chapter8 relu2deriv about grokking-deep-learning HOT 3 OPEN

for i in range(len(images)):
    layer_0 = images[i:i+1]
    layer_1 = np.dot(layer_0,weights_0_1) # modify
    layer_1_relu = relu(layer_1) # modify
    layer_2 = np.dot(layer_1_relu,weights_1_2)

    error += np.sum((labels[i:i+1] - layer_2) ** 2)
    correct_cnt += int(np.argmax(layer_2) == \
                                    np.argmax(labels[i:i+1]))

    layer_2_delta = (labels[i:i+1] - layer_2)
    layer_1_delta = layer_2_delta.dot(weights_1_2.T)\
                                * relu2deriv(layer_1)
    weights_1_2 += alpha * layer_1_relu.T.dot(layer_2_delta) # modify
    weights_0_1 += alpha * layer_0.T.dot(layer_1_delta)

relu2deriv = lambda x: x>=0 # returns 1 for input > 0, return 0 otherwise
relu = lambda x:(x>=0) * x # returns x if x > 0, return 0 otherwise

relu2deriv(1) # True = 1 - ok
relu(1) # 1 - ok

relu(0) # 0 - weight does not affect the output
relu2deriv(0) # True = 1 - but used in backpropagation

relu2deriv(-1) # False = 0 - ok
relu(-1) # 0 - ok

relu2deriv = lambda x: x>0 # returns 1 for input > 0, return 0 otherwise
relu = lambda x:(x>0) * x # returns x if x > 0, return 0 otherwise

relu2deriv(1) # True = 1 - ok
relu(1) # 1 - ok

relu(0) # 0 - ok
relu2deriv(0) # False = 0 - ok

relu2deriv(-1) # False = 0 - ok
relu(-1) # 0 - ok