# If we train on the whole set we expect it to learn to detect edges. batch_size= 512*4 tensor_x = mnist_data.train_data.type(torch.FloatTensor) # transform to torch tensors tensor_y = ...
Example for training a centered and normal binary restricted Boltzmann machine on the MNIST handwritten digit dataset. The model has 500 hidden units, is trained for 200 epochs (That takes a while, ...
Unele rezultate au fost ascunse, deoarece pot fi inaccesibile pentru dvs.
Afișați rezultatele inaccesibile
Părere