Search code examples
imageluadata-visualizationconvolutiontorch

Visualize images in intermediate layers in torch (lua)

In the conv-nets model, I know how to visualize the filters, we can do itorch.image(model:get(1).weight)

But how could I efficiently visualize the output images after the convolution? especially those images in the second or third layer in a deep neural network?

Thanks.

Solution

  • Similarly to weight, you can use:

    itorch.image(model:get(1).output)