Tallisgo
Tallisgo
First thanks for your hard work. Recently, I train a model on quantized mobilenet_v3_large ( based on torchvision ). I pruned this model and quantize the pruned model. I found...
### Describe the bug It is a small problem. When I follow REAMDE `Import from Transformers` to initialize model, a error (NameError: name 'torch' is not defined) occurs. So it...
**Describe the bug** I excute test_input.json need 7s, but I excute sdxl json need 59s.  Can you please provide me some solutions to find the reasons.
Thanks for your work. I have some questions about `alignment/coordinate_reg`. I download the model 2d106det.onnx, and watch its structure.  I just want to know the meaning of output tensor's...
Thanks for your hard work. I think it is very useful. According to the tutorial, it should first get jetson files and install dependencies. If we can boot from a...
hi, I have some questions about generate the coordinates of keypoints. Why `Face_Alignment_prob` need to plus1 and then divide 2? What is the meaning of `Face_Alignment_prob` `alignmentface.landmarks[start]=int((Face_Alignment_prob[start]+1)*img.cols / 2); alignmentface.landmarks[start+1]=int((Face_Alignment_prob[start+1]+1)*img.cols...