Extracting vector from Pooling Classifier

[kontrabas]

Sorry - my bad.

Best regards

EDIT:
I’ve found a solution thanks to:

PyTorch - Best way to get at intermediate layers in VGG and ResNet?

To get output of any layer while doing a single forward pass, you can use register_forward_hook. outputs= [] def hook(module, input, output): outputs.append(output) res50_model = models.resnet50(pretrained=True) res50_model.layer4[0].conv2.register_forward_hook(hook) out = res50_model(res) out = res50_model(res1) print(outputs) Here in the outputs you get a list with two tensors in it. Those tensors are outputs of that particular layer for each forward pass.

I’ve modified the code and it looks like:

def hook(module, input, output):
    outputs.append(output)

outputs = []
awd = learn.model
awd[1].layers[2].register_forward_hook(hook)
awd.reset()

with torch.no_grad():
    awd.eval()(xb)

And the outputs from this layer are stored in ‘outputs’ list.