RNN简单实现

卷积层反向传播

from layer_utils import *

class ThreeLayerConvNet(object):    
    """    
    A three-layer convolutional network with the following architecture:       
       conv - relu - 2x2 max pool - affine - relu - affine - softmax
    """

    def __init__(self, input_dim=(3, 32, 32), num_filters=32, filter_size=7,             
                 hidden_dim=100, num_classes=10, weight_scale=1e-3, reg=0.0,
                 dtype=np.float32):
        self.params = {}
        self.reg = reg
        self.dtype = dtype

        # Initialize weights and biases
        C, H, W = input_dim
        self.params['W1'] = weight_scale * np.random.randn(num_filters, C, filter_size, filter_size)
        self.params['b1'] = np.zeros(num_filters)
        self.params['W2'] = weight_scale * np.random.randn(num_filters*H*W/4, hidden_dim)
        self.params['b2'] = np.zeros(hidden_dim)
        self.params['W3'] = weight_scale * np.random.randn(hidden_dim, num_classes)
        self.params['b3'] = np.zeros(num_classes)

        for k, v in self.params.iteritems():    
            self.params[k] = v.astype(dtype)


    def loss(self, X, y=None):
        W1, b1 = self.params['W1'], self.params['b1']
        W2, b2 = self.params['W2'], self.params['b2']
        W3, b3 = self.params['W3'], self.params['b3']

        # pass conv_param to the forward pass for the convolutional layer
        filter_size = W1.shape[2]
        conv_param = {'stride': 1, 'pad': (filter_size - 1) / 2}

        # pass pool_param to the forward pass for the max-pooling layer
        pool_param = {'pool_height': 2, 'pool_width': 2, 'stride': 2}

        # compute the forward pass
        a1, cache1 = conv_relu_pool_forward(X, W1, b1, conv_param, pool_param)
        a2, cache2 = affine_relu_forward(a1, W2, b2)
        scores, cache3 = affine_forward(a2, W3, b3)

        if y is None:    
            return scores

        # compute the backward pass
        data_loss, dscores = softmax_loss(scores, y)
        da2, dW3, db3 = affine_backward(dscores, cache3)
        da1, dW2, db2 = affine_relu_backward(da2, cache2)
        dX, dW1, db1 = conv_relu_pool_backward(da1, cache1)

        # Add regularization
        dW1 += self.reg * W1
        dW2 += self.reg * W2
        dW3 += self.reg * W3
        reg_loss = 0.5 * self.reg * sum(np.sum(W * W) for W in [W1, W2, W3])

        loss = data_loss + reg_loss
        grads = {'W1': dW1, 'b1': db1, 'W2': dW2, 'b2': db2, 'W3': dW3, 'b3': db3}

        return loss, grads

layer_utils.py

from layers import *

def affine_relu_forward(x, w, b):
  """
  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
  """
  a, fc_cache = affine_forward(x, w, b)
  out, relu_cache = relu_forward(a)
  cache = (fc_cache, relu_cache)
  return out, cache


def affine_relu_backward(dout, cache):
  """
  Backward pass for the affine-relu convenience layer
  """
  fc_cache, relu_cache = cache
  da = relu_backward(dout, relu_cache)
  dx, dw, db = affine_backward(da, fc_cache)
  return dx, dw, db


pass


def conv_relu_forward(x, w, b, conv_param):
  """
  A convenience layer that performs a convolution followed by a ReLU.

  Inputs:
  - x: Input to the convolutional layer
  - w, b, conv_param: Weights and parameters for the convolutional layer
  
  Returns a tuple of:
  - out: Output from the ReLU
  - cache: Object to give to the backward pass
  """
  a, conv_cache = conv_forward_fast(x, w, b, conv_param)
  out, relu_cache = relu_forward(a)
  cache = (conv_cache, relu_cache)
  return out, cache


def conv_relu_backward(dout, cache):
  """
  Backward pass for the conv-relu convenience layer.
  """
  conv_cache, relu_cache = cache
  da = relu_backward(dout, relu_cache)
  dx, dw, db = conv_backward_fast(da, conv_cache)
  return dx, dw, db


def conv_relu_pool_forward(x, w, b, conv_param, pool_param):
  """
  Convenience layer that performs a convolution, a ReLU, and a pool.

  Inputs:
  - x: Input to the convolutional layer
  - w, b, conv_param: Weights and parameters for the convolutional layer
  - pool_param: Parameters for the pooling layer

  Returns a tuple of:
  - out: Output from the pooling layer
  - cache: Object to give to the backward pass
  """
  # cache = (x, w, b, conv_param)
  a, conv_cache = conv_forward_naive(x, w, b, conv_param)
  s, relu_cache = relu_forward(a)
  out, pool_cache = max_pool_forward_naive(s, pool_param)
  cache = (conv_cache, relu_cache, pool_cache)
  return out, cache


def conv_relu_pool_backward(dout, cache):
  """
  Backward pass for the conv-relu-pool convenience layer
  """
  conv_cache, relu_cache, pool_cache = cache
  ds = max_pool_backward_naive(dout, pool_cache)
  da = relu_backward(ds, relu_cache)
  dx, dw, db = conv_backward_naive(da, conv_cache)
  return dx, dw, db

layers.py

import numpy as np

def 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, db

def 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, cache

def 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 dx

def 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, dx

def 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, dx

def ReLU(x):    
    """ReLU non-linearity."""    
    return np.maximum(0, x)
def conv_forward_naive(x, w, b, conv_param):
    stride, pad = conv_param['stride'], conv_param['pad']
    N, C, H, W = x.shape
    F, C, HH, WW = w.shape
    x_padded = np.pad(x, ((0, 0), (0, 0), (pad, pad), (pad, pad)), mode='constant')
    H_new = 1 + (H + 2 * pad - HH) / stride
    W_new = 1 + (W + 2 * pad - WW) / stride
    s = stride
    out = np.zeros((N, F, H_new, W_new))

    for i in xrange(N):       # ith image    
        for f in xrange(F):   # fth filter        
            for j in xrange(H_new):            
                for k in xrange(W_new):   
                    #print x_padded[i, :, j*s:HH+j*s, k*s:WW+k*s].shape
                    #print w[f].shape  
                    #print b.shape  
                    #print np.sum((x_padded[i, :, j*s:HH+j*s, k*s:WW+k*s] * w[f]))         
                    out[i, f, j, k] = np.sum(x_padded[i, :, j*s:HH+j*s, k*s:WW+k*s] * w[f]) + b[f]

    cache = (x, w, b, conv_param)

    return out, cache


def conv_backward_naive(dout, cache):
    #print '1111'
    x, w, b, conv_param = cache
    pad = conv_param['pad']
    stride = conv_param['stride']
    F, C, HH, WW = w.shape
    N, C, H, W = x.shape
    H_new = 1 + (H + 2 * pad - HH) / stride
    W_new = 1 + (W + 2 * pad - WW) / stride

    dx = np.zeros_like(x)
    dw = np.zeros_like(w)
    db = np.zeros_like(b)

    s = stride
    x_padded = np.pad(x, ((0, 0), (0, 0), (pad, pad), (pad, pad)), 'constant')
    dx_padded = np.pad(dx, ((0, 0), (0, 0), (pad, pad), (pad, pad)), 'constant')

    for i in xrange(N):       # ith image    
        for f in xrange(F):   # fth filter        
            for j in xrange(H_new):            
                for k in xrange(W_new):                
                    window = x_padded[i, :, j*s:HH+j*s, k*s:WW+k*s]
                    db[f] += dout[i, f, j, k]                
                    dw[f] += window * dout[i, f, j, k]                
                    dx_padded[i, :, j*s:HH+j*s, k*s:WW+k*s] += w[f] * dout[i, f, j, k]

    # Unpad
    dx = dx_padded[:, :, pad:pad+H, pad:pad+W]

    return dx, dw, db
def max_pool_forward_naive(x, pool_param):
    HH, WW = pool_param['pool_height'], pool_param['pool_width']
    s = pool_param['stride']
    N, C, H, W = x.shape
    H_new = 1 + (H - HH) / s
    W_new = 1 + (W - WW) / s
    out = np.zeros((N, C, H_new, W_new))
    for i in xrange(N):    
        for j in xrange(C):        
            for k in xrange(H_new):            
                for l in xrange(W_new):                
                    window = x[i, j, k*s:HH+k*s, l*s:WW+l*s] 
                    out[i, j, k, l] = np.max(window)

    cache = (x, pool_param)

    return out, cache


def max_pool_backward_naive(dout, cache):
    x, pool_param = cache
    HH, WW = pool_param['pool_height'], pool_param['pool_width']
    s = pool_param['stride']
    N, C, H, W = x.shape
    H_new = 1 + (H - HH) / s
    W_new = 1 + (W - WW) / s
    dx = np.zeros_like(x)
    for i in xrange(N):    
        for j in xrange(C):        
            for k in xrange(H_new):            
                for l in xrange(W_new):                
                    window = x[i, j, k*s:HH+k*s, l*s:WW+l*s]                
                    m = np.max(window)               
                    dx[i, j, k*s:HH+k*s, l*s:WW+l*s] = (window == m) * dout[i, j, k, l]

    return dx