Model is not being trained about nolearn HOT 10 CLOSED

Is this a classification problem? How does the network definition look like?

from nolearn.

Yes it is a classification problem, my input is 100x100 gray-scale images which has to be classified in to 5 classes. I have shared my code.
Here is a architecture of network.

    net = NeuralNet(
        layers=[
            ('input', layers.InputLayer),
            ('conv1', Conv2DLayer),
            ('pool1', MaxPool2DLayer),
            ('conv2', Conv2DLayer),
            ('pool2', MaxPool2DLayer),
            ('hidden4', layers.DenseLayer),
            ('output', layers.DenseLayer),
            ],
        input_shape=(None, 1, 100, 100),
        conv1_num_filters=1, conv1_filter_size=(3, 3), pool1_ds=(2, 2),
        conv2_num_filters=1, conv2_filter_size=(2, 2), pool2_ds=(2, 2),     
        hidden4_num_units=50,
        output_num_units=5, output_nonlinearity=None,

        update_learning_rate=0.01,
        update_momentum=0.9,

        regression=False,
        max_epochs=5,
        verbose=1)

The dimensions and dtypes of X and Y which I pass to fit method are

net.fit(X, Y)

shape of X (35126L, 1L, 100L, 100L)
shape of Y (35126L,)
dtype of X = float32
dtype of Y = int32

and
theano.config.floatX = float32

from nolearn.

@jayendra13 You just mentioned that this is a classification problem, right ? Then,
output_nonlinearity=None should be replaced by output_nonlinearity=lasagne.nonlinearities.softmax

from nolearn.

@paipai880429 Thanks for your comment I changed output_nonlinearity to softmax from the None, still
I am getting the same results, I think still there is something where I am making silly mistake.
One thing I forgot to mention that whenever I use predict method, it returns all zeros

from nolearn.

@jayendra13 It seems that the learning process has never been started. Then, did you try to decrease your initial learning rate?

from nolearn.

That might not be issue because initial random weights should give me some non-nan values for train and validation losses

from nolearn.

Hello I have the same problem. How did you fix it? Thank you

from nolearn.

I solved my problem, there were a set of value equal to inf ( it was an error) in my dataset.

from nolearn.

Had the same issue and "softmax" fixed it for me !
Thks 👍

from nolearn.

@paipai880429 In my case I had a learning rate of 0.01, changing it to 0.001 solved the problem, thanks for the tip. Why would the learning rate lead to this numerical instability?! Is it related to dataset size? Mine is big. Thanks

from nolearn.