[CS231n@Stanford] Assignment1-Q4 (python) Two layer neural network实现

neural_net.py

import numpy as np
import matplotlib.pyplot as plt


class TwoLayerNet(object):
  """
  A two-layer fully-connected neural network. The net has an input dimension of
  N, a hidden layer dimension of H, and performs classification over C classes.
  We train the network with a softmax loss function and L2 regularization on the
  weight matrices. The network uses a ReLU nonlinearity after the first fully
  connected layer.

  In other words, the network has the following architecture:

  input - fully connected layer - ReLU - fully connected layer - softmax

  The outputs of the second fully-connected layer are the scores for each class.
  """

  def __init__(self, input_size, hidden_size, output_size, std=1e-4):
    """
    Initialize the model. Weights are initialized to small random values and
    biases are initialized to zero. Weights and biases are stored in the
    variable self.params, which is a dictionary with the following keys:

    W1: First layer weights; has shape (D, H)
    b1: First layer biases; has shape (H,)
    W2: Second layer weights; has shape (H, C)
    b2: Second layer biases; has shape (C,)

    Inputs:
    - input_size: The dimension D of the input data.
    - hidden_size: The number of neurons H in the hidden layer.
    - output_size: The number of classes C.
    """
    self.params = {}
    self.params['W1'] = std * np.random.randn(input_size, hidden_size)
    self.params['b1'] = np.zeros(hidden_size)
    self.params['W2'] = std * np.random.randn(hidden_size, output_size)
    self.params['b2'] = np.zeros(output_size)

  def loss(self, X, y=None, reg=0.0):
    """
    Compute the loss and gradients for a two layer fully connected neural
    network.

    Inputs:
    - X: Input data of shape (N, D). Each X[i] is a training sample.
    - y: Vector of training labels. y[i] is the label for X[i], and each y[i] is
      an integer in the range 0 <= y[i] < C. This parameter is optional; if it
      is not passed then we only return scores, and if it is passed then we
      instead return the loss and gradients.
    - reg: Regularization strength.

    Returns:
    If y is None, return a matrix scores of shape (N, C) where scores[i, c] is
    the score for class c on input X[i].

    If y is not None, instead return a tuple of:
    - loss: Loss (data loss and regularization loss) for this batch of training
      samples.
    - grads: Dictionary mapping parameter names to gradients of those parameters
      with respect to the loss function; has the same keys as self.params.
    """
    # Unpack variables from the params dictionary
    W1, b1 = self.params['W1'], self.params['b1']
    W2, b2 = self.params['W2'], self.params['b2']
    N, D = X.shape

    # Compute the forward pass
    scores = None
    #############################################################################
    # TODO: Perform the forward pass, computing the class scores for the input. #
    # Store the result in the scores variable, which should be an array of      #
    # shape (N, C).                                                             #
    #############################################################################
    
    f = lambda x: np.maximum(0,x)
    h1 = f(np.dot(X, W1)+b1)
    h2 = np.dot(h1,W2)+b2

    scores = h2
    
    
    pass
    #############################################################################
    #                              END OF YOUR CODE                             #
    #############################################################################
    
    # If the targets are not given then jump out, we're done
    if y is None:
      return scores

    # Compute the loss
    loss = None
    #############################################################################
    # TODO: Finish the forward pass, and compute the loss. This should include  #
    # both the data loss and L2 regularization for W1 and W2. Store the result  #
    # in the variable loss, which should be a scalar. Use the Softmax           #
    # classifiers loss. So that your results match ours, multiply the            #
    # regularization loss by 0.5                                                #
    #############################################################################
    
    
    shift_scores = scores - np.max(scores, axis = 1).reshape(-1,1)
    softmax_output = np.exp(shift_scores)/np.sum(np.exp(shift_scores), axis = 1).reshape(-1,1)
    loss = -np.sum(np.log(softmax_output[np.arange(N), y]))
    loss /= N 
    loss +=  reg * 0.5* (np.sum(W1 * W1)+np.sum(W2 * W2))
    
    
    
    pass
    #############################################################################
    #                              END OF YOUR CODE                             #
    #############################################################################

    # Backward pass: compute gradients
    grads = {}
    #############################################################################
    # TODO: Compute the backward pass, computing the derivatives of the weights #
    # and biases. Store the results in the grads dictionary. For example,       #
    # grads['W1'] should store the gradient on W1, and be a matrix of same size #
    #############################################################################
    
    softmax_output[np.arange(N), y] += -1
    grads['W2'] =  1.0/N * h1.T.dot(softmax_output) + reg* W2
    grads['b2'] =  1.0/N * np.sum(softmax_output, axis = 0) 
    
    dh1 = softmax_output.dot(W2.T)
    dh1_ReLU = (X.dot(W1)+b1 >0)*dh1
    
    grads['W1'] = 1.0/N * X.T.dot(dh1_ReLU) + reg* W1
    grads['b1'] = 1.0/N * np.sum(dh1_ReLU, axis = 0) 
    
    
    pass
    #############################################################################
    #                              END OF YOUR CODE                             #
    #############################################################################

    return loss, grads

  def train(self, X, y, X_val, y_val,
            learning_rate=1e-3, learning_rate_decay=0.95,
            reg=1e-5, num_iters=100,
            batch_size=200, verbose=False):
    """
    Train this neural network using stochastic gradient descent.

    Inputs:
    - X: A numpy array of shape (N, D) giving training data.
    - y: A numpy array f shape (N,) giving training labels; y[i] = c means that
      X[i] has label c, where 0 <= c < C.
    - X_val: A numpy array of shape (N_val, D) giving validation data.
    - y_val: A numpy array of shape (N_val,) giving validation labels.
    - learning_rate: Scalar giving learning rate for optimization.
    - learning_rate_decay: Scalar giving factor used to decay the learning rate
      after each epoch.
    - reg: Scalar giving regularization strength.
    - num_iters: Number of steps to take when optimizing.
    - batch_size: Number of training examples to use per step.
    - verbose: boolean; if true print progress during optimization.
    """
    num_train = X.shape[0]
    iterations_per_epoch = max(num_train / batch_size, 1)

    # Use SGD to optimize the parameters in self.model
    loss_history = []
    train_acc_history = []
    val_acc_history = []

    for it in xrange(num_iters):
      X_batch = None
      y_batch = None

      #########################################################################
      # TODO: Create a random minibatch of training data and labels, storing  #
      # them in X_batch and y_batch respectively.                             #
      #########################################################################
      
      sample_index = np.random.choice(num_train, batch_size ,replace = True)
      X_batch = X[sample_index,:]
      y_batch = y[sample_index]
      
      pass
      #########################################################################
      #                             END OF YOUR CODE                          #
      #########################################################################

      # Compute loss and gradients using the current minibatch
      loss, grads = self.loss(X_batch, y=y_batch, reg=reg)
      loss_history.append(loss)

      #########################################################################
      # TODO: Use the gradients in the grads dictionary to update the         #
      # parameters of the network (stored in the dictionary self.params)      #
      # using stochastic gradient descent. You'll need to use the gradients   #
      # stored in the grads dictionary defined above.                         #
      #########################################################################
      
      
      self.params['W1'] = self.params['W1'] -learning_rate*grads['W1'] 
      self.params['W2'] = self.params['W2'] -learning_rate*grads['W2'] 
      self.params['b1'] = self.params['b1'] -learning_rate*grads['b1']
      self.params['b2'] = self.params['b2'] -learning_rate*grads['b2']       
      
      pass
      #########################################################################
      #                             END OF YOUR CODE                          #
      #########################################################################

      if verbose and it % 100 == 0:
        print 'iteration %d / %d: loss %f' % (it, num_iters, loss)

      # Every epoch, check train and val accuracy and decay learning rate.
      if it % iterations_per_epoch == 0:
        # Check accuracy
        train_acc = (self.predict(X_batch) == y_batch).mean()
        val_acc = (self.predict(X_val) == y_val).mean()
        train_acc_history.append(train_acc)
        val_acc_history.append(val_acc)

        # Decay learning rate
        learning_rate *= learning_rate_decay

    return {
      'loss_history': loss_history,
      'train_acc_history': train_acc_history,
      'val_acc_history': val_acc_history,
    }

  def predict(self, X):
    """
    Use the trained weights of this two-layer network to predict labels for
    data points. For each data point we predict scores for each of the C
    classes, and assign each data point to the class with the highest score.

    Inputs:
    - X: A numpy array of shape (N, D) giving N D-dimensional data points to
      classify.

    Returns:
    - y_pred: A numpy array of shape (N,) giving predicted labels for each of
      the elements of X. For all i, y_pred[i] = c means that X[i] is predicted
      to have class c, where 0 <= c < C.
    """
    y_pred = None

    ###########################################################################
    # TODO: Implement this function; it should be VERY simple!                #
    ###########################################################################
    
    f = lambda x: np.maximum(0,x)
    h1 = f(np.dot(X, self.params['W1'])+self.params['b1'])
    h2 = np.dot(h1,self.params['W2'])+self.params['b2']
    scores = h2

    y_pred = np.argmax(scores, axis = 1)
    
    
    pass
    ###########################################################################
    #                              END OF YOUR CODE                           #
    ###########################################################################

    return y_pred

two_layer_net.ipynb的部分代码实现

from vis_utils import visualize_grid

# Visualize the weights of the network

def show_net_weights(net):
  W1 = net.params['W1']
  W1 = W1.reshape(32, 32, 3, -1).transpose(3, 0, 1, 2)
  plt.imshow(visualize_grid(W1, padding=3).astype('uint8'))
  plt.gca().axis('off')
  plt.show()


best_net = None # store the best model into this 

results = {} 
best_val = -1  
learning_rate = [8e-4, 9e-4]  
regularization_strengths = [0.01, 0.005]  
learning_rate_decay= [0.97, 0.95]

#################################################################################
# TODO: Tune hyperparameters using the validation set. Store your best trained  #
# model in best_net.                                                            #
#                                                                               #
# To help debug your network, it may help to use visualizations similar to the  #
# ones we used above; these visualizations will have significant qualitative    #
# differences from the ones we saw above for the poorly tuned network.          #
#                                                                               #
# Tweaking hyperparameters by hand can be fun, but you might find it useful to  #
# write code to sweep through possible combinations of hyperparameters          #
# automatically like we did on the previous exercises.                          #
#################################################################################

iters = 2000    
for lr in learning_rate:    
    for reg in regularization_strengths:    
        for lrd in learning_rate_decay:
            print lr,reg,lrd
            net = TwoLayerNet(input_size, hidden_size, num_classes) 
            net.train(X_train, y_train, X_val, y_val, learning_rate=lr, reg=reg, learning_rate_decay=lrd, num_iters=iters, verbose=False)    
            
            y_train_pred = net.predict(X_train)    
            acc_train = np.mean(y_train == y_train_pred)    
            
            y_val_pred = net.predict(X_val)    
            acc_val = np.mean(y_val == y_val_pred)    
    
            results[(lr, reg, lrd)] = (acc_train, acc_val)    
            
            if best_val < acc_val:    
                best_val = acc_val    
                best_net = net   


pass
#################################################################################
#                               END OF YOUR CODE                                #
#################################################################################
# Print out results.
for lr, reg, lrd in sorted(results):
    train_accuracy, val_accuracy = results[(lr, reg, lrd)]
    print 'lr %e reg %e lrd %e train accuracy: %f val accuracy: %f' % (
                lr, reg, lrd, train_accuracy, val_accuracy)
    
print 'best validation accuracy achieved during cross-validation: %f' % best_val 
# visualize the weights of the best network
show_net_weights(best_net)

test_acc = (best_net.predict(X_test) == y_test).mean()
print 'Test accuracy: ', test_acc

lr 8.000000e-04 reg 5.000000e-03 lrd 9.500000e-01 train accuracy: 0.524082 val accuracy: 0.480000
lr 8.000000e-04 reg 5.000000e-03 lrd 9.700000e-01 train accuracy: 0.533122 val accuracy: 0.491000
lr 8.000000e-04 reg 1.000000e-02 lrd 9.500000e-01 train accuracy: 0.529204 val accuracy: 0.501000
lr 8.000000e-04 reg 1.000000e-02 lrd 9.700000e-01 train accuracy: 0.532184 val accuracy: 0.499000
lr 9.000000e-04 reg 5.000000e-03 lrd 9.500000e-01 train accuracy: 0.533469 val accuracy: 0.486000
lr 9.000000e-04 reg 5.000000e-03 lrd 9.700000e-01 train accuracy: 0.533041 val accuracy: 0.499000
lr 9.000000e-04 reg 1.000000e-02 lrd 9.500000e-01 train accuracy: 0.532510 val accuracy: 0.493000
lr 9.000000e-04 reg 1.000000e-02 lrd 9.700000e-01 train accuracy: 0.531918 val accuracy: 0.477000
best validation accuracy achieved during cross-validation: 0.501000
Test accuracy:  0.501