Mahsa Hasheminejad

Results 2 comments of Mahsa Hasheminejad

@ttyio @nvpohanh I have the same problem, but I get correct results from the ONNX (QAT) and wrong results when trying to infer in TensorRT8.2. More info: QAT with torch...

@nvpohanh Here is a link to the QAT model in pytorch (ResNet50 - pretrained - 7clss): [ResNet50.pth](https://drive.google.com/file/d/1oXHghW0RAj_7KHlqx4BVvytfp4JN4YGC/view?usp=sharing ) It's trained with mentioned versions above.