Steps to reproduce:
- Load an alexnet from torchvision
- Change model’s first weight to torch.tensor(float(‘inf’))
- Register forward hook and check the output of first conv layer and first ReLu layer
I speculate this bug was caused by torch’s measure to inf value
Screen Shots:
Conv Layer’s output and another parameter:
ReLu Layer’s output and another parameter:
Torchinfo’s summary of AlexNet
Note: input_val was a tuple