Darknet model to onnx

Question

I am currently working with Darknet on Yolov4, with 1 class.

I need to export those weights to onnx format, for tensorRT inference. I've tried multiple technics, using ultralytics to convert or going from tensorflow to onnx. But none seems to work. Is there a direct way to do it?

score 5 · Answer 1 · edited Nov 04 '21 at 02:31

5

Check this GitHub repo: https://github.com/Tianxiaomo/pytorch-YOLOv4

Running the demo_darknet2onnx.py script you'll be able to generate the ONNX model from the .cfg and .weights darknet files.

Usage example:

python demo_darknet2onnx.py <cfgFile> <weightFile> <imageFile> <batchSize>

You can also decide the batch size for the inference calls of the converted model.

edited Nov 04 '21 at 02:31

jklemmack

3,518
3
30
56

answered Jul 09 '20 at 12:53

Renan Vilas Novas

1,210
1
10
22

Asmita Khaneja · Answer 2 · 2022-08-24T18:21:43.480

2

The following repo exports yolov3 models from darknet to onnx, for tensorRT inference. You can use this as reference for your model.

https://github.com/jkjung-avt/tensorrt_demos/tree/master/yolo

edited Aug 24 '22 at 18:21

answered Jul 01 '20 at 09:11

Asmita Khaneja

355
1
8

This link is no longer available – Scott Nov 16 '20 at 09:22
I think it was renamed? Is it this? https://github.com/jkjung-avt/tensorrt_demos/tree/master/yolo – Stéphane Dec 11 '20 at 16:55

score 0 · Answer 3 · answered Aug 18 '21 at 10:09

0

You can convert scaled YOLO-yolov4,yolov4-csp.yolov4x-mish,yolov4-P5 etc models into onxx & its perfectly work fine.

https://github.com/linghu8812/tensorrt_inference

answered Aug 18 '21 at 10:09

Akash Desai

498
5
11

Darknet model to onnx

3 Answers3