Skip to content

Latest commit

 

History

History
158 lines (106 loc) · 3.17 KB

DAMOYOLO.md

File metadata and controls

158 lines (106 loc) · 3.17 KB

DAMO-YOLO usage

Convert model

1. Download the DAMO-YOLO repo and install the requirements

git clone https://github.com/tinyvision/DAMO-YOLO.git
cd DAMO-YOLO
pip3 install -r requirements.txt
pip3 install onnx onnxsim onnxruntime

NOTE: It is recommended to use Python virtualenv.

2. Copy conversor

Copy the export_damoyolo.py file from DeepStream-Yolo/utils directory to the DAMO-YOLO folder.

3. Download the model

Download the pth file from DAMO-YOLO releases (example for DAMO-YOLO-S*)

wget https://idstcv.oss-cn-zhangjiakou.aliyuncs.com/DAMO-YOLO/release_model/clean_model_0317/damoyolo_tinynasL25_S_477.pth

NOTE: You can use your custom model.

4. Convert model

Generate the ONNX model file (example for DAMO-YOLO-S*)

python3 export_damoyolo.py -w damoyolo_tinynasL25_S_477.pth -c configs/damoyolo_tinynasL25_S.py --simplify --dynamic

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_damoyolo file

Edit the config_infer_primary_damoyolo.txt file according to your model (example for DAMO-YOLO-S* with 80 classes)

[property]
...
onnx-file=damoyolo_tinynasL25_S.onnx
model-engine-file=damoyolo_tinynasL25_S.onnx_b1_gpu0_fp32.engine
...
num-detected-classes=80
...
parse-bbox-func-name=NvDsInferParseYoloE
...

NOTE: The DAMO-YOLO do not resize the input with padding. To get better accuracy, use

maintain-aspect-ratio=0

Edit the deepstream_app_config file

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