To answer my own question and have a solution – I wrote a plain c++ solution called keras2cpp (its code available on github). In this solution you store network architecture (in json) and weights (in hdf5). Then you can dump a network to a plain text file with provided script. You can use obtained text … Read more
The number of parameters is 7850 because with every hidden unit you have 784 input weights and one weight of connection with bias. This means that every hidden unit gives you 785 parameters. You have 10 units so it sums up to 7850. The role of this additional bias term is really important. It significantly … Read more
You can find the answer at the Keras docs: https://keras.io/getting-started/faq/#how-can-i-obtain-reproducible-results-using-keras-during-development. In short, to be absolutely sure that you will get reproducible results with your python script on one computer’s/laptop’s CPU then you will have to do the following: Set the PYTHONHASHSEED environment variable at a fixed value Set the python built-in pseudo-random generator at a … Read more
model.predict() expects the first parameter to be a numpy array. You supply a list, which does not have the shape attribute a numpy array has. Otherwise your code looks fine, except that you are doing nothing with the prediction. Make sure you store it in a variable, for example like this: prediction = model.predict(np.array(tk.texts_to_sequences(text))) print(prediction)
Regression with neural networks is hard to get working because the output is unbounded, so you are especially prone to the exploding gradients problem (the likely cause of the nans). Historically, one key solution to exploding gradients was to reduce the learning rate, but with the advent of per-parameter adaptive learning rate algorithms like Adam, … Read more
There are lots of things I have seen make a model diverge. Too high of a learning rate. You can often tell if this is the case if the loss begins to increase and then diverges to infinity. I am not to familiar with the DNNClassifier but I am guessing it uses the categorical cross … Read more