Coursera深度学习课程 DeepLearning.ai 编程作业——Building your Recurrent Neural Network - Step by Step

Building your Recurrent Neural Network - Step by Step

Welcome to Course 5’s first assignment! In this assignment, you will implement your first Recurrent Neural Network in numpy.

Recurrent Neural Networks (RNN) are very effective for Natural Language Processing and other sequence tasks because they have “memory”. They can read inputs $x^{⟨t⟩}$ (such as words) one at a time, and remember some information/context through the hidden layer activations that get passed from one time-step to the next. This allows a uni-directional RNN to take information from the past to process later inputs. A bidirection RNN can take context from both the past and the future.

Notation:

• Superscript $[l]$ denotes an object associated with the $l^{th}$ layer. ($[l]$表示第$l^{th}$层)

  • Example: $a^{[4]}$ is the $4^{th}$ layer activation. $W^{[5]}$ and $b^{[5]}$ are the $5^{th}$ layer parameters.

• Superscript $(i)$ denotes an object associated with the $i^{th}$ example. ($(i)$ 表示第 $i$ 个样本)

  • Example: $x^{(i)}$ is the $i^{th}$ training example input.

• Superscript $⟨t⟩$ denotes an object at the $t^{th}$ time-step. （$⟨t⟩$表示第t个时间段）

  • Example: $x^{⟨t⟩}$ is the input x at the $t^{th}$ time-step. $x^{(i)⟨t⟩}$ is the input at the $t^{th}$ timestep of example $i$.

• Lowerscript $i$ denotes the $i^{th}$ entry of a vector. （$a_i^{[l]}$ 表示层数激活层的第$i^{th}$个输入 ）

  • Example: $a_i^{[l]}$ denotes the $i^{th}$ entry of the activations in layer $l$.

We assume that you are already familiar with numpy and/or have completed the previous courses of the specialization. Let’s get started!

rnn_utils.py

import numpy as np

def softmax(x):
    e_x = np.exp(x - np.max(x))
    return e_x / e_x.sum(axis=0)

def smooth(loss, cur_loss):
    return loss * 0.999 + cur_loss * 0.001

def print_sample(sample_ix, ix_to_char):
    txt = ''.join(ix_to_char[ix] for ix in sample_ix)
    print ('----\n %s \n----' % (txt, ))
    
def get_initial_loss(vocab_size, seq_length):
    return -np.log(1.0/vocab_size)*seq_length

def softmax(x):
    e_x = np.exp(x - np.max(x))
    return e_x / e_x.sum(axis=0)

def initialize_parameters(n_a, n_x, n_y):
    """
    Initialize parameters with small random values
    
    Returns:
    parameters -- python dictionary containing:
                        Wax -- Weight matrix multiplying the input, numpy array of shape (n_a, n_x)
                        Waa -- Weight matrix multiplying the hidden state, numpy array of shape (n_a, n_a)
                        Wya -- Weight matrix relating the hidden-state to the output, numpy array of shape (n_y, n_a)
                        b --  Bias, numpy array of shape (n_a, 1)
                        by -- Bias relating the hidden-state to the output, numpy array of shape (n_y, 1)
    """
    np.random.seed(1)
    Wax = np.random.randn(n_a, n_x)*0.01 # input to hidden
    Waa = np.random.randn(n_a, n_a)*0.01 # hidden to hidden
    Wya = np.random.randn(n_y, n_a)*0.01 # hidden to output
    b = np.zeros((n_a, 1)) # hidden bias
    by = np.zeros((n_y, 1)) # output bias
    
    parameters = {"Wax": Wax, "Waa": Waa, "Wya": Wya, "b": b,"by": by}
    
    return parameters

def rnn_step_forward(parameters, a_prev, x):
    
    Waa, Wax, Wya, by, b = parameters['Waa'], parameters['Wax'], parameters['Wya'], parameters['by'], parameters['b']
    a_next = np.tanh(np.dot(Wax, x) + np.dot(Waa, a_prev) + b) # hidden state
    p_t = softmax(np.dot(Wya, a_next) + by) # unnormalized log probabilities for next chars # probabilities for next chars 
    
    return a_next, p_t

def rnn_step_backward(dy, gradients, parameters, x, a, a_prev):
    
    gradients['dWya'] += np.dot(dy, a.T)
    gradients['dby'] += dy
    da = np.dot(parameters['Wya'].T, dy) + gradients['da_next'] # backprop into h
    daraw = (1 - a * a) * da # backprop through tanh nonlinearity
    gradients['db'] += daraw
    gradients['dWax'] += np.dot(daraw, x.T)
    gradients['dWaa'] += np.dot(daraw, a_prev.T)
    gradients['da_next'] = np.dot(parameters['Waa'].T, daraw)
    return gradients

def update_parameters(parameters, gradients, lr):

    parameters['Wax'] += -lr * gradients['dWax']
    parameters['Waa'] += -lr * gradients['dWaa']
    parameters['Wya'] += -lr * gradients['dWya']
    parameters['b']  += -lr * gradients['db']
    parameters['by']  += -lr * gradients['dby']
    return parameters

def rnn_forward(X, Y, a0, parameters, vocab_size = 71):
    
    # Initialize x, a and y_hat as empty dictionaries
    x, a, y_hat = {}, {}, {}
    
    a[-1] = np.copy(a0)
    
    # initialize your loss to 0
    loss = 0
    
    for t in range(len(X)):
        
        # Set x[t] to be the one-hot vector representation of the t'th character in X.
        x[t] = np.zeros((vocab_size,1)) 
        x[t][X[t]] = 1
        
        # Run one step forward of the RNN
        a[t], y_hat[t] = rnn_step_forward(parameters, a[t-1], x[t])
        
        # Update the loss by substracting the cross-entropy term of this time-step from it.
        loss -= np.log(y_hat[t][Y[t],0])
        
    cache = (y_hat, a, x)
        
    return loss, cache

def rnn_backward(X, Y, parameters, cache):
    # Initialize gradients as an empty dictionary
    gradients = {}
    
    # Retrieve from cache and parameters
    (y_hat, a, x) = cache
    Waa, Wax, Wya, by, b = parameters['Waa'], parameters['Wax'], parameters['Wya'], parameters['by'], parameters['b']
    
    # each one should be initialized to zeros of the same dimension as its corresponding parameter
    gradients['dWax'], gradients['dWaa'], gradients['dWya'] = np.zeros_like(Wax), np.zeros_like(Waa), np.zeros_like(Wya)
    gradients['db'], gradients['dby'] = np.zeros_like(b), np.zeros_like(by)
    gradients['da_next'] = np.zeros_like(a[0])
    
    ### START CODE HERE ###
    # Backpropagate through time
    for t in reversed(range(len(X))):
        dy = np.copy(y_hat[t])
        dy[Y[t]] -= 1
        gradients = rnn_step_backward(dy, gradients, parameters, x[t], a[t], a[t-1])
    ### END CODE HERE ###
    
    return gradients, a

Let’s first import all the packages that you will need during this assignment.

import numpy as np
from rnn_utils import *

1 - Forward propagation for the basic Recurrent Neural Network

Later this week, you will generate music using an RNN. The basic RNN that you will implement has the structure below. In this example, $T_x=T_y$.

**Figure 1**: Basic RNN model

Here’s how you can implement an RNN:

Steps:

1. Implement the calculations needed for one time-step of the RNN. (首先执行1个时间段所需要的计算)
2. Implement a loop over $T_x$ time-steps in order to process all the inputs, one at a time. （执行很多时间步）

Let’s go!

1.1 - RNN cell

A Recurrent neural network can be seen as the repetition of a single cell. You are first going to implement the computations for a single time-step. The following figure describes the operations for a single time-step of an RNN cell.

**Figure 2**: Basic RNN cell. Takes as input $x^{\langle t \rangle}$ (current input) and $a^{\langle t - 1\rangle}$ (previous hidden state containing information from the past), and outputs $a^{\langle t \rangle}$ which is given to the next RNN cell and also used to predict $y^{\langle t \rangle}$

Exercise: Implement the RNN-cell described in Figure (2).

Instructions:

1. Compute the hidden state with tanh activation: $a^{⟨t⟩}=\tanh (W_{aa}{a}^{⟨t-1⟩}+W_{ax}{x}^{⟨t⟩}+b_a)$.
2. Using your new hidden state $a^{⟨t⟩}$, compute the prediction ${\hat{y}}^{⟨t⟩}=softmax(W_{ya}{a}^{⟨t⟩}+b_y)$. We provided you a function: softmax.
3. Store $(a^{⟨t⟩},a^{⟨t-1⟩},x^{⟨t⟩},parameters)$ in cache
4. Return $a^{⟨t⟩}$ , $y^{⟨t⟩}$ and cache

We will vectorize over $m$ examples. Thus, $x^{⟨t⟩}$ will have dimension $(n_x,m)$, and $a^{⟨t⟩}$ will have dimension $(n_a,m)$.

# GRADED FUNCTION: rnn_cell_forward

def rnn_cell_forward(xt, a_prev, parameters):
    """
    Implements a single forward step of the RNN-cell as described in Figure (2)

    Arguments:
    xt -- your input data at timestep "t", numpy array of shape (n_x, m). 
    a_prev -- Hidden state at timestep "t-1", numpy array of shape (n_a, m)
    parameters -- python dictionary containing:
                        Wax -- Weight matrix multiplying the input, numpy array of shape (n_a, n_x)
                        Waa -- Weight matrix multiplying the hidden state, numpy array of shape (n_a, n_a)
                        Wya -- Weight matrix relating the hidden-state to the output, numpy array of shape (n_y, n_a)
                        ba --  Bias, numpy array of shape (n_a, 1)
                        by -- Bias relating the hidden-state to the output, numpy array of shape (n_y, 1)
    Returns:
    a_next -- next hidden state, of shape (n_a, m)
    yt_pred -- prediction at timestep "t", numpy array of shape (n_y, m)
    cache -- tuple of values needed for the backward pass, contains (a_next, a_prev, xt, parameters)
    """
    
    # Retrieve parameters from "parameters"
    Wax = parameters["Wax"]
    Waa = parameters["Waa"]
    Wya = parameters["Wya"]
    ba = parameters["ba"]
    by = parameters["by"]
    
    ### START CODE HERE ### (≈2 lines)
    # compute next activation state using the formula given above
    a_next = np.dot(Wax,xt)+np.dot(Waa,a_prev)+ba
    a_next=  (np.exp(a_next)-np.exp(-a_next))/(np.exp(a_next)+np.exp(-a_next))
    
    # compute output of the current cell using the formula given above
    yt_pred = softmax(np.dot(Wya,a_next)+by)
    ### END CODE HERE ###
    
    # store values you need for backward propagation in cache
    cache = (a_next, a_prev, xt, parameters)
    
    return a_next, yt_pred, cache

Input:

np.random.seed(1)
xt = np.random.randn(3,10)
a_prev = np.random.randn(5,10)
Waa = np.random.randn(5,5)
Wax = np.random.randn(5,3)
Wya = np.random.randn(2,5)
ba = np.random.randn(5,1)
by = np.random.randn(2,1)
parameters = {"Waa": Waa, "Wax": Wax, "Wya": Wya, "ba": ba, "by": by}

a_next, yt_pred, cache = rnn_cell_forward(xt, a_prev, parameters)
print("a_next[4] = ", a_next[4])
print("a_next.shape = ", a_next.shape)
print("yt_pred[1] =", yt_pred[1])
print("yt_pred.shape = ", yt_pred.shape)

Output:

a_next[4] =  [ 0.59584544  0.18141802  0.61311866  0.99808218  0.85016201  0.99980978 -0.18887155  0.99815551  0.6531151   0.82872037]
a_next.shape =  (5, 10)
yt_pred[1] = [ 0.9888161   0.01682021  0.21140899  0.36817467  0.98988387  0.88945212
  0.36920224  0.9966312   0.9982559   0.17746526]
yt_pred.shape =  (2, 10)

1.2 - RNN forward pass

You can see an RNN as the repetition of the cell you’ve just built. If your input sequence of data is carried over 10 time steps, then you will copy the RNN cell 10 times. Each cell takes as input the hidden state from the previous cell ($a^{⟨t-1⟩}$) and the current time-step’s input data ($x^{⟨t⟩}$). It outputs a hidden state ($a^{⟨t⟩}$) and a prediction ($y^{⟨t⟩}$) for this time-step.

**Figure 3**: Basic RNN. The input sequence $x = (x^{\langle 1 \rangle}, x^{\langle 2 \rangle}, ..., x^{\langle T_x \rangle})$ is carried over $T_x$ time steps. The network outputs $y = (y^{\langle 1 \rangle}, y^{\langle 2 \rangle}, ..., y^{\langle T_x \rangle})$.

Exercise: Code the forward propagation of the RNN described in Figure (3).

Instructions:

1. Create a vector of zeros ($a$) that will store all the hidden