| Network | TensorRT | OpenVINO | OnnxRuntime | Translator Plugin | Minimum required EVA | Reference link |
|---|---|---|---|---|---|---|
| Yolov3 | Tested | Tested | Tested | adtrans_yolo | 2.0+ | AlexeyAB/darknet yolov3_onnx |
Original model : https://github.com/AlexeyAB/darknet
Convert Darknet model to ONNX format
https://github.com/jkjung-avt/tensorrt_demos/tree/c6afc40082da72397b2b0ad91eb6f32acf3b731d#yolov3
trtexec --onnx=yolov3.onnx --buildOnly --saveEngine=YOUR_MODEL_NAME.enginetrtexec --onnx=yolov3.onnx --buildOnly --saveEngine=YOUR_MODEL_NAME.engine --fp16Note : YOLO family models have different input dimensions like 288 ( 32*9 ), 416 ( 32*13 ), 608 ( 32*,19). When convert, please pay attention to which input dimension of your model
| Network | TensorRT | OpenVINO | OnnxRuntime | Translator Plugin | Minimum required EVA | Reference link |
|---|---|---|---|---|---|---|
| Yolov4 | Tested | Tested | Tested | adtrans_yolo | 3.5.3+ | AlexeyAB/darknet yolov4_onnx |
Original model : https://github.com/AlexeyAB/darknet
Convert Darknet model to ONNX format
https://github.com/jkjung-avt/tensorrt_demos/tree/c6afc40082da72397b2b0ad91eb6f32acf3b731d#yolov4
trtexec --onnx=yolov4.onnx --buildOnly --saveEngine=YOUR_MODEL_NAME.engine trtexec --onnx=yolov4.onnx --buildOnly --saveEngine=YOUR_MODEL_NAME.engine --fp16
https://docs.openvino.ai/2021.2/omz_models_public_yolo_v4_tf_yolo_v4_tf.html
Note : YOLO family models have different input dimensions like 288 ( 32*9 ), 416 ( 32*13 ), 608 ( 32*,19). When convert, please pay attention to which input dimension of your model
gst-launch-1.0 filesrc location=street.mp4 ! decodebin ! videoconvert ! adrt model=yolov3.engine scale=0.0039 rgbconv=True mean="0 0 0" ! adtrans_yolo blob-size=13,26,52 label="files/yolo.txt" input-height=416 input-width=416 mask="(6,7,8),(3,4,5),(0,1,2)" ! admetadrawer ! videoconvert ! ximagesink Explanation of some plugins parameters
adrt model=yolov3.engine scale=0.0039 rgbconv=True mean="0 0 0" adtrans_yolo blob-size=13,26,52 label="files/yolo.txt" input-height=416 input-width=416 mask="(6,7,8),(3,4,5),(0,1,2)" use-sigmoid=true