For different models we reshape the network and reinitialize the classifier’s layer, the link here “Finetuning Torchvision Models — PyTorch Tutorials 1.2.0 documentation” does not include Shufflenet V2. Does anyone have any idea??
I don’t think there is any particular reason besides that the tutorial uses a subset of all torchvision
models.
Are you seeing any issues in applying the tutorial to ShuffleNet?