Yixuan Zhou
Yixuan Zhou
A pie chart feature would be really nice to have!
Got it, i will give TRT10 a try
Gotcha! Thank you for the clarification!
@lix19937 Thank you very much for helping out! > Do you start with a pretrained model to QAT? Yes, to be specific, what I did was PTQ using [TRT modelopt](https://nvidia.github.io/TensorRT-Model-Optimizer/guides/_pytorch_quantization.html#apply-post-training-quantization-ptq)....
Got it, thanks for the follow up @akhilg-nv. Sorry for the delay, I was away last & this week. I can try the experiment you suggested next week. To clarify:...
Hi @akhilg-nv, I disabled quantization of all the Conv layers: what got quantized are: 1. maxpool and average pool 2. skip connections (adds) 3. final layer that does the classification...
Hi @akhilg-nv, thanks for the response. I didn't check the diff between onnx and native for this partially quantized model. I will double check that later and get back to...
Hi @akhilg-nv, thanks for taking a look! Could you try this link: https://file.io/3M5bla347qa0? Seems to be working for me when i try to re-download. I apologize the previous link didn't...
Hi @akhilg-nv, I am terribly sorry for the confusion... I didn't re-check the model architecture. I looked at the onnx graph and I see there is no BatchNorm and falsely...
Thank you for providing this repro. I was able to verify that with this approach the onnx runtime and the TRT compiled model outputing the same output. In my workflow,...