Anyone have any idea about Yolov4 tiny model with batch size 1.
I refered this Yolov4 repo Here to generate onnx file. By default, I had batch size 64 in my cfg. It took a while to build the engine. And then inference is also as expected but it was very slow.
Then I realized I should give batch size 1 in my cfg file.
I changed batch size to 1 in my yolov4-tiny.cfg and Onnx model is generated, Used trtexec to build an engine.
used this command:
sudo ./trtexec --onnx=yolov4-tiny.onnx --saveEngine=yolov4-tiny.rt --fp16 --verbose
But when I run inference on some test data, I get correct classes, probs but boxes are not correct.
They are way too small and placed at the top of the image everytime.
What could be the reason for this ?
Should I change something here ->(in the output calculation) postprocess when I change the batch size to 1.
Any help/ hint would be appreciated.
TensorRT Version: 8.0.1