mirrors
/
PaddleClas
mirror of https://github.com/PaddlePaddle/PaddleClas.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

fix trt doc (#485) 

* fix trt doc

* update history
pull/490/head
littletomatodonkey 2020-12-16 12:01:32 +08:00 committed by GitHub
parent 3d5cde1aed
commit bcaf6a8528
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 42 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -7,6 +7,7 @@
PaddleClas is a toolset for image classification tasks prepared for the industry and academia. It helps users train better computer vision models and apply them in real scenarios.
**Recent update**
- 2020.12.16 Add support for TensorRT when using cpp inference to obain more obvious acceleration.
- 2020.12.06 Add `SE_HRNet_W64_C_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 84.75%.
- 2020.11.23 Add `GhostNet_x1_3_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 79.38%.
- 2020.11.09 Add `InceptionV3` architecture and pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 79.1%.
@ -15,7 +16,6 @@ PaddleClas is a toolset for image classification tasks prepared for the industry
- 2020.10.10 Add cpp inference demo and improve FAQ tutorial.
- 2020.09.17 Add `HRNet_W48_C_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 83.62%. Add `ResNet34_vd_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 79.72%.
- 2020.09.07 Add `HRNet_W18_C_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 81.16%.
- 2020.07.14 Add `Res2Net200_vd_26w_4s_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 85.13%. Add `Fix_ResNet50_vd_ssld_v2` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 84.00%.
- [more](./docs/en/update_history_en.md)
@ -76,7 +76,7 @@ PaddleClas is a toolset for image classification tasks prepared for the industry
- [Prediction based on training engine](./docs/en/tutorials/getting_started_en.md)
- [Python inference](./docs/en/tutorials/getting_started_en.md)
- [C++ inference](./deploy/cpp_infer/readme_en.md)
- [Serving deployment](./docs/en/extension/paddle_serving_en.md)
- [Serving deployment](./deploy/hubserving/readme_en.md)
- [Mobile](./deploy/lite/readme_en.md)
- [Model Quantization and Compression](docs/en/extension/paddle_quantization_en.md)
- Advanced tutorials

4
README_cn.md
View File

@ -8,6 +8,7 @@
**近期更新**
- 2020.12.16 添加对cpp预测的tensorRT支持，预测加速更明显。
- 2020.12.06 添加`SE_HRNet_W64_C_ssld`模型，在ImageNet-1k上Top-1 Acc可达84.75%。
- 2020.11.23 添加`GhostNet_x1_3_ssld `模型，在ImageNet-1k上Top-1 Acc可达79.38%。
- 2020.11.18 添加图像分类[常见问题2020第一季第三期](./docs/zh_CN/faq_series/faq_2020_s1.md) 5个新问题，并且计划以后每周会更新，欢迎大家持续关注。
@ -17,7 +18,6 @@
- 2020.10.10 添加cpp inference demo，完善`FAQ 30问`教程。
- 2020.09.17 添加 `HRNet_W48_C_ssld `模型，在ImageNet-1k上Top-1 Acc可达83.62%；添加 `ResNet34_vd_ssld `模型，在ImageNet-1k上Top-1 Acc可达79.72%。
- 2020.09.07 添加 `HRNet_W18_C_ssld `模型，在ImageNet-1k上Top-1 Acc可达81.16%；添加 `MobileNetV3_small_x0_35_ssld `模型，在ImageNet-1k上Top-1 Acc可达55.55%。
- 2020.07.14 添加 `Res2Net200_vd_26w_4s_ssld `模型，在ImageNet-1k上Top-1 Acc可达85.13%；添加 `Fix_ResNet50_vd_ssld_v2 `模型，在ImageNet-1k上Top-1 Acc可达84.0%。
- [more](./docs/zh_CN/update_history.md)
@ -78,7 +78,7 @@
- [基于训练引擎预测推理](./docs/zh_CN/tutorials/getting_started.md)
- [基于Python预测引擎预测推理](./docs/zh_CN/tutorials/getting_started.md)
- [基于C++预测引擎预测推理](./deploy/cpp_infer/readme.md)
- [服务化部署](./docs/zh_CN/extension/paddle_serving.md)
- [服务化部署](./deploy/hubserving/readme.md)
- [端侧部署](./deploy/lite/readme.md)
- [模型量化压缩](docs/zh_CN/extension/paddle_quantization.md)
- 高阶使用

BIN
deploy/cpp_infer/docs/imgs/cpp_infer_result.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 28 KiB

After

Width:  |  Height:  |  Size: 42 KiB

6
deploy/cpp_infer/readme.md
View File

@ -164,6 +164,7 @@ OPENCV_DIR=your_opencv_dir
LIB_DIR=your_paddle_inference_dir
CUDA_LIB_DIR=your_cuda_lib_dir
CUDNN_LIB_DIR=your_cudnn_lib_dir
TENSORRT_DIR=your_tensorrt_lib_dir
BUILD_DIR=build
rm -rf ${BUILD_DIR}
@ -176,6 +177,7 @@ cmake .. \
-DWITH_GPU=OFF \
-DWITH_STATIC_LIB=OFF \
-DWITH_TENSORRT=OFF \
-DTENSORRT_DIR=${TENSORRT_DIR} \
-DOPENCV_DIR=${OPENCV_DIR} \
-DCUDNN_LIB=${CUDNN_LIB_DIR} \
-DCUDA_LIB=${CUDA_LIB_DIR} \
@ -193,6 +195,8 @@ make -j
* `CUDNN_LIB_DIR`为cudnn库文件地址，在docker中为`/usr/lib/x86_64-linux-gnu/`。
* `TENSORRT_DIR`是tensorrt库文件地址，在dokcer中为`/usr/local/TensorRT6-cuda10.0-cudnn7/`，TensorRT需要结合GPU使用。
在执行上述命令，编译完成之后，会在当前路径下生成`build`文件夹，其中生成一个名为`clas_system`的可执行文件。
@ -203,6 +207,8 @@ make -j
* gpu_mem：显存；
* cpu_math_library_num_threads：底层科学计算库所用线程的数量；
* use_mkldnn：是否使用MKLDNN加速；
* use_tensorrt: 是否使用tensorRT进行加速；
* use_fp16：是否使用半精度浮点数进行计算，该选项仅在use_tensorrt为true时有效；
* cls_model_path：预测模型结构文件路径；
* cls_params_path：预测模型参数文件路径；
* resize_short_size：预处理时图像缩放大小；

24
deploy/cpp_infer/readme_en.md
View File

@ -172,6 +172,7 @@ OPENCV_DIR=your_opencv_dir
LIB_DIR=your_paddle_inference_dir
CUDA_LIB_DIR=your_cuda_lib_dir
CUDNN_LIB_DIR=your_cudnn_lib_dir
TENSORRT_DIR=your_tensorrt_lib_dir
BUILD_DIR=build
rm -rf ${BUILD_DIR}
@ -180,10 +181,11 @@ cd ${BUILD_DIR}
cmake .. \
-DPADDLE_LIB=${LIB_DIR} \
-DWITH_MKL=ON \
-DDEMO_NAME=ocr_system \
-DDEMO_NAME=clas_system \
-DWITH_GPU=OFF \
-DWITH_STATIC_LIB=OFF \
-DWITH_TENSORRT=OFF \
-DTENSORRT_DIR=${TENSORRT_DIR} \
-DOPENCV_DIR=${OPENCV_DIR} \
-DCUDNN_LIB=${CUDNN_LIB_DIR} \
-DCUDA_LIB=${CUDA_LIB_DIR} \
@ -201,11 +203,29 @@ In the above parameters of command:
* `CUDNN_LIB_DIR` is the cudnn library file path, in docker it is `/usr/lib/x86_64-linux-gnu/`.
* `TENSORRT_DIR` is the tensorrt library file path，in dokcer it is `/usr/local/TensorRT6-cuda10.0-cudnn7/`，TensorRT is just enabled for GPU.
After the compilation is completed, an executable file named `clas_system` will be generated in the `build` folder.
### Run the demo
* First, please modify the `tools/config.txt` and `tools/run.sh`. Then execute the following command to complete the classification of an image.
* First, please modify the `tools/config.txt` and `tools/run.sh`.
* Some key words in `tools/config.txt` is as follows.
* use_gpu: Whether to use GPU.
* gpu_id: GPU id.
* gpu_mem：GPU memory.
* cpu_math_library_num_threads：Number of thread for math library acceleration.
* use_mkldnn：Whether to use mkldnn.
* use_tensorrt: Whether to use tensorRT.
* use_fp16：Whether to use Float16 (half precision), it is just enabled when use_tensorrt is set as 1.
* cls_model_path: Model path of inference model.
* cls_params_path: Params path of inference model.
* resize_short_size：Short side length of the image after resize.
* crop_size：Image size after center crop.
* Then execute the following command to complete the classification of an image.
```shell
sh tools/run.sh

7
docs/en/update_history_en.md
View File

@ -1,14 +1,17 @@
# Release Notes
- 2020.12.16
* Add support for TensorRT when using cpp inference to obain more obvious acceleration.
- 2020.12.06
* Add `SE_HRNet_W64_C_ssld` pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 84.75%.
- 2020.11.23
* Add `GhostNet_x1_3_ssld` pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 79.38%.
- 2020.11.09
* Add `InceptionV3` architecture and pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 79.1%.
* 2020.10.20
* Add `Res2Net50_vd_26w_4s_ssld` pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 83.1%.
* Add `Res2Net101_vd_26w_4s_ssld` pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 83.9%.

7
docs/zh_CN/update_history.md
View File

@ -1,14 +1,17 @@
# 更新日志
- 2020.12.16
* 添加对cpp预测的tensorRT支持，预测加速更明显。
- 2020.12.06
* 添加SE_HRNet_W64_C_ssld模型，在ImageNet上Top-1 Acc可达0.8475。
- 2020.11.23
* 添加GhostNet_x1_3_ssld模型，在ImageNet上Top-1 Acc可达0.7938。
- 2020.11.09
* 添加InceptionV3结构和模型，在ImageNet上Top-1 Acc可达0.791。
- 2020.10.20
* 添加Res2Net50_vd_26w_4s_ssld模型，在ImageNet上Top-1 Acc可达0.831；添加Res2Net101_vd_26w_4s_ssld模型，在ImageNet上Top-1 Acc可达0.839。