Closed xinsuinizhuan closed 4 years ago
Yes! That is correct, you could load the data into a cube that is a multiple of 32 and just leave the last column empty (zeros).
Eventually I would like to add "training" functions so that you wouldn't need to write the training step your self. (Like how pytorch has a 'fit' method)
percept_MNIST function in mnist_test_recurrent example, batch_size==32, and samples=32X1024, but in my real data, the samples is not the batch_size's multiple, for example, my data size is 32X1024+31, so the last 31 record is not trained?