paddle2onnx --model_dir output_inference/picodet_s_320_coco_lcnet/ \ python -m onnxsim picodet_s_320_coco.onnx picodet_s_processed.onnx ``` + If the model includes postprocessing, specify `dynamic-input-shape` when simplifying the model: + ```shell + python -m onnxsim picodet_s_320_coco.onnx picodet_s_processed.onnx --dynamic-input-shape --input-shape image:1,3,320,320 + ``` +
- Deploy models | Model | Input size | ONNX(w/o postprocess) | Paddle Lite(fp32) | Paddle Lite(fp16) | | :-------- | :--------: | :---------------------: | :----------------: | :----------------: | -| PicoDet-XS | 320*320 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_320_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_320.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_320_fp16.tar) | -| PicoDet-XS | 416*416 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_416_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_416.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_416_fp16.tar) | -| PicoDet-S | 320*320 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_320_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_320.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_320_fp16.tar) | -| PicoDet-S | 416*416 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_416_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_fp16.tar) | -| PicoDet-M | 320*320 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_320_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_320.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_320_fp16.tar) | -| PicoDet-M | 416*416 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_416_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_416.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_416_fp16.tar) | -| PicoDet-L | 320*320 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_320_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_320.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_320_fp16.tar) | -| PicoDet-L | 416*416 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_416_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_416.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_416_fp16.tar) | -| PicoDet-L | 640*640 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_640_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_640_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_640.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_640_fp16.tar) | +| PicoDet-XS | 320*320 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_320_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_320_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_320_coco_lcnet_fp16.tar) | +| PicoDet-XS | 416*416 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_416_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_xs_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_416_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_xs_416_coco_lcnet_fp16.tar) | +| PicoDet-S | 320*320 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_320_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_320_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_320_coco_lcnet_fp16.tar) | +| PicoDet-S | 416*416 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_416_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_coco_lcnet_fp16.tar) | +| PicoDet-M | 320*320 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_320_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_320_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_320_coco_lcnet_fp16.tar) | +| PicoDet-M | 416*416 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_416_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_m_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_416_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_m_416_coco_lcnet_fp16.tar) | +| PicoDet-L | 320*320 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_320_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_320_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_320_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_320_coco_lcnet_fp16.tar) | +| PicoDet-L | 416*416 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_416_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_416_coco_lcnet.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_416_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_416_coco_lcnet_fp16.tar) | +| PicoDet-L | 640*640 | [( w/ postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_640_lcnet_postprocessed.onnx) | [( w/o postprocess)](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_l_640_coco_lcnet.onnx) [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_640_coco_lcnet.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_l_640_coco_lcnet_fp16.tar) | ### Deploy -- OpenVINO demo [Python](../../deploy/third_engine/demo/openvino/python) +- OpenVINO demo [Python](../../deploy/third_engine/demo_openvino/python) - [PaddleLite C++ demo](../../deploy/lite) - [Android demo(Paddle Lite)](https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/develop/object_detection/android/app/cxx/picodet_detection_demo) +- ONNXRuntime demo [Python](../../deploy/third_engine/demo_onnxruntime) - PaddleInference demo [Python](../../deploy/python) & [C++](../../deploy/cpp) @@ -269,7 +275,8 @@ python tools/train.py -c configs/picodet/picodet_s_416_coco_lcnet.yml \
Toturial: -Please refer this [documentation](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/picodet/pruner/README.md) for details such as requirements, training and deployment. +Please refer this [documentation](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/picodet/legacy_model/pruner/README.md) for details such as requirements, training and deployment. +
diff --git a/deploy/third_engine/demo_openvino/python/README.md b/deploy/third_engine/demo_openvino/python/README.md index 34ac8cae8b41a122390d07d7430fea7c81417b4a..629336d5f780bddc831d1b5dc4d1cc0779990959 100644 --- a/deploy/third_engine/demo_openvino/python/README.md +++ b/deploy/third_engine/demo_openvino/python/README.md @@ -19,7 +19,6 @@ pip install openvino==2022.1.0 - 准备测试所用图片：本demo默认利用PaddleDetection/demo/[000000014439.jpg](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/demo/000000014439.jpg) -### Benchmark - 在本目录下直接运行： ```shell @@ -30,16 +29,7 @@ python openvino_benchmark.py --img_path ..\..\..\..\demo\000000014439.jpg --onnx ``` - 注意：```--in_shape```为对应模型输入size，默认为320 -### Inference images(w/o 后处理) - -```shell -# Linux -python openvino_benchmark.py --benchmark 0 --img_path ../../../../demo/000000014439.jpg --onnx_path out_onnxsim/picodet_s_320_coco_lcnet.onnx --in_shape 320 -# Windows -python openvino_benchmark.py --benchmark 0 --img_path ..\..\..\..\demo\000000014439.jpg --onnx_path out_onnxsim\picodet_s_320_coco_lcnet.onnx --in_shape 320 -``` - -## Inference images(w/ 后处理, w/o NMS) +## 真实图片测试(网络包含后处理，但不包含NMS) - 准备测试模型：根据[PicoDet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/picodet)中【导出及转换模型】步骤，采用**包含后处理**但**不包含NMS**的方式导出模型（`-o export.benchmark=False export.nms=False` ），并生成待测试模型简化后的onnx模型（可在下文链接中直接下载）。同时在本目录下新建```out_onnxsim_infer```文件夹，将导出的onnx模型放在该目录下。 @@ -51,12 +41,22 @@ python openvino_infer.py --img_path ../../demo_onnxruntime/imgs/bus.jpg --onnx_p # Windows python openvino_infer.py --img_path ..\..\demo_onnxruntime\imgs\bus.jpg --onnx_path out_onnxsim_infer\picodet_s_320_postproccesed_woNMS.onnx --in_shape 320 ``` + +### 真实图片测试(网络不包含后处理) + +```shell +# Linux +python openvino_benchmark.py --benchmark 0 --img_path ../../../../demo/000000014439.jpg --onnx_path out_onnxsim/picodet_s_320_coco_lcnet.onnx --in_shape 320 +# Windows +python openvino_benchmark.py --benchmark 0 --img_path ..\..\..\..\demo\000000014439.jpg --onnx_path out_onnxsim\picodet_s_320_coco_lcnet.onnx --in_shape 320 +``` + - 结果：
-## 结果 +## Benchmark结果 - 测速结果如下：