cs231n作业一之实现SVM

这个代码不能在python熵运行，是官方给的代码，我只是按照我的意思理解了一下，并把自己的理解写上去，如果想要找能运行的代码的同学请忽视，如果你找到了也可以和我分享

import numpy as npfrom random import shuffledef svm_loss_naive(W, X, y, reg):  """  Structured SVM loss function, naive implementation (with loops).  Inputs have dimension D, there are C classes, and we operate on minibatches  of N examples.  Inputs:  - W: A numpy array of shape (D, C) containing weights.  - X: A numpy array of shape (N, D) containing a minibatch of data.  - y: A numpy array of shape (N,) containing training labels; y[i] = c means    that X[i] has label c, where 0 <= c < C.  - reg: (float) regularization strength  Returns a tuple of:  - loss as single float  - gradient with respect to weights W; an array of same shape as W  """  dW = np.zeros(W.shape) # 初始化梯度为零  # compute the loss and the gradient  num_classes = W.shape[1]  num_train = X.shape[0]  loss = 0.0  for i in xrange(num_train):    scores = X[i].dot(W)#做点乘    correct_class_score = scores[y[i]]#最后的得分    for j in xrange(num_classes):      if j == y[i]:        continue      margin = scores[j] - correct_class_score + 1 #svm损失函数，Li=max(0,Sj-Syi+1)只要j!=yi          if margin > 0:        loss += margin#取最大值        dW[:,j] += X[i].T        dW[:,y[i]] += -X[i].T   # Right now the loss is a sum over all training examples, but we want it  # to be an average instead so we divide by num_train.  loss /= num_train#获得损失的平均值  dW /= num_train#梯度的平均值  # 在损失中增加正规化。  loss += 0.5 * reg * np.sum(W * W)  dW += reg * W  #############################################################################  # TODO:                                                                     #  # Compute the gradient of the loss function and store it dW.损失函数的梯度                #  # Rather that first computing the loss and then computing the derivative,   #  # it may be simpler to compute the derivative at the same time that the     #  # loss is being computed. As a result you may need to modify some of the    #  # code above to compute the gradient.                                       #  #############################################################################  return loss, dWdef svm_loss_vectorized(W, X, y, reg):  """  Structured SVM loss function, vectorized implementation.损失函数  Inputs and outputs are the same as svm_loss_naive.  """  loss = 0.0  dW = np.zeros(W.shape) #初始化梯度为零  #############################################################################  # TODO:                                                                     #  # Implement a vectorized version of the structured SVM loss, storing the    #  # result in loss.                                                           #  #############################################################################  num_train = X.shape[0]  num_classes = W.shape[1]  scores = X.dot(W)#WX  correct_class_scores = scores[range(num_train), list(y)].reshape(-1,1) #(N, 1)  margins = np.maximum(0, scores - correct_class_scores +1)  margins[range(num_train), list(y)] = 0  loss = np.sum(margins) / num_train + 0.5 * reg * np.sum(W * W)  #pass  #############################################################################  #                             END OF YOUR CODE                              #  #############################################################################  #############################################################################  # TODO:                                                                     #  # Implement a vectorized version of the gradient for the structured SVM     #  # loss, storing the result in dW.                                           #  #                                                                           #  # Hint: Instead of computing the gradient from scratch, it may be easier    #  # to reuse some of the intermediate values that you used to compute the     #  # loss.                                                                     #  #############################################################################  coeff_mat = np.zeros((num_train, num_classes))  coeff_mat[margins > 0] = 1  coeff_mat[range(num_train), list(y)] = 0  coeff_mat[range(num_train), list(y)] = -np.sum(coeff_mat, axis=1)  dW = (X.T).dot(coeff_mat)  dW = dW/num_train + reg*W  #pass  #############################################################################  #                             END OF YOUR CODE                              #  #############################################################################  return loss, dW