ValueError: 'total size of new array must be unchanged' about nolearn HOT 7 CLOSED

Ah, it looks like you're using the Conv2DLayer implementation that doesn't like batches that aren't exactly of size batch_size. The cuda_convnet-based implementation (used in the tutorial) doesn't have this problem. See here for a discussion with two possible solutions.

from nolearn.

It turns out that there's a much easier solution to this problem. In the tutorial, I made an error and falsely set the input layer's shape[0] (the batch size) to be 128. This should have been None. I verified that with this setting the "legacy" Theano convnet layer (for CPU) is happy and every other layer that I tested was too.

So that means I could undo the forced_even change again. Please update your code.

from nolearn.

Could you try and print out the values of Xb.shape and yb.shape at this point:

batch_train_loss = self.train_iter_(Xb, yb)

from nolearn.

Xb (31, 1, 300, 400)
yb (31,)

from nolearn.

Well maybe an easier solution to what's discussed in that other ticket is to just hack BatchIterator to skip remainder batches that are smaller than batch_size. Could be an option to BatchIterator, maybe you want to send a pull request.

from nolearn.

Is there any performance gain to having the Theano compiler know up front the size of the batch size?

from nolearn.

Tried with a large net, didn't see any performance difference.

from nolearn.