cs231n assignment1--two_layer_net

神经网络部分。要先把理论知识搞的比较清楚才好写作业。

梯度推导参考：
http://www.jianshu.com/p/004c99623104multiclass
梯度推导：

调整参数部分，一开始想要把参数综合起来找一个最优参数，结果发现一次训练跑了一个小时，于是我就对每个参数进行单独训练，找到一个最好的参数，保留下来，换另一个参数。最后的测试正确率有54.8%

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
    h1 = np.maximum(0,np.dot(X,W1)+b1)
    scores = np.dot(h1,W2)+b2

    #############################################################################
    # 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).                                                             #
    #############################################################################
    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
    scores = scores - np.reshape(np.max(scores,axis=1),(N,-1))
    p = np.exp(scores)/np.reshape(np.sum(np.exp(scores),axis=1),(N,-1))
    loss = -sum(np.log(p[np.arange(N),y]))/N
    loss += 0.5*reg*np.sum(W1*W1)+0.5*reg*np.sum(W2*W2)

    #############################################################################
    # 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           #
    # classifier loss. So that your results match ours, multiply the            #
    # regularization loss by 0.5                                                #
    #############################################################################
    pass
    #############################################################################
    #                              END OF YOUR CODE                             #
    #############################################################################

    # Backward pass: compute gradients
    grads = {}
    dscores = p
    dscores[range(N),y]-=1.0
    dscores/=N
    dW2 = np.dot(h1.T,dscores)
    dh2 = np.sum(dscores,axis=0,keepdims=False)
    da2 = np.dot(dscores,W2.T)
    da2[h1<=0]=0
    dW1 = np.dot(X.T,da2)
    dh1 = np.sum(da2,axis=0,keepdims=False)
    dW2 += reg*W2
    dW1 += reg*W1
    grads['W1']=dW1
    grads['b1']=dh1
    grads['W2']=dW2
    grads['b2']=dh2

    ##########################################################