What are some common strategies to visualise a weight matrix in a convolutional neural network?
I.e. visualise a matrix with the form (kH, inD, outD) in 1D convolution, and (kH, kW, inD, outD) in 2D convolution, where k is the kernel sizes and in/out is the input/output dimensions.
Preferably in Numpy/Matplotlib
Thanks Fred