2-D convolution as a matrix-matrix multiplication [closed]

by

Yes, it is possible and you should also use a doubly block circulant matrix (which is a special case of Toeplitz matrix). I will give you an example with a small size of kernel and the input, but it is possible to construct Toeplitz matrix for any kernel. So you have a 2d input x and 2d kernel k and you want to calculate the convolution x * k. Also let’s assume that k is already flipped. Let’s also assume that x is of size n×n and k is m×m.

So you unroll k into a sparse matrix of size (n-m+1)^2 × n^2, and unroll x into a long vector n^2 × 1. You compute a multiplication of this sparse matrix with a vector and convert the resulting vector (which will have a size (n-m+1)^2 × 1) into a n-m+1 square matrix.

I am pretty sure this is hard to understand just from reading. So here is an example for 2×2 kernel and 3×3 input.

enter image description here * enter image description here

Here is a constructed matrix with a vector:

enter image description here

which is equal to enter image description here.

And this is the same result you would have got by doing a sliding window of k over x.

More Related Contents:

  1. How to calculate the number of parameters for convolutional neural network?
  2. scale the loss value according to “badness” in caffe
  3. should I use float or classes as output for the final layer in my neural network?
  4. Why binary_crossentropy and categorical_crossentropy give different performances for the same problem?
  5. Keras input explanation: input_shape, units, batch_size, dim, etc
  6. Test labels for regression caffe, float not allowed?
  7. Intuitive understanding of 1D, 2D, and 3D convolutions in convolutional neural networks [closed]
  8. Caffe | solver.prototxt values setting strategy
  9. LSTM module for Caffe
  10. caffe data layer example step by step
  11. How to create caffe.deploy from train.prototxt
  12. caffe: model definition: write same layer with different phase using caffe.NetSpec()
  13. What is a `”Python”` layer in caffe?
  14. Many to one and many to many LSTM examples in Keras
  15. How to assign a value to a TensorFlow variable?
  16. How to initialize weights in PyTorch?
  17. InfogainLoss layer
  18. How do I initialize weights in PyTorch?
  19. How to interpret caffe log with debug_info?
  20. Why do we need to call zero_grad() in PyTorch?
  21. What is the difference between loss function and metric in Keras? [duplicate]
  22. Dimension of shape in conv1D
  23. Does Caffe need data to be shuffled?
  24. Is deep learning bad at fitting simple non linear functions outside training scope (extrapolating)?
  25. How to interpret loss and accuracy for a machine learning model [closed]
  26. Obtaining output of an Intermediate layer in TensorFlow/Keras
  27. Multiple outputs in Keras
  28. keras: how to save the training history attribute of the history object
  29. how to implement custom metric in keras?
  30. Choosing number of Steps per Epoch

Leave a Comment