Skip to content

Latest commit

 

History

History
160 lines (106 loc) · 3.68 KB

YOLOX.md

File metadata and controls

160 lines (106 loc) · 3.68 KB

YOLOX usage

NOTE: You can use the main branch of the YOLOX repo to convert all model versions.

Convert model

1. Download the YOLOX repo and install the requirements

git clone https://github.com/Megvii-BaseDetection/YOLOX.git
cd YOLOX
pip3 install -r requirements.txt
python3 setup.py develop
pip3 install onnx onnxsim onnxruntime

NOTE: It is recommended to use Python virtualenv.

2. Copy conversor

Copy the export_yolox.py file from DeepStream-Yolo/utils directory to the YOLOX folder.

3. Download the model

Download the pth file from YOLOX releases (example for YOLOX-s)

wget https://github.com/Megvii-BaseDetection/YOLOX/releases/download/0.1.1rc0/yolox_s.pth

NOTE: You can use your custom model.

4. Convert model

Generate the ONNX model file (example for YOLOX-s)

python3 export_yolox.py -w yolox_s.pth -c exps/default/yolox_s.py --simplify

5. Copy generated files

Copy the generated ONNX model file to the DeepStream-Yolo folder.

Compile the lib

Open the DeepStream-Yolo folder and compile the lib

  • DeepStream 6.2 on x86 platform

    CUDA_VER=11.8 make -C nvdsinfer_custom_impl_Yolo

  • DeepStream 6.1.1 on x86 platform

    CUDA_VER=11.7 make -C nvdsinfer_custom_impl_Yolo

  • DeepStream 6.1 on x86 platform

    CUDA_VER=11.6 make -C nvdsinfer_custom_impl_Yolo

  • DeepStream 6.0.1 / 6.0 on x86 platform

    CUDA_VER=11.4 make -C nvdsinfer_custom_impl_Yolo

  • DeepStream 6.2 / 6.1.1 / 6.1 on Jetson platform

    CUDA_VER=11.4 make -C nvdsinfer_custom_impl_Yolo

  • DeepStream 6.0.1 / 6.0 on Jetson platform

    CUDA_VER=10.2 make -C nvdsinfer_custom_impl_Yolo

Edit the config_infer_primary_yolox file

Edit the config_infer_primary_yolox.txt file according to your model (example for YOLOX-s with 80 classes)

[property]
...
onnx-file=yolox_s.onnx
model-engine-file=yolox_s.onnx_b1_gpu0_fp32.engine
...
num-detected-classes=80
...
parse-bbox-func-name=NvDsInferParseYolo
...

NOTE: If you use the legacy model, you should edit the config_infer_primary_yolox_legacy.txt file.

NOTE: The YOLOX and YOLOX legacy resize the input with left/top padding. To get better accuracy, use

maintain-aspect-ratio=1
symmetric-padding=0

NOTE: The YOLOX uses no normalization on the image preprocess. It is important to change the net-scale-factor according to the trained values.

net-scale-factor=1

NOTE: The YOLOX legacy uses normalization on the image preprocess. It is important to change the net-scale-factor and offsets according to the trained values.

Default: mean = 0.485, 0.456, 0.406 and std = 0.229, 0.224, 0.225

net-scale-factor=0.0173520735727919486
offsets=123.675;116.28;103.53

Edit the deepstream_app_config file

...
[primary-gie]
...
config-file=config_infer_primary_yolox.txt

NOTE: If you use the legacy model, you should edit it to config_infer_primary_yolox_legacy.txt.

Testing the model

deepstream-app -c deepstream_app_config.txt

NOTE: The TensorRT engine file may take a very long time to generate (sometimes more than 10 minutes).

NOTE: For more information about custom models configuration (batch-size, network-mode, etc), please check the docs/customModels.md file.