Nan Cost In Tensorflow Training Perceptron

I am trying to train a single layer perceptron (basing my code on this) on the following data file in tensor flow: 1,1,0.05,-1.05 1,1,0.1,-1.1 .... where the last column is the la

Solution 1:

Is this one example at a time? I would go batches and increase batch size to 128 or similar, as long as you are getting nans.

When I am getting nans it is usually either of the three: - batch size too small (in your case then just 1) - log(0) somewhere - learning rate too high and uncapped gradients