[CS231n Assignment #1] 简单图像分类器——单隐层神经网络分类器

作业介绍

• 作业主页：Assignment #1

• 官方给的示例代码：assigment #1 code

知识点简单回顾

神经网络(Neural Networks) 是一种非线性分类器，区别于 SVM分类器 和 Softmax分类器，它的中间网络层通过激活函数等手段引入了非线性性，而一个比较简单的网络模型如下，它只有一个中间隐藏层：

一般的神经网络模型都包括 前向传播 和 反向传播 两个过程。以上图为例：

• 前向传播接收输入 X，然后映射到中间隐藏层 H：
  $$H=f(W_{1}X+b_1)$$
  当然，你也可以把每一个隐藏层的行为看成与之前的线性分类器类似，但是需要添加非线性的激活函数 $f()$。
• 然后中间隐藏层 $H$ 再经过映射得到我们的预测分数层 $S$
  $$S=f(W_{2}H+b_2)$$
• 这里的 $S$ 我们可以看成之前线性分类器的得分，然后后面使用 $SVM$ 或者 $Softmax$ 进行分类。
• 反向传播阶段就是根据 计算图 和 链式法则 计算出 损失函数对于参数的 梯度，然后用 SGD来更新梯度。
  
• 上图中，绿色代表前向传播，红色代表反向传播过程。

1. 下载数据集

参照之前的 KNN 分类器

2. 神经网络分类器

• 使用 jupyter nodetebook 打开文件 two_layer_net.ipynb 梳理一下流程（期间没有的python库需要自己手动安装一下）
• 首先，我们需要在cs231n/classifiers/neural_net.py中实现我们的分类器
• 而我们的分类器就类似于上图中的两层神经网络分类器，其网络结果如下
• Input -> Fully Connected Layer -> ReLu -> Fully Connected Layer -> Softmax

2.1 实现神经网络分类器

• 我们实现 neural_net.py\TwoLayerNet中简单分类器的权重初始化、前向传播、反向传播和预测过程。

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.

  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.dot(X,W1) + b1
    h2 = np.maximum(0,h1) # relu 激活函数
    scores = np.dot(h2,W2) + b2
    # If the targets are not given then jump out, we're done
    if y is None:
      return scores

    # Compute the loss
    loss = None
    # Use the Softmax classifier loss.
    # 得分函数减一个最大值，避免指数结果太大
    scores -= np.max(scores,axis = 1,keepdims = True)
    softmax_output = np.exp(scores) / np.sum(np.exp(scores),axis = 1, keepdims = True)
    loss = np.sum(-np.log(softmax_output[range(N),y])) # 只有正确分类才有损失
    # 添加正则项
    loss /= N# 平均损失
    # 注意：这里我在正则项前面加了一个0.5
    # 所以，可能