深度神经网络图像分类过程中的断言错误

Question

# GRADED FUNCTION: two_layer_model

def two_layer_model(X, Y, layers_dims, learning_rate = 0.0075, num_iterations = 3000, print_cost=False):
    """
    Implements a two-layer neural network: LINEAR->RELU->LINEAR->SIGMOID.
    
    Arguments:
    X -- input data, of shape (n_x, number of examples)
    Y -- true "label" vector (containing 0 if cat, 1 if non-cat), of shape (1, number of examples)
    layers_dims -- dimensions of the layers (n_x, n_h, n_y)
    num_iterations -- number of iterations of the optimization loop
    learning_rate -- learning rate of the gradient descent update rule
    print_cost -- If set to True, this will print the cost every 100 iterations 
    
    Returns:
    parameters -- a dictionary containing W1, W2, b1, and b2
    """
    
    np.random.seed(1)
    grads = {}
    costs = []                              # to keep track of the cost
    m = X.shape[1]                           # number of examples
    (n_x, n_h, n_y) = layers_dims
    
    # Initialize parameters dictionary, by calling one of the functions you'd previously implemented
    ### START CODE HERE ### (≈ 1 line of code)
    parameters = initialize_parameters(n_x, n_h, n_y)
    ### END CODE HERE ###
    
    # Get W1, b1, W2 and b2 from the dictionary parameters.
    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]
    
    # Loop (gradient descent)

    for i in range(0, num_iterations):

        # Forward propagation: LINEAR -> RELU -> LINEAR -> SIGMOID. Inputs: "X, W1, b1". Output: "A1, cache1, A2, cache2".
        ### START CODE HERE ### (≈ 2 lines of code)
        A1, cache1 = linear_activation_forward(X, W1, b1, activation= "relu")
        A2, cache2 = linear_activation_forward(A1, W2, b2, activation= "sigmoid")
        ### END CODE HERE ###
        
        # Compute cost
        ### START CODE HERE ### (≈ 1 line of code)
        cost = compute_cost(A2, Y)
        ### END CODE HERE ###
        
        # Initializing backward propagation
        dA2 = - (np.divide(Y, A2) - np.divide(1 - Y, 1 - A2))
        
        # Backward propagation. Inputs: "dA2, cache2, cache1". Outputs: "dA1, dW2, db2; also dA0 (not used), dW1, db1".
        ### START CODE HERE ### (≈ 2 lines of code)
        dA1, dW2, db2 = linear_activation_backward(dA2, cache2, activation = "sigmoid")
        dA0, dW1, db1 = linear_activation_backward(dA1, cache1, activation = "relu")
        ### END CODE HERE ###
        
        # Set grads['dWl'] to dW1, grads['db1'] to db1, grads['dW2'] to dW2, grads['db2'] to db2
        grads['dW1'] = dW1
        grads['db1'] = db1
        grads['dW2'] = dW2
        grads['db2'] = db2
        
        # Update parameters.
        ### START CODE HERE ### (approx. 1 line of code)
        parameters = update_parameters(parameters, grads, learning_rate)
        ### END CODE HERE ###

        # Retrieve W1, b1, W2, b2 from parameters
        W1 = parameters["W1"]
        b1 = parameters["b1"]
        W2 = parameters["W2"]
        b2 = parameters["b2"]
        
        # Print the cost every 100 training example
        if print_cost and i % 100 == 0:
            print("Cost after iteration {}: {}".format(i, np.squeeze(cost)))
        costs.append(cost)
       
    # plot the cost

    plt.plot(np.squeeze(costs))
    plt.ylabel('cost')
    plt.xlabel('iterations (per tens)')
    plt.title("Learning rate =" + str(learning_rate))
    plt.show()
    
    return parameters, costs
 

    parameters, costs = two_layer_model(train_x, train_y, layers_dims = (n_x, n_h, n_y), num_iterations = 2, print_cost=False)
    
    print("Cost after first iteration: " + str(costs[0]))
    
    two_layer_model_test(two_layer_model)

**

我收到此错误：

  1  Tests passed
     3  Tests failed
    ---------------------------------------------------------------------------
    AssertionError                            Traceback (most recent call last)
    <ipython-input-14-f9ec5304d38d> in <module>
          3 print("Cost after first iteration: " + str(costs[0]))
          4 
    ----> 5 two_layer_model_test(two_layer_model)
    ~/work/release/W4A2/public_tests.py in two_layer_model_test(target)
         75     ]
         76 
    ---> 77     multiple_test(test_cases, target)
         78 
         79 
    ~/work/release/W4A2/test_utils.py in multiple_test(test_cases, target)
        140         print('\033[92m', success," Tests passed")
        141         print('\033[91m', len(test_cases) - success, " Tests failed")
    --> 142         raise AssertionError("Not all tests were passed for {}. Check your equations and avoid using global variables inside the function.".format(target.__name__))
        143 
    AssertionError: Not all tests were passed for two_layer_model. Check your equations and avoid using global variables inside the function.

Answer 1

def two_layer_model(X, Y, layers_dims, learning_rate = 0.0075, num_iterations = 3000, print_cost=False): """ 实现两层神经网络：LINEAR->RELU->LINEAR->SIGMOID。

Arguments:
X -- input data, of shape (n_x, number of examples)
Y -- true "label" vector (containing 0 if cat, 1 if non-cat), of shape (1, number of examples)
layers_dims -- dimensions of the layers (n_x, n_h, n_y)
num_iterations -- number of iterations of the optimization loop
learning_rate -- learning rate of the gradient descent update rule
print_cost -- If set to True, this will print the cost every 100 iterations 

Returns:
parameters -- a dictionary containing W1, W2, b1, and b2
"""

np.random.seed(1)
grads = {}
costs = []                              # to keep track of the cost
m = X.shape[1]                           # number of examples
(n_x, n_h, n_y) = layers_dims

# Initialize parameters dictionary, by calling one of the functions you'd previously implemented
### START CODE HERE ### (≈ 1 line of code)
parameters = initialize_parameters(n_x, n_h, n_y)
### END CODE HERE ###

# Get W1, b1, W2 and b2 from the dictionary parameters.
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]

# Loop (gradient descent)

for i in range(0, num_iterations):

    # Forward propagation: LINEAR -> RELU -> LINEAR -> SIGMOID. Inputs: "X, W1, b1". Output: "A1, cache1, A2, cache2".
    ### START CODE HERE ### (≈ 2 lines of code)
    A1, cache1 = linear_activation_forward(X, W1, b1, activation= "relu")
    A2, cache2 = linear_activation_forward(A1, W2, b2, activation= "sigmoid")
    ### END CODE HERE ###
    
    # Compute cost
    ### START CODE HERE ### (≈ 1 line of code)
    cost = compute_cost(A2, Y)
    ### END CODE HERE ###
    
    # Initializing backward propagation
    dA2 = - (np.divide(Y, A2) - np.divide(1 - Y, 1 - A2))
    
    # Backward propagation. Inputs: "dA2, cache2, cache1". Outputs: "dA1, dW2, db2; also dA0 (not used), dW1, db1".
    ### START CODE HERE ### (≈ 2 lines of code)
    dA1, dW2, db2 = linear_activation_backward(dA2, cache2, activation = "sigmoid")
    dA0, dW1, db1 = linear_activation_backward(dA1, cache1, activation = "relu")
    ### END CODE HERE ###
    
    # Set grads['dWl'] to dW1, grads['db1'] to db1, grads['dW2'] to dW2, grads['db2'] to db2
    grads['dW1'] = dW1
    grads['db1'] = db1
    grads['dW2'] = dW2
    grads['db2'] = db2
    
    # Update parameters.
    ### START CODE HERE ### (approx. 1 line of code)
    parameters = update_parameters(parameters, grads, learning_rate)
    ### END CODE HERE ###

    # Retrieve W1, b1, W2, b2 from parameters
    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]
    
    # Print the cost every 100 training example
    if print_cost and i % 100 == 0:
        print("Cost after iteration {}: {}".format(i, np.squeeze(cost)))
    if i % 100 == 0 or i == num_iterations:
        costs.append(cost)
   
# plot the cost

plt.plot(np.squeeze(costs))
plt.ylabel('cost')
plt.xlabel('iterations (per tens)')
plt.title("Learning rate =" + str(learning_rate))
plt.show()

return parameters, costs