# 1 input layer of size 64 (the images are 8x8 gray pixels)
# 1 hidden layer of size 100
# 1 output layer of size 10 (the labels of digits are 0 to 9)
nn = ANN([784, 300, 10])
# see how long training takes
startTime = time.time()
# train it
nn.train2(30, X_train_l, labels_train_l, 100000, step_cb)
elapsedTime = time.time() - startTime
print("Training took {0} seconds".format(elapsedTime))
# serialize and save the ANN
nn.serialize(nn, serialized_name)
# compute the predictions
predictions = []
for i in range(X_test.shape[0]):
o = nn.predict(X_test[i])
# the inverse of the binarization would be taking the maximum argument index
# ex: [.1 .1 .1 .1 .9 .1 .1 .1 .1 .1] -> 4
# ex: [.1 .1 .1 .1 .1 .1 .1 .9 .1 .1] -> 7
predictions.append(np.argmax(o))
# compute a confusion matrix
print("confusion matrix")
print(confusion_matrix(y_test, predictions))
