Skip to content

Latest commit

 

History

History
177 lines (117 loc) · 3.23 KB

YOLOR.md

File metadata and controls

177 lines (117 loc) · 3.23 KB

YOLOR usage

NOTE: Select the correct branch of the YOLOR repo before the conversion.

NOTE: The cfg file is required for the main branch.

Convert model

1. Download the YOLOR repo and install the requirements

git clone https://github.com/WongKinYiu/yolor.git
cd yolor
pip3 install -r requirements.txt
pip3 install onnx onnxsim onnxruntime

NOTE: It is recommended to use Python virtualenv.

2. Copy conversor

Copy the export_yolor.py file from DeepStream-Yolo/utils directory to the yolor folder.

3. Download the model

Download the pt file from YOLOR repo.

NOTE: You can use your custom model.

4. Convert model

Generate the ONNX model file

  • Main branch

    Example for YOLOR-CSP

    python3 export_yolor.py -w yolor_csp.pt -c cfg/yolor_csp.cfg --simplify --dynamic

  • Paper branch

    Example for YOLOR-P6

    python3 export_yolor.py -w yolor-p6.pt --simplify --dynamic

NOTE: To convert a P6 model

--p6

NOTE: To change the inference size (defaut: 640)

-s SIZE
--size SIZE
-s HEIGHT WIDTH
--size HEIGHT WIDTH

Example for 1280

-s 1280

or

-s 1280 1280

5. Copy generated files

Copy the generated ONNX model file and labels.txt file (if generated) 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_yolor file

Edit the config_infer_primary_yolor.txt file according to your model (example for YOLOR-CSP with 80 classes)

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

NOTE: The YOLOR resizes the input with center padding. To get better accuracy, use

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

Edit the deepstream_app_config file

...
[primary-gie]
...
config-file=config_infer_primary_yolor.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.