CS231n Assignment2--Fully-connected Neural Network

课程网址：http://cs231n.github.io/assignments2016/assignment2/

主要目的是保存一下一个比较完整的全连接神经网络代码，不带说明了，代码说明也比较详细。

dataset.py

# -*- coding: utf-8 -*-import numpy as npdef unpickle(file):    import cPickle    fo = open(file, 'rb')    dict = cPickle.load(fo)    fo.close()    return dict#load dataset of cifar10def load_CIFAR10(cifar10_dir):    #get the training data    X_train = []    y_train = []    for i in range(1,6):        dic = unpickle(cifar10_dir+"\\data_batch_"+str(i))        for item in dic["data"]:            X_train.append(item)        for item in dic["labels"]:            y_train.append(item)                #get test data    X_test = []    y_test = []    #do not know why the path is not just right as above,add a extra\    dic = unpickle(cifar10_dir+"\\test_batch")    for item in dic["data"]:       X_test.append(item)    for item in dic["labels"]:       y_test.append(item)        X_train = np.asarray(X_train)    y_train = np.asarray(y_train)    X_test = np.asarray(X_test)    y_test = np.array(y_test)    return X_train, y_train, X_test, y_testdef get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000):      """     Load the CIFAR-10 dataset from disk and perform preprocessing to prepare     it for the linear classifier. These are the same steps as we used for the SVM,     but condensed to a single function.      """      # Load the raw CIFAR-10 data     cifar10_dir = 'E:\python\cs231n\cifar-10-batches-py'   # make a change    X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)      # Subsample the data        mask = range(num_training, num_training + num_validation)        X_val = X_train[mask]                   # (1000,32,32,3)        y_val = y_train[mask]                   # (1000L,)       mask = range(num_training)        X_train = X_train[mask]                 # (49000,32,32,3)        y_train = y_train[mask]                 # (49000L,)        mask = range(num_test)       X_test = X_test[mask]                   # (1000,32,32,3)        y_test = y_test[mask]                   # (1000L,)        # preprocessing: subtract the mean image        mean_image = np.mean(X_train, axis=0)        X_train -= mean_image       X_val -= mean_image        X_test -= mean_image        # Reshape data to rows        X_train = X_train.reshape(num_training, -1)      # (49000,3072)        X_val = X_val.reshape(num_validation, -1)        # (1000,3072)        X_test = X_test.reshape(num_test, -1)            # (1000,3072)           data = {}    data['X_train'] = X_train    data['y_train'] = y_train    data['X_val'] = X_val    data['y_val'] = y_val    data['X_test'] = X_test    data['y_test'] = y_test    return data

fc_net.py

# -*- coding: utf-8 -*-__coauthor__ = 'Andrew'# 2.25.2017 #import  numpy as npimport layersclass TwoLayerNet(object):       """        A two-layer fully-connected neural network with ReLU nonlinearity and        softmax loss that uses a modular layer design. We assume an input dimension        of D, a hidden dimension of H, and perform classification over C classes.        The architecure should be affine - relu - affine - softmax.        Note that this class does not implement gradient descent; instead, it        will interact with a separate Solver object that is responsible for running        optimization.        The learnable parameters of the model are stored in the dictionary        self.params that maps parameter names to numpy arrays.       """    def __init__(self, input_dim=3*32*32, hidden_dim=100, num_classes=10,                                         weight_scale=1e-3, reg=0.0):            """            Initialize a new network.           Inputs:            - input_dim: An integer giving the size of the input            - hidden_dim: An integer giving the size of the hidden layer            - num_classes: An integer giving the number of classes to classify            - dropout: Scalar between 0 and 1 giving dropout strength.            - weight_scale: Scalar giving the standard deviation for random                         initialization of the weights.            - reg: Scalar giving L2 regularization strength.            """            self.params = {}            self.reg = reg           self.params['W1'] = weight_scale * np.random.randn(input_dim, hidden_dim)             self.params['b1'] = np.zeros((1, hidden_dim))            self.params['W2'] = weight_scale * np.random.randn(hidden_dim, num_classes)          self.params['b2'] = np.zeros((1, num_classes))    def loss(self, X, y=None):            """           Compute loss and gradient for a minibatch of data.            Inputs:            - X: Array of input data of shape (N, d_1, ..., d_k)            - y: Array of labels, of shape (N,). y[i] gives the label for X[i].          Returns:           If y is None, then run a test-time forward pass of the model and return:            - scores: Array of shape (N, C) giving classification scores, where                                scores[i, c] is the classification score for X[i] and class c.         If y is not None, then run a training-time forward and backward pass and            return a tuple of:            - loss: Scalar value giving the loss           - grads: Dictionary with the same keys as self.params, mapping parameter                              names to gradients of the loss with respect to those parameters.            """        scores = None        N = X.shape[0]        # Unpack variables from the params dictionary        W1, b1 = self.params['W1'], self.params['b1']        W2, b2 = self.params['W2'], self.params['b2']        h1, cache1 = layers.affine_forward(X, W1, b1)        h1, cacheh1 = layers.relu_forward(h1)        out, cache2 = layers.affine_forward(h1, W2, b2)        scores = out              # (N,C)        # If y is None then we are in test mode so just return scores        if y is None:               return scores        loss, grads = 0, {}        data_loss, dscores = layers.softmax_loss(scores, y)        reg_loss = 0.5 * self.reg * np.sum(W1*W1) + 0.5 * self.reg * np.sum(W2*W2)        loss = data_loss + reg_loss        # Backward pass: compute gradients        dh1, dW2, db2 = layers.affine_backward(dscores, cache2)        dh1 = layers.relu_backward(dh1,cacheh1)        dX, dW1, db1 = layers.affine_backward(dh1, cache1)                # Add the regularization gradient contribution        dW2 += self.reg * W2        dW1 += self.reg * W1        grads['W1'] = dW1        grads['b1'] = db1        grads['W2'] = dW2        grads['b2'] = db2        return loss, grads

layers.py

# -*- coding: utf-8 -*-__coauthor__ = 'Andrew'# 2 .26.2017import numpy as npdef affine_forward(x, w, b):       """        Computes the forward pass for an affine (fully-connected) layer.     The input x has shape (N, d_1, ..., d_k) and contains a minibatch of N       examples, where each example x[i] has shape (d_1, ..., d_k). We will        reshape each input into a vector of dimension D = d_1 * ... * d_k, and        then transform it to an output vector of dimension M.        Inputs:        - x: A numpy array containing input data, of shape (N, d_1, ..., d_k)        - w: A numpy array of weights, of shape (D, M)        - b: A numpy array of biases, of shape (M,)       Returns a tuple of:        - out: output, of shape (N, M)        - cache: (x, w, b)       """    out = None    # Reshape x into rows    N = x.shape[0]    x_row = x.reshape(N, -1)         # (N,D)    out = np.dot(x_row, w) + b       # (N,M)    cache = (x, w, b)    return out, cache    def affine_backward(dout, cache):       """        Computes the backward pass for an affine layer.        Inputs:        - dout: Upstream derivative, of shape (N, M)        - cache: Tuple of:     - x: Input data, of shape (N, d_1, ... d_k)        - w: Weights, of shape (D, M)        Returns a tuple of:       - dx: Gradient with respect to x, of shape (N, d1, ..., d_k)        - dw: Gradient with respect to w, of shape (D, M)     - db: Gradient with respect to b, of shape (M,)        """        x, w, b = cache        dx, dw, db = None, None, None       dx = np.dot(dout, w.T)                       # (N,D)        dx = np.reshape(dx, x.shape)                 # (N,d1,...,d_k)       x_row = x.reshape(x.shape[0], -1)            # (N,D)        dw = np.dot(x_row.T, dout)                   # (D,M)        db = np.sum(dout, axis=0, keepdims=True)     # (1,M)        return dx, dw, dbdef relu_forward(x):       """        Computes the forward pass for a layer of rectified linear units (ReLUs).        Input:        - x: Inputs, of any shape        Returns a tuple of:        - out: Output, of the same shape as x        - cache: x        """       out = None        out = ReLU(x)        cache = x        return out, cachedef relu_backward(dout, cache):       """      Computes the backward pass for a layer of rectified linear units (ReLUs).       Input:        - dout: Upstream derivatives, of any shape        - cache: Input x, of same shape as dout        Returns:        - dx: Gradient with respect to x        """        dx, x = None, cache        dx = dout        dx[x <= 0] = 0        return dxdef svm_loss(x, y):       """        Computes the loss and gradient using for multiclass SVM classification.        Inputs:        - x: Input data, of shape (N, C) where x[i, j] is the score for the jth class                  for the ith input.        - y: Vector of labels, of shape (N,) where y[i] is the label for x[i] and                  0 <= y[i] < C       Returns a tuple of:        - loss: Scalar giving the loss       - dx: Gradient of the loss with respect to x        """        N = x.shape[0]       correct_class_scores = x[np.arange(N), y]        margins = np.maximum(0, x - correct_class_scores[:, np.newaxis] + 1.0)        margins[np.arange(N), y] = 0       loss = np.sum(margins) / N       num_pos = np.sum(margins > 0, axis=1)        dx = np.zeros_like(x)       dx[margins > 0] = 1        dx[np.arange(N), y] -= num_pos        dx /= N        return loss, dxdef softmax_loss(x, y):        """        Computes the loss and gradient for softmax classification.    Inputs:        - x: Input data, of shape (N, C) where x[i, j] is the score for the jth class             for the ith input.        - y: Vector of labels, of shape (N,) where y[i] is the label for x[i] and                  0 <= y[i] < C       Returns a tuple of:        - loss: Scalar giving the loss        - dx: Gradient of the loss with respect to x       """        probs = np.exp(x - np.max(x, axis=1, keepdims=True))        probs /= np.sum(probs, axis=1, keepdims=True)        N = x.shape[0]       loss = -np.sum(np.log(probs[np.arange(N), y])) / N        dx = probs.copy()        dx[np.arange(N), y] -= 1        dx /= N        return loss, dxdef ReLU(x):        """ReLU non-linearity."""        return np.maximum(0, x)

optim.py

# -*- coding: utf-8 -*-__coauthor__ = 'Andrew'# 2 .26.2017import numpy as npdef sgd(w, dw, config=None):        """        Performs vanilla stochastic gradient descent.        config format:        - learning_rate: Scalar learning rate.        """        if config is None: config = {}        config.setdefault('learning_rate', 1e-2)        w -= config['learning_rate'] * dw        return w, configdef sgd_momentum(w, dw, config=None):        """        Performs stochastic gradient descent with momentum.        config format:        - learning_rate: Scalar learning rate.        - momentum: Scalar between 0 and 1 giving the momentum value.                    Setting momentum = 0 reduces to sgd.        - velocity: A numpy array of the same shape as w and dw used to store a moving        average of the gradients.       """       if config is None: config = {}        config.setdefault('learning_rate', 1e-2)       config.setdefault('momentum', 0.9)        v = config.get('velocity', np.zeros_like(w))        next_w = None        v = config['momentum'] * v - config['learning_rate'] * dw        next_w = w + v        config['velocity'] = v        return next_w, configdef rmsprop(x, dx, config=None):        """        Uses the RMSProp update rule, which uses a moving average of squared gradient        values to set adaptive per-parameter learning rates.        config format:        - learning_rate: Scalar learning rate.        - decay_rate: Scalar between 0 and 1 giving the decay rate for the squared                      gradient cache.        - epsilon: Small scalar used for smoothing to avoid dividing by zero.        - cache: Moving average of second moments of gradients.       """        if config is None: config = {}        config.setdefault('learning_rate', 1e-2)      config.setdefault('decay_rate', 0.99)        config.setdefault('epsilon', 1e-8)        config.setdefault('cache', np.zeros_like(x))        next_x = None        cache = config['cache']        decay_rate = config['decay_rate']        learning_rate = config['learning_rate']        epsilon = config['epsilon']        cache = decay_rate * cache + (1 - decay_rate) * (dx**2)        x += - learning_rate * dx / (np.sqrt(cache) + epsilon)      config['cache'] = cache        next_x = x        return next_x, configdef adam(x, dx, config=None):        """        Uses the Adam update rule, which incorporates moving averages of both the      gradient and its square and a bias correction term.        config format:        - learning_rate: Scalar learning rate.        - beta1: Decay rate for moving average of first moment of gradient.        - beta2: Decay rate for moving average of second moment of gradient.       - epsilon: Small scalar used for smoothing to avoid dividing by zero.        - m: Moving average of gradient.        - v: Moving average of squared gradient.        - t: Iteration number.       """        if config is None: config = {}        config.setdefault('learning_rate', 1e-3)        config.setdefault('beta1', 0.9)        config.setdefault('beta2', 0.999)        config.setdefault('epsilon', 1e-8)        config.setdefault('m', np.zeros_like(x))        config.setdefault('v', np.zeros_like(x))        config.setdefault('t', 0)       next_x = None        m = config['m']        v = config['v']        beta1 = config['beta1']        beta2 = config['beta2']        learning_rate = config['learning_rate']        epsilon = config['epsilon']       t = config['t']        t += 1        m = beta1 * m + (1 - beta1) * dx        v = beta2 * v + (1 - beta2) * (dx**2)        m_bias = m / (1 - beta1**t)        v_bias = v / (1 - beta2**t)        x += - learning_rate * m_bias / (np.sqrt(v_bias) + epsilon)        next_x = x        config['m'] = m        config['v'] = v        config['t'] = t        return next_x, config

solver.py

# -*- coding: utf-8 -*-import numpy as npimport optimclass Solver(object):  """  A Solver encapsulates all the logic necessary for training classification  models. The Solver performs stochastic gradient descent using different  update rules defined in optim.py.  The solver accepts both training and validataion data and labels so it can  periodically check classification accuracy on both training and validation  data to watch out for overfitting.  To train a model, you will first construct a Solver instance, passing the  model, dataset, and various optoins (learning rate, batch size, etc) to the  constructor. You will then call the train() method to run the optimization  procedure and train the model.    After the train() method returns, model.params will contain the parameters  that performed best on the validation set over the course of training.  In addition, the instance variable solver.loss_history will contain a list  of all losses encountered during training and the instance variables  solver.train_acc_history and solver.val_acc_history will be lists containing  the accuracies of the model on the training and validation set at each epoch.    Example usage might look something like this:    data = {    'X_train': # training data    'y_train': # training labels    'X_val': # validation data    'X_train': # validation labels  }  model = MyAwesomeModel(hidden_size=100, reg=10)  solver = Solver(model, data,                  update_rule='sgd',                  optim_config={                    'learning_rate': 1e-3,                  },                  lr_decay=0.95,                  num_epochs=10, batch_size=100,                  print_every=100)  solver.train()  A Solver works on a model object that must conform to the following API:  - model.params must be a dictionary mapping string parameter names to numpy    arrays containing parameter values.  - model.loss(X, y) must be a function that computes training-time loss and    gradients, and test-time classification scores, with the following inputs    and outputs:    Inputs:    - X: Array giving a minibatch of input data of shape (N, d_1, ..., d_k)    - y: Array of labels, of shape (N,) giving labels for X where y[i] is the      label for X[i].    Returns:    If y is None, run a test-time forward pass and return:    - scores: Array of shape (N, C) giving classification scores for X where      scores[i, c] gives the score of class c for X[i].    If y is not None, run a training time forward and backward pass and return    a tuple of:    - loss: Scalar giving the loss    - grads: Dictionary with the same keys as self.params mapping parameter      names to gradients of the loss with respect to those parameters.  """  def __init__(self, model, data, **kwargs):    """    Construct a new Solver instance.        Required arguments:    - model: A model object conforming to the API described above    - data: A dictionary of training and validation data with the following:      'X_train': Array of shape (N_train, d_1, ..., d_k) giving training images      'X_val': Array of shape (N_val, d_1, ..., d_k) giving validation images      'y_train': Array of shape (N_train,) giving labels for training images      'y_val': Array of shape (N_val,) giving labels for validation images          Optional arguments:    - update_rule: A string giving the name of an update rule in optim.py.      Default is 'sgd'.    - optim_config: A dictionary containing hyperparameters that will be      passed to the chosen update rule. Each update rule requires different      hyperparameters (see optim.py) but all update rules require a      'learning_rate' parameter so that should always be present.    - lr_decay: A scalar for learning rate decay; after each epoch the learning      rate is multiplied by this value.    - batch_size: Size of minibatches used to compute loss and gradient during      training.    - num_epochs: The number of epochs to run for during training.    - print_every: Integer; training losses will be printed every print_every      iterations.    - verbose: Boolean; if set to false then no output will be printed during      training.    """    self.model = model    self.X_train = data['X_train']    self.y_train = data['y_train']    self.X_val = data['X_val']    self.y_val = data['y_val']        # Unpack keyword arguments    self.update_rule = kwargs.pop('update_rule', 'sgd')    self.optim_config = kwargs.pop('optim_config', {})    self.lr_decay = kwargs.pop('lr_decay', 1.0)    self.batch_size = kwargs.pop('batch_size', 100)    self.num_epochs = kwargs.pop('num_epochs', 10)    self.print_every = kwargs.pop('print_every', 10)    self.verbose = kwargs.pop('verbose', True)    # Throw an error if there are extra keyword arguments    if len(kwargs) > 0:      extra = ', '.join('"%s"' % k for k in kwargs.keys())      raise ValueError('Unrecognized arguments %s' % extra)    # Make sure the update rule exists, then replace the string    # name with the actual function    if not hasattr(optim, self.update_rule):      raise ValueError('Invalid update_rule "%s"' % self.update_rule)    self.update_rule = getattr(optim, self.update_rule)    self._reset()  def _reset(self):    """    Set up some book-keeping variables for optimization. Don't call this    manually.    """    # Set up some variables for book-keeping    self.epoch = 0    self.best_val_acc = 0    self.best_params = {}    self.loss_history = []    self.train_acc_history = []    self.val_acc_history = []    # Make a deep copy of the optim_config for each parameter    self.optim_configs = {}    for p in self.model.params:      d = {k: v for k, v in self.optim_config.iteritems()}      self.optim_configs[p] = d  def _step(self):    """    Make a single gradient update. This is called by train() and should not    be called manually.    """    # Make a minibatch of training data    num_train = self.X_train.shape[0]    batch_mask = np.random.choice(num_train, self.batch_size)    X_batch = self.X_train[batch_mask]    y_batch = self.y_train[batch_mask]    # Compute loss and gradient    loss, grads = self.model.loss(X_batch, y_batch)    self.loss_history.append(loss)    # Perform a parameter update    for p, w in self.model.params.iteritems():      dw = grads[p]      config = self.optim_configs[p]      next_w, next_config = self.update_rule(w, dw, config) #因为有很多update的方法      self.model.params[p] = next_w      self.optim_configs[p] = next_config  def check_accuracy(self, X, y, num_samples=None, batch_size=100):    """    Check accuracy of the model on the provided data.        Inputs:    - X: Array of data, of shape (N, d_1, ..., d_k)    - y: Array of labels, of shape (N,)    - num_samples: If not None, subsample the data and only test the model      on num_samples datapoints.    - batch_size: Split X and y into batches of this size to avoid using too      much memory.          Returns:    - acc: Scalar giving the fraction of instances that were correctly      classified by the model.    """        # Maybe subsample the data    N = X.shape[0]    if num_samples is not None and N > num_samples:      mask = np.random.choice(N, num_samples)      N = num_samples      X = X[mask]      y = y[mask]    # Compute predictions in batches    num_batches = N / batch_size    if N % batch_size != 0:      num_batches += 1    y_pred = []    for i in xrange(num_batches):      start = i * batch_size      end = (i + 1) * batch_size      scores = self.model.loss(X[start:end])      y_pred.append(np.argmax(scores, axis=1))    y_pred = np.hstack(y_pred)    acc = np.mean(y_pred == y)    return acc  def train(self):    """    Run optimization to train the model.    """    num_train = self.X_train.shape[0]    iterations_per_epoch = max(num_train / self.batch_size, 1)    num_iterations = self.num_epochs * iterations_per_epoch    for t in xrange(num_iterations):      self._step()      # Maybe print training loss      if self.verbose and t % self.print_every == 0:        print '(Iteration %d / %d) loss: %f' % (               t + 1, num_iterations, self.loss_history[-1])      # At the end of every epoch, increment the epoch counter and decay the      # learning rate.      epoch_end = (t + 1) % iterations_per_epoch == 0      if epoch_end:        self.epoch += 1        for k in self.optim_configs:          self.optim_configs[k]['learning_rate'] *= self.lr_decay      # Check train and val accuracy on the first iteration, the last      # iteration, and at the end of each epoch.      first_it = (t == 0)      last_it = (t == num_iterations + 1)      if first_it or last_it or epoch_end:        train_acc = self.check_accuracy(self.X_train, self.y_train,                                        num_samples=1000)        val_acc = self.check_accuracy(self.X_val, self.y_val)        self.train_acc_history.append(train_acc)        self.val_acc_history.append(val_acc)        if self.verbose:          print '(Epoch %d / %d) train acc: %f; val_acc: %f' % (                 self.epoch, self.num_epochs, train_acc, val_acc)        # Keep track of the best model        if val_acc > self.best_val_acc:          self.best_val_acc = val_acc          self.best_params = {}          for k, v in self.model.params.iteritems():            self.best_params[k] = v.copy()    # At the end of training swap the best params into the model    self.model.params = self.best_params

test.py

# -*- coding: utf-8 -*-import matplotlib.pyplot as pltimport numpy as npimport fc_netfrom solver import Solverimport datasetdata = dataset.get_CIFAR10_data()model = fc_net.TwoLayerNet(reg=0.9,weight_scale=1e-4)solver = Solver(model, data,                                lr_decay=0.95,                                print_every=100, num_epochs=40, batch_size=400,                 update_rule='sgd_momentum',                                optim_config={'learning_rate': 5e-4, 'momentum': 0.5})solver.train()                 best_model = modely_test_pred = np.argmax(best_model.loss(data['X_test']), axis=1)y_val_pred = np.argmax(best_model.loss(data['X_val']), axis=1)print 'Validation set accuracy: ', (y_val_pred == data['y_val']).mean()print 'Test set accuracy: ', (y_test_pred == data['y_test']).mean()