[CS231n@Stanford] Assignment2-Q2 (python) Batch Normalization 实现 和Q3(python)Dropout 实现

layers.py

def batchnorm_forward(x, gamma, beta, bn_param):
  """
  Forward pass for batch normalization.
  
  During training the sample mean and (uncorrected) sample variance are
  computed from minibatch statistics and used to normalize the incoming data.
  During training we also keep an exponentially decaying running mean of the mean
  and variance of each feature, and these averages are used to normalize data
  at test-time.

  At each timestep we update the running averages for mean and variance using
  an exponential decay based on the momentum parameter:

  running_mean = momentum * running_mean + (1 - momentum) * sample_mean
  running_var = momentum * running_var + (1 - momentum) * sample_var

  Note that the batch normalization paper suggests a different test-time
  behavior: they compute sample mean and variance for each feature using a
  large number of training images rather than using a running average. For
  this implementation we have chosen to use running averages instead since
  they do not require an additional estimation step; the torch7 implementation
  of batch normalization also uses running averages.

  Input:
  - x: Data of shape (N, D)
  - gamma: Scale parameter of shape (D,)
  - beta: Shift paremeter of shape (D,)
  - bn_param: Dictionary with the following keys:
    - mode: 'train' or 'test'; required
    - eps: Constant for numeric stability
    - momentum: Constant for running mean / variance.
    - running_mean: Array of shape (D,) giving running mean of features
    - running_var Array of shape (D,) giving running variance of features

  Returns a tuple of:
  - out: of shape (N, D)
  - cache: A tuple of values needed in the backward pass
  """
  mode = bn_param['mode']
  eps = bn_param.get('eps', 1e-5)
  momentum = bn_param.get('momentum', 0.9)

  N, D = x.shape
  running_mean = bn_param.get('running_mean', np.zeros(D, dtype=x.dtype))
  running_var = bn_param.get('running_var', np.zeros(D, dtype=x.dtype))

  out, cache = None, None
  if mode == 'train':
    #############################################################################
    # TODO: Implement the training-time forward pass for batch normalization.   #
    # Use minibatch statistics to compute the mean and variance, use these      #
    # statistics to normalize the incoming data, and scale and shift the        #
    # normalized data using gamma and beta.                                     #
    #                                                                           #
    # You should store the output in the variable out. Any intermediates that   #
    # you need for the backward pass should be stored in the cache variable.    #
    #                                                                           #
    # You should also use your computed sample mean and variance together with  #
    # the momentum variable to update the running mean and running variance,    #
    # storing your result in the running_mean and running_var variables.        #
    #############################################################################
    sample_mean = np.mean(x, axis = 0) 
    sample_var = np.var(x, axis = 0)

    x_normalized = (x-sample_mean) / np.sqrt(sample_var + eps)
    out = gamma*x_normalized + beta

    running_mean = momentum * running_mean + (1 - momentum) * sample_mean
    running_var = momentum * running_var + (1 - momentum) * sample_var

    cache = (x, sample_mean, sample_var, x_normalized, beta, gamma, eps)
    #############################################################################
    #                             END OF YOUR CODE                              #
    #############################################################################
  elif mode == 'test':
    #############################################################################
    # TODO: Implement the test-time forward pass for batch normalization. Use   #
    # the running mean and variance to normalize the incoming data, then scale  #
    # and shift the normalized data using gamma and beta. Store the result in   #
    # the out variable.                                                         #
    #############################################################################
    
    x_normalized = (x - running_mean)/np.sqrt(running_var +eps)
    out = gamma*x_normalized + beta
    
    #############################################################################
    #                             END OF YOUR CODE                              #
    #############################################################################
  else:
    raise ValueError('Invalid forward batchnorm mode "%s"' % mode)

  # Store the updated running means back into bn_param
  bn_param['running_mean'] = running_mean
  bn_param['running_var'] = running_var

  return out, cache


def batchnorm_backward(dout, cache):
  """
  Backward pass for batch normalization.
  
  For this implementation, you should write out a computation graph for
  batch normalization on paper and propagate gradients backward through
  intermediate nodes.
  
  Inputs:
  - dout: Upstream derivatives, of shape (N, D)
  - cache: Variable of intermediates from batchnorm_forward.
  
  Returns a tuple of:
  - dx: Gradient with respect to inputs x, of shape (N, D)
  - dgamma: Gradient with respect to scale parameter gamma, of shape (D,)
  - dbeta: Gradient with respect to shift parameter beta, of shape (D,)
  """
  dx, dgamma, dbeta = None, None, None
  #############################################################################
  # TODO: Implement the backward pass for batch normalization. Store the      #
  # results in the dx, dgamma, and dbeta variables.                           #
  #############################################################################
  
  (x, sample_mean, sample_var, x_normalized, beta, gamma, eps) = cache
  N = x.shape[0]
  dbeta = np.sum(dout, axis=0)
  dgamma = np.sum(x_normalized*dout, axis = 0)
  dx_normalized = gamma* dout
  dsample_var = np.sum(-1.0/2*dx_normalized*(x-sample_mean)/(sample_var+eps)**(3.0/2), axis =0)
  dsample_mean = np.sum(-1/np.sqrt(sample_var+eps)* dx_normalized, axis = 0) + 1.0/N*dsample_var *np.sum(-2*(x-sample_mean), axis = 0) 
  dx = 1/np.sqrt(sample_var+eps)*dx_normalized + dsample_var*2.0/N*(x-sample_mean) + 1.0/N*dsample_mean
  
  #############################################################################
  #                             END OF YOUR CODE                              #
  #############################################################################

  return dx, dgamma, dbeta


def batchnorm_backward_alt(dout, cache):
  """
  Alternative backward pass for batch normalization.
  
  For this implementation you should work out the derivatives for the batch
  normalizaton backward pass on paper and simplify as much as possible. You
  should be able to derive a simple expression for the backward pass.
  
  Note: This implementation should expect to receive the same cache variable
  as batchnorm_backward, but might not use all of the values in the cache.
  
  Inputs / outputs: Same as batchnorm_backward
  """
  dx, dgamma, dbeta = None, None, None
  #############################################################################
  # TODO: Implement the backward pass for batch normalization. Store the      #
  # results in the dx, dgamma, and dbeta variables.                           #
  #                                                                           #
  # After computing the gradient with respect to the centered inputs, you     #
  # should be able to compute gradients with respect to the inputs in a       #
  # single statement; our implementation fits on a single 80-character line.  #
  #############################################################################
  
  (x, sample_mean, sample_var, x_normalized, beta, gamma, eps) = cache
  N = x.shape[0]
  dbeta = np.sum(dout, axis=0)
  dgamma = np.sum(x_normalized*dout, axis = 0)
  dx_normalized = gamma* dout
  dsample_var = np.sum(-1.0/2*dx_normalized*x_normalized/(sample_var+eps), axis =0)
  dsample_mean = np.sum(-1/np.sqrt(sample_var+eps)* dx_normalized, axis = 0) # drop the second term which simplfies to zero
  dx = 1/np.sqrt(sample_var+eps)*dx_normalized + dsample_var*2.0/N*(x-sample_mean) + 1.0/N*dsample_mean
  
  #############################################################################
  #                             END OF YOUR CODE                              #
  #############################################################################
  
  return dx, dgamma, dbeta

fc_net.py

class FullyConnectedNet(object):
  """
  A fully-connected neural network with an arbitrary number of hidden layers,
  ReLU nonlinearities, and a softmax loss function. This will also implement
  dropout and batch normalization as options. For a network with L layers,
  the architecture will be
  
  {affine - [batch norm] - relu - [dropout]} x (L - 1) - affine - softmax
  
  where batch normalization and dropout are optional, and the {...} block is
  repeated L - 1 times.
  
  Similar to the TwoLayerNet above, learnable parameters are stored in the
  self.params dictionary and will be learned using the Solver class.
  """

  def __init__(self, hidden_dims, input_dim=3*32*32, num_classes=10,
               dropout=0, use_batchnorm=False, reg=0.0,
               weight_scale=1e-2, dtype=np.float32, seed=None):
    """
    Initialize a new FullyConnectedNet.
    
    Inputs:
    - hidden_dims: A list of integers giving the size of each hidden layer.
    - input_dim: An integer giving the size of the input.
    - num_classes: An integer giving the number of classes to classify.
    - dropout: Scalar between 0 and 1 giving dropout strength. If dropout=0 then
      the network should not use dropout at all.
    - use_batchnorm: Whether or not the network should use batch normalization.
    - reg: Scalar giving L2 regularization strength.
    - weight_scale: Scalar giving the standard deviation for random
      initialization of the weights.
    - dtype: A numpy datatype object; all computations will be performed using
      this datatype. float32 is faster but less accurate, so you should use
      float64 for numeric gradient checking.
    - seed: If not None, then pass this random seed to the dropout layers. This
      will make the dropout layers deteriminstic so we can gradient check the
      model.
    """
    self.use_batchnorm = use_batchnorm
    self.use_dropout = dropout > 0
    self.reg = reg
    self.num_layers = 1 + len(hidden_dims)
    self.dtype = dtype
    self.params = {}

    ############################################################################
    # TODO: Initialize the parameters of the network, storing all values in    #
    # the self.params dictionary. Store weights and biases for the first layer #
    # in W1 and b1; for the second layer use W2 and b2, etc. Weights should be #
    # initialized from a normal distribution with standard deviation equal to  #
    # weight_scale and biases should be initialized to zero.                   #
    #                                                                          #
    # When using batch normalization, store scale and shift parameters for the #
    # first layer in gamma1 and beta1; for the second layer use gamma2 and     #
    # beta2, etc. Scale parameters should be initialized to one and shift      #
    # parameters should be initialized to zero.                                #
    ############################################################################
    for i in range(1, self.num_layers+1):

       layer_input_dim = input_dim if i == 1 else hidden_dims[i-2]
       layer_output_dim = num_classes if i==self.num_layers else hidden_dims[i-1]
      
       self.params['W' + str(i)] = np.random.normal(0, weight_scale, (layer_input_dim, layer_output_dim))
       self.params['b' + str(i)] = np.zeros(layer_output_dim)

       if use_batchnorm and i!=self.num_layers:
          self.params['beta'+str(i)]=np.zeros(layer_output_dim)
          self.params['gamma'+str(i)]=np.ones(layer_output_dim)
    
    ############################################################################
    #                             END OF YOUR CODE                             #
    ############################################################################

    # When using dropout we need to pass a dropout_param dictionary to each
    # dropout layer so that the layer knows the dropout probability and the mode
    # (train / test). You can pass the same dropout_param to each dropout layer.
    self.dropout_param = {}
    if self.use_dropout:
      self.dropout_param = {'mode': 'train', 'p': dropout}
      if seed is not None:
        self.dropout_param['seed'] = seed
    
    # With batch normalization we need to keep track of running means and
    # variances, so we need to pass a special bn_param object to each batch
    # normalization layer. You should pass self.bn_params[0] to the forward pass
    # of the first batch normalization layer, self.bn_params[1] to the forward
    # pass of the second batch normalization layer, etc.
    self.bn_params = []
    if self.use_batchnorm:
      self.bn_params = [{'mode': 'train'} for i in xrange(self.num_layers - 1)]
    
    # Cast all parameters to the correct datatype
    for k, v in self.params.iteritems():
      self.params[k] = v.astype(dtype)


  def loss(self, X, y=None):
    """
    Compute loss and gradient for the fully-connected net.

    Input / output: Same as TwoLayerNet above.
    """
    X = X.astype(self.dtype)
    mode = 'test' if y is None else 'train'

    # Set train/test mode for batchnorm params and dropout param since they
    # behave differently during training and testing.
    if self.dropout_param is not None:
      self.dropout_param['mode'] = mode   
    if self.use_batchnorm:
      for bn_param in self.bn_params:
        bn_param[mode] = mode

    scores = None
    ############################################################################
    # TODO: Implement the forward pass for the fully-connected net, computing  #
    # the class scores for X and storing them in the scores variable.          #
    #                                                                          #
    # When using dropout, you'll need to pass self.dropout_param to each       #
    # dropout forward pass.                                                    #
    #                                                                          #
    # When using batch normalization, you'll need to pass self.bn_params[0] to #
    # the forward pass for the first batch normalization layer, pass           #
    # self.bn_params[1] to the forward pass for the second batch normalization #
    # layer, etc.                                                              #
    ############################################################################
    current_input = X 
    affine_relu_cache={}
    affine_bn_relu_cache={}
    dropout_cache={}


    for i in range(1, self.num_layers):
        keyW = 'W' + str(i)
        keyb = 'b' + str(i)
        if not self.use_batchnorm:
            current_input, affine_relu_cache[i] = affine_relu_forward(current_input, self.params[keyW], self.params[keyb])

        else:  
            key_gamma = 'gamma'+str(i)
            key_beta = 'beta'+str(i)
            current_input, affine_bn_relu_cache[i] = affine_bn_relu_forward(current_input, self.params[keyW], self.params[keyb],
                                                                                    self.params[key_gamma], self.params[key_beta], self.bn_params[i-1] )

        if self.use_dropout:
            current_input, dropout_cache[i] = dropout_forward(current_input,self.dropout_param)  


    # Last affine layer:
    keyW = 'W' + str(self.num_layers)
    keyb = 'b' + str(self.num_layers)
    affine_out, affine_cache = affine_forward(current_input, self.params[keyW], self.params[keyb])
    scores = affine_out
    
    ############################################################################
    #                             END OF YOUR CODE                             #
    ############################################################################

    # If test mode return early
    if mode == 'test':
      return scores

    loss, grads = 0.0, {}
    ############################################################################
    # TODO: Implement the backward pass for the fully-connected net. Store the #
    # loss in the loss variable and gradients in the grads dictionary. Compute #
    # data loss using softmax, and make sure that grads[k] holds the gradients #
    # for self.params[k]. Don't forget to add L2 regularization!               #
    #                                                                          #
    # When using batch normalization, you don't need to regularize the scale   #
    # and shift parameters.                                                    #
    #                                                                          #
    # NOTE: To ensure that your implementation matches ours and you pass the   #
    # automated tests, make sure that your L2 regularization includes a factor #
    # of 0.5 to simplify the expression for the gradient.                      #
    ############################################################################
    
    loss, dscores = softmax_loss(scores, y)

    #last layer:
    affine_dx, affine_dw, affine_db = affine_backward(dscores, affine_cache)
    grads['W'+str(self.num_layers)] = affine_dw + self.reg * self.params['W'+str(self.num_layers)]
    grads['b'+str(self.num_layers)] = affine_db
    loss += 0.5 * self.reg*(np.sum(self.params['W'+str(self.num_layers)]* self.params['W'+str(self.num_layers)]))


    for i in range(self.num_layers-1,0,-1):
        if self.use_dropout:
            affine_dx = dropout_backward(affine_dx, dropout_cache[i])

        if not self.use_batchnorm:       
            affine_dx, affine_dw, affine_db = affine_relu_backward(affine_dx, affine_relu_cache[i])

        else:       
            affine_dx, affine_dw, affine_db, dgamma, dbeta = affine_bn_relu_backward(affine_dx, affine_bn_relu_cache[i]) 
            grads['beta'+str(i)]=dbeta
            grads['gamma'+str(i)]=dgamma
        
        keyW = 'W' + str(i)
        keyb = 'b' + str(i)    
        loss += 0.5 * self.reg*(np.sum(self.params[keyW]* self.params[keyW])) 
        grads[keyW] = affine_dw + self.reg * self.params[keyW]
        grads[keyb] = affine_db

    ############################################################################
    #                             END OF YOUR CODE                             #
    ############################################################################

    return loss, grads



def affine_bn_relu_forward(x, w, b, gamma, beta, bn_param):
  """
  Convenience layer that perorms an affine transform followed by a ReLU

  Inputs:
  - x: Input to the affine layer
  - w, b: Weights for the affine layer

  Returns a tuple of:
  - out: Output from the ReLU
  - cache: Object to give to the backward pass
  """
  affine_out, fc_cache = affine_forward(x, w, b)
  bn_out, bn_cache = batchnorm_forward(affine_out, gamma, beta, bn_param)
  relu_out, relu_cache = relu_forward(bn_out)
  cache = (fc_cache, bn_cache, relu_cache)
  return relu_out, cache

def affine_bn_relu_backward(dout, cache):
  """
  Backward pass for the affine-relu convenience layer
  """
  fc_cache, bn_cache, relu_cache = cache
  drelu_out = relu_backward(dout, relu_cache)
  dbn_out, dgamma, dbeta = batchnorm_backward(drelu_out, bn_cache)
  dx, dw, db = affine_backward(dbn_out, fc_cache)
  return dx, dw, db, dgamma, dbeta

～～～～～～～～～～～～～～～～～以下dropout实现～～～～～～～～～～～～～～～～～～～

layer.py

def dropout_forward(x, dropout_param):
  """
  Performs the forward pass for (inverted) dropout.

  Inputs:
  - x: Input data, of any shape
  - dropout_param: A dictionary with the following keys:
    - p: Dropout parameter. We drop each neuron output with probability p.
    - mode: 'test' or 'train'. If the mode is train, then perform dropout;
      if the mode is test, then just return the input.
    - seed: Seed for the random number generator. Passing seed makes this
      function deterministic, which is needed for gradient checking but not in
      real networks.

  Outputs:
  - out: Array of the same shape as x.
  - cache: A tuple (dropout_param, mask). In training mode, mask is the dropout
    mask that was used to multiply the input; in test mode, mask is None.
  """
  p, mode = dropout_param['p'], dropout_param['mode']
  if 'seed' in dropout_param:
    np.random.seed(dropout_param['seed'])

  mask = None
  out = None

  if mode == 'train':
    ###########################################################################
    # TODO: Implement the training phase forward pass for inverted dropout.   #
    # Store the dropout mask in the mask variable.                            #
    ###########################################################################
    
    [N,D] = x.shape
    mask = (np.random.rand(N,D) < (1-p))/(1-p)
    out = x*mask
    
    ###########################################################################
    #                            END OF YOUR CODE                             #
    ###########################################################################
  elif mode == 'test':
    ###########################################################################
    # TODO: Implement the test phase forward pass for inverted dropout.       #
    ###########################################################################
    
    out = x
    
    ###########################################################################
    #                            END OF YOUR CODE                             #
    ###########################################################################

  cache = (dropout_param, mask)
  out = out.astype(x.dtype, copy=False)

  return out, cache


def dropout_backward(dout, cache):
  """
  Perform the backward pass for (inverted) dropout.

  Inputs:
  - dout: Upstream derivatives, of any shape
  - cache: (dropout_param, mask) from dropout_forward.
  """
  dropout_param, mask = cache
  mode = dropout_param['mode']
  
  dx = None
  if mode == 'train':
    ###########################################################################
    # TODO: Implement the training phase backward pass for inverted dropout.  #
    ###########################################################################
    
    dx = mask*dout
    
    ###########################################################################
    #                            END OF YOUR CODE                             #
    ###########################################################################
  elif mode == 'test':
    dx = dout
  return dx