Open kitckso opened 1 month ago
@kitckso Do you run official with compile and triton ?
No, all default setting, only run inference with image and driving video.
@kitckso Take note, will support for fp16 onnx
I just https://huggingface.co/myn0908/Live-Portrait-ONNX/tree/main I downloaded the new ONNX and found that it is slower than the original one
@galigaligo Yes, but that’s not fair for compare onnx with torch, because onnx is design for run on cpu , and when run on gpu it’ll copy the input to gpu device and torch don’t do that, waiting for TensorRT , you can compare it with torch
@galigaligo Yes, but that’s not fair for compare onnx with torch, because onnx is design for run on cpu , and when run on gpu it’ll copy the input to gpu device and torch don’t do that, waiting for TensorRT , you can compare it with torch
What I mean is, compared to today's onnx and two days ago's onnx, it's much slower
@galigaligo because I’m modify some in onnx for correct model that it can convert to tensorrt , if you still use old onnx model, you can’t convert it
Tested the ONNX version with 3060, only Animating process: Official pytorch: 27s Animating... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:27 ONNX: 87s Animating...: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 231/231 [01:27<00:00, 2.63it/s]
Maybe explained by juntaosun https://github.com/KwaiVGI/LivePortrait/issues/144