maggiez0138 / yolov5_quant_sample

This is 8-bit quantization sample for yolov5. Both PTQ, QAT and Partial Quantization have been implemented, and present the results based on yolov5s.
GNU General Public License v3.0
95 stars 26 forks source link

Zero-point must be Long, found Int #9

Open phanben110 opened 1 year ago

phanben110 commented 1 year ago

I found an error when convert model QAT .pt to .onnx

image
xiuxiuxius commented 1 year ago

参考这个https://github.com/NVIDIA/TensorRT/issues/1763

image

phanben110 commented 1 year ago

Thanks you so much