Is your feature request related to a problem? Please describe.
At the moment, to use the neural network, you have to reshape the data to a 3D matrix like this:
X = X.reshape(X.shape[0], input_length, 1)
You can see an example in examples/mnist_train.py
Describe the solution you'd like
The 3rd dimension is unnecessary and prone to errors. The shape should be 2D like this:
# either
X = X.reshape(X.shape[0], -1)
# or
X = X.reshape(X.shape[0], input_length)
Describe alternatives you've considered
/
Additional context
There is a deprecation warning in pylearn/neural_network/network.py, remove it once you adjusted the code.
Is your feature request related to a problem? Please describe.
At the moment, to use the neural network, you have to reshape the data to a 3D matrix like this:
You can see an example in
examples/mnist_train.pyDescribe the solution you'd like
The 3rd dimension is unnecessary and prone to errors. The shape should be 2D like this:
Describe alternatives you've considered
/
Additional context
There is a deprecation warning in
pylearn/neural_network/network.py, remove it once you adjusted the code.