K.C. Tung
K.C. Tung
When I tried to trace the model with torch.jit.trace with an image tensor os size (1,3,640, 640), I get error: ``` RuntimeError: Tracer cannot infer type of [[tensor([[[[[ 3.4373e-01, -3.1998e-01,...
keep getting this error even though I tried different version of rich module. How do I go about fixing it?
I tried running `demo.py` with `--cpu` flag. But I get the following runtime error. Here is the command: `python demo.py --config config/vox-256.yaml --driving_video ~/mywork/first-order-model/crop.mp4 --source_image ~/mywork/first-order-model/source-image.jpeg --checkpoint ~/mywork/yadisk-direct/first-order-model/vox-cpk.pth.tar --relative --adapt_scale...
I am able to trace the model with `torch.jit.trace`, and I know the shape of input tensors. I don't think I am using any tensors outside the GPU, but I...