Restormer
Restormer copied to clipboard
About inference on Huggingface
I'm really impressed in inferencing on HuggingFace. I had run Motion Deblur task on my own CPU(i7) and got ~50s inference runtime. May I convert from pth model to onnx and get better runtime.
We have not tried the onnx model. Please share your results with us here in case you run it.