# Reusing debugInitializeWeights to get random X
X = debugInitializeWeights(input_layer_size - 1, m)
# Set each element of y to be in [0,num_labels]
y = [(i % num_labels) for i in range(m)]
# Unroll parameters
nn_params = np.append(Theta2, Theta1).reshape(-1)
y = (np.ravel(y) - 1)
ys = np.zeros((m, num_labels))
for i in range(m):
ys[i][y[i]] = 1
# Compute Cost
cost, grad = net._backprop(X, np.array(ys))
def reduced_cost_func(p):
""" Cheaply decorated nnCostFunction """
net.th[0] = np.reshape(p[:hidden_layer_size * (input_layer_size + 1)],
(hidden_layer_size, (input_layer_size + 1)))
net.th[1] = np.reshape(p[hidden_layer_size * (input_layer_size + 1):],
(num_labels, (hidden_layer_size + 1)))
return net._backprop(X, np.array(ys))[0]
numgrad = computeNumericalGradient(reduced_cost_func, nn_params)
# Check two gradients
np.testing.assert_almost_equal(grad, numgrad)
print(grad - numgrad)
