Hi, I would like to modify the structure of the model Resnet50 . My goal is neither to add nor to remove layers, only to replace the convolutions that in the code are made by the pytorch nn.Conv function by convolutions made by the Nvidia CUTLASS library (cutlass/examples/python/02_pytorch_extension_grouped_gemm.ipynb at main · NVIDIA/cutlass · GitHub).
I don’t intend either to retrain or to modify weights, only to substitute the call to the convolutions with the call to a convolution of cutlass in a similar way to how I describe it in the pytorch forum: Using diffetent conv2d ops with pre trained models
My question is if it is possible, within the guidelines of the repository and then how can I import the file Resnet50 from another file or pytorch as it would be done with Models and pre-trained weights — Torchvision main documentation.
Thanks.