DeepLearning AI (1-4-1)

Building your Deep Neural Network Step by Step

#packages
import numpy as np
import h5py
import matplotlib.pyplot as plt
from testCases import *
from dnn_utils import sigmoid, sigmoid_backward, relu, relu_backward
from public_tests import *

%matplotlib inline
plt.rcParams['figure.figsize'] = (5.0, 4.0) # set default size of plots
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'

%load_ext autoreload
%autoreload 2

np.random.seed(1)

def initialize_parameters(n_x, n_h, n_y):
    """
    Argument:
    n_x -- size of the input layer
    n_h -- size of the hidden layer
    n_y -- size of the output layer
    
    Returns:
    parameters -- python dictionary containing your parameters:
                    W1 -- weight matrix of shape (n_h, n_x)
                    b1 -- bias vector of shape (n_h, 1)
                    W2 -- weight matrix of shape (n_y, n_h)
                    b2 -- bias vector of shape (n_y, 1)
    """
    
    np.random.seed(1)
    
    #(≈ 4 lines of code)
    # W1 = ...
    # b1 = ...
    # W2 = ...
    # b2 = ...
    # YOUR CODE STARTS HERE
    W1=np.random.randn(n_h,n_x)*0.01
    b1=np.zeros((n_h,1))
    W2=np.random.randn(n_y,n_h)*0.01
    b2=np.zeros((n_y,1))
    # YOUR CODE ENDS HERE
    
    parameters = {"W1": W1,
                  "b1": b1,
                  "W2": W2,
                  "b2": b2}
    
    return parameters    

def initialize_parameters_deep(layer_dims):
    """
    Arguments:
    layer_dims -- python array (list) containing the dimensions of each layer in our network
    
    Returns:
    parameters -- python dictionary containing your parameters "W1", "b1", ..., "WL", "bL":
                    Wl -- weight matrix of shape (layer_dims[l], layer_dims[l-1])
                    bl -- bias vector of shape (layer_dims[l], 1)
    """
    
    np.random.seed(3)
    parameters = {}
    L = len(layer_dims) # number of layers in the network

    for l in range(1, L):
        #(≈ 2 lines of code)
        # parameters['W' + str(l)] = ...
        # parameters['b' + str(l)] = ...
        # YOUR CODE STARTS HERE
        parameters['W' + str(l)]=np.random.randn(layer_dims[l], layer_dims[l-1])*0.01
        parameters['b' + str(l)]=np.zeros((layer_dims[l],1))
        
        # YOUR CODE ENDS HERE
        
        assert(parameters['W' + str(l)].shape == (layer_dims[l], layer_dims[l - 1]))
        assert(parameters['b' + str(l)].shape == (layer_dims[l], 1))

        
    return parameters

def linear_forward(A, W, b):
    """
    Implement the linear part of a layer's forward propagation.

    Arguments:
    A -- activations from previous layer (or input data): (size of previous layer, number of examples)
    W -- weights matrix: numpy array of shape (size of current layer, size of previous layer)
    b -- bias vector, numpy array of shape (size of the current layer, 1)

    Returns:
    Z -- the input of the activation function, also called pre-activation parameter 
    cache -- a python tuple containing "A", "W" and "b" ; stored for computing the backward pass efficiently
    """
    
    #(≈ 1 line of code)
    # Z = ...
    # YOUR CODE STARTS HERE
    Z=np.dot(W,A)+b
    
    # YOUR CODE ENDS HERE
    cache = (A, W, b)
    
    return Z, cache

def linear_activation_forward(A_prev, W, b, activation):
    """
    Implement the forward propagation for the LINEAR->ACTIVATION layer

    Arguments:
    A_prev -- activations from previous layer (or input data): (size of previous layer, number of examples)
    W -- weights matrix: numpy array of shape (size of current layer, size of previous layer)
    b -- bias vector, numpy array of shape (size of the current layer, 1)
    activation -- the activation to be used in this layer, stored as a text string: "sigmoid" or "relu"

    Returns:
    A -- the output of the activation function, also called the post-activation value 
    cache -- a python tuple containing "linear_cache" and "activation_cache";
             stored for computing the backward pass efficiently
    """
    
    if activation == "sigmoid":
        #(≈ 2 lines of code)
        # Z, linear_cache = ...
        # A, activation_cache = ...
        # YOUR CODE STARTS HERE
        Z,linear_cache=linear_forward(A_prev, W, b)
        A,activation_cache=sigmoid(Z)
        # YOUR CODE ENDS HERE
    
    elif activation == "relu":
        #(≈ 2 lines of code)
        # Z, linear_cache = ...
        # A, activation_cache = ...
        # YOUR CODE STARTS HERE
        Z,linear_cache=linear_forward(A_prev, W, b)
        A,activation_cache=relu(Z)
        # YOUR CODE ENDS HERE
    cache = (linear_cache, activation_cache)

    return A, cache

def L_model_forward(X, parameters):
    """
    Implement forward propagation for the [LINEAR->RELU]*(L-1)->LINEAR->SIGMOID computation
    
    Arguments:
    X -- data, numpy array of shape (input size, number of examples)
    parameters -- output of initialize_parameters_deep()
    
    Returns:
    AL -- activation value from the output (last) layer
    caches -- list of caches containing:
                every cache of linear_activation_forward() (there are L of them, indexed from 0 to L-1)
    """

    caches = []
    A = X
    L = len(parameters) // 2                  # number of layers in the neural network
    
    # Implement [LINEAR -> RELU]*(L-1). Add "cache" to the "caches" list.
    # The for loop starts at 1 because layer 0 is the input
    for l in range(1, L):
        A_prev = A 
        #(≈ 2 lines of code)
        # A, cache = ...
        # caches ...
        # YOUR CODE STARTS HERE
        A, cache = linear_activation_forward(A_prev, parameters['W' + str(l)], parameters['b' + str(l)], "relu")
        caches.append(cache)
        # YOUR CODE ENDS HERE
    
    # Implement LINEAR -> SIGMOID. Add "cache" to the "caches" list.
    #(≈ 2 lines of code)
    # AL, cache = ...
    # caches ...
    # YOUR CODE STARTS HERE
    AL, cache = linear_activation_forward(A, parameters['W' + str(L)], parameters['b' + str(L)], "sigmoid")
    caches.append(cache)
  
    # YOUR CODE ENDS HERE
          
    return AL, caches

def compute_cost(AL, Y):
    """
    Implement the cost function defined by equation (7).

    Arguments:
    AL -- probability vector corresponding to your label predictions, shape (1, number of examples)
    Y -- true "label" vector (for example: containing 0 if non-cat, 1 if cat), shape (1, number of examples)

    Returns:
    cost -- cross-entropy cost
    """
    
    m = Y.shape[1]

    # Compute loss from aL and y.
    # (≈ 1 lines of code)
    # cost = ...
    # YOUR CODE STARTS HERE
    
    cost=-1/m*np.sum(Y*np.log(AL)+(1-Y)*np.log(1-AL))
    
    # YOUR CODE ENDS HERE
    
    cost = np.squeeze(cost)      # To make sure your cost's shape is what we expect (e.g. this turns [[17]] into 17).

    
    return cost

def linear_backward(dZ, cache):
    """
    Implement the linear portion of backward propagation for a single layer (layer l)

    Arguments:
    dZ -- Gradient of the cost with respect to the linear output (of current layer l)
    cache -- tuple of values (A_prev, W, b) coming from the forward propagation in the current layer

    Returns:
    dA_prev -- Gradient of the cost with respect to the activation (of the previous layer l-1), same shape as A_prev
    dW -- Gradient of the cost with respect to W (current layer l), same shape as W
    db -- Gradient of the cost with respect to b (current layer l), same shape as b
    """
    A_prev, W, b = cache
    m = A_prev.shape[1]

    ### START CODE HERE ### (≈ 3 lines of code)
    # dW = ...
    # db = ... sum by the rows of dZ with keepdims=True
    # dA_prev = ...
    # YOUR CODE STARTS HERE
    dW=1/m*np.dot(dZ,A_prev.T)
    db=np.sum(dZ,axis=1,keepdims=True)/m
    dA_prev=np.dot(W.T,dZ)
    # YOUR CODE ENDS HERE
    
    return dA_prev, dW, db

def linear_activation_backward(dA, cache, activation):
    """
    Implement the backward propagation for the LINEAR->ACTIVATION layer.
    
    Arguments:
    dA -- post-activation gradient for current layer l 
    cache -- tuple of values (linear_cache, activation_cache) we store for computing backward propagation efficiently
    activation -- the activation to be used in this layer, stored as a text string: "sigmoid" or "relu"
    
    Returns:
    dA_prev -- Gradient of the cost with respect to the activation (of the previous layer l-1), same shape as A_prev
    dW -- Gradient of the cost with respect to W (current layer l), same shape as W
    db -- Gradient of the cost with respect to b (current layer l), same shape as b
    """
    linear_cache, activation_cache = cache
    
    if activation == "relu":
        #(≈ 2 lines of code)
        # dZ =  ...
        # dA_prev, dW, db =  ...
        # YOUR CODE STARTS HERE
        dZ=relu_backward(dA, activation_cache)
        dA_prev, dW, db=linear_backward(dZ, linear_cache)
        # YOUR CODE ENDS HERE
        
    elif activation == "sigmoid":
        #(≈ 2 lines of code)
        # dZ =  ...
        # dA_prev, dW, db =  ...
        # YOUR CODE STARTS HERE
        dZ=sigmoid_backward(dA, activation_cache)
        dA_prev, dW, db=linear_backward(dZ, linear_cache)
        
        # YOUR CODE ENDS HERE
    
    return dA_prev, dW, db

def L_model_backward(AL, Y, caches):
    """
    Implement the backward propagation for the [LINEAR->RELU] * (L-1) -> LINEAR -> SIGMOID group
    
    Arguments:
    AL -- probability vector, output of the forward propagation (L_model_forward())
    Y -- true "label" vector (containing 0 if non-cat, 1 if cat)
    caches -- list of caches containing:
                every cache of linear_activation_forward() with "relu" (it's caches[l], for l in range(L-1) i.e l = 0...L-2)
                the cache of linear_activation_forward() with "sigmoid" (it's caches[L-1])
    
    Returns:
    grads -- A dictionary with the gradients
             grads["dA" + str(l)] = ... 
             grads["dW" + str(l)] = ...
             grads["db" + str(l)] = ... 
    """
    grads = {}
    L = len(caches) # the number of layers
    m = AL.shape[1]
    Y = Y.reshape(AL.shape) # after this line, Y is the same shape as AL
    
    # Initializing the backpropagation
    #(1 line of code)
    # dAL = ...
    # YOUR CODE STARTS HERE
    dAL=-np.divide(Y,AL)+np.divide((1-Y),(1-AL))
    
    # YOUR CODE ENDS HERE
    
    # Lth layer (SIGMOID -> LINEAR) gradients. Inputs: "dAL, current_cache". Outputs: "grads["dAL-1"], grads["dWL"], grads["dbL"]
    #(approx. 5 lines)
    # current_cache = ...
    # dA_prev_temp, dW_temp, db_temp = ...
    # grads["dA" + str(L-1)] = ...
    # grads["dW" + str(L)] = ...
    # grads["db" + str(L)] = ...
    # YOUR CODE STARTS HERE
    current_cache=caches[L-1]
    dA_prev_temp, dW_temp, db_temp =linear_activation_backward(dAL,current_cache,"sigmoid")
    grads["dA" + str(L-1)]=dA_prev_temp
    grads["dW" + str(L)] =dW_temp
    grads["db" + str(L)]=db_temp
    # YOUR CODE ENDS HERE
    
    # Loop from l=L-2 to l=0
    for l in reversed(range(L-1)):
        # lth layer: (RELU -> LINEAR) gradients.
        # Inputs: "grads["dA" + str(l + 1)], current_cache". Outputs: "grads["dA" + str(l)] , grads["dW" + str(l + 1)] , grads["db" + str(l + 1)] 
        #(approx. 5 lines)
        # current_cache = ...
        # dA_prev_temp, dW_temp, db_temp = ...
        # grads["dA" + str(l)] = ...
        # grads["dW" + str(l + 1)] = ...
        # grads["db" + str(l + 1)] = ...
        # YOUR CODE STARTS HERE
        current_cache=caches[l]
        dA_prev_temp, dW_temp, db_temp =linear_activation_backward(dA_prev_temp,current_cache,"relu")
        grads["dA" + str(l)]=dA_prev_temp
        grads["dW" + str(l+1)] =dW_temp
        grads["db" + str(l+1)]=db_temp
        
        
        # YOUR CODE ENDS HERE

    return grads

def update_parameters(params, grads, learning_rate):
    """
    Update parameters using gradient descent
    
    Arguments:
    params -- python dictionary containing your parameters 
    grads -- python dictionary containing your gradients, output of L_model_backward
    
    Returns:
    parameters -- python dictionary containing your updated parameters 
                  parameters["W" + str(l)] = ... 
                  parameters["b" + str(l)] = ...
    """
    parameters = params.copy()
    L = len(parameters) // 2 # number of layers in the neural network

    # Update rule for each parameter. Use a for loop.
    #(≈ 2 lines of code)
    for l in range(L):
        # parameters["W" + str(l+1)] = ...
        # parameters["b" + str(l+1)] = ...
        # YOUR CODE STARTS HERE
        parameters["W" + str(l+1)] = parameters["W" + str(l+1)]-learning_rate*grads["dW"+str(l+1)]
        parameters["b" + str(l+1)] = parameters["b" + str(l+1)]-learning_rate*grads["db"+str(l+1)]
        
        # YOUR CODE ENDS HERE
    return parameters