X = np.random.rand(N) * 2.0 * np.pi
Y = np.sin(X)
training_data = [[np.array([[x]]), y] for x, y in zip(X, Y)]
input_size = 1
hidden_size = 10
hidden_layer_num = 10
output_size = 1
Neural_structure = [input_size]
for l in range(hidden_layer_num):
Neural_structure.append(hidden_size)
Neural_structure.append(output_size)
net = Network.Network(Neural_structure, cost=Network.CrossEntropyCost())
print('Layer # = %d' % (hidden_layer_num))
print('NN structure:', Neural_structure)
epochs_num = 50
mini_batch_size = 10
eta = 0.1
ims = []
Y_plot = Y[np.argsort(X)]
X_plot = np.sort(X)
for epochs in range(50):
net.SGD(
