cs231n assignment1 --SVM

   作业地址：https://github.com/donghaiyu233/cs231n ，欢迎fork~。

   先来看一看作业要求：

重点在于SVM的loss function、gradient descent、完成SGD的optimize和W的可视化。话不多说，开始干活！

1.SVM（Support Vector Machine）原理

    最终还是因为太懒orz，不如引用经典，以下是自己推荐一看的解释。

    最直观的理解：支持向量机（SVM）是什么意思 --知乎

    应用上的简单推导：CS231n Linear Classification

    还有更严谨的数学推导，可以翻阅李航老师的《统计学习方法》。

    最终我们得到full Multiclass SVM loss的式子，其中Δ：安全的距离；  λ：regularization strength。（每次看到这里我总会不要自主想到小公主（逃orz）

2.课程作业

linear_svm.py

svm_loss_naive()在课程网站的note上有；需要注意的两点：

    1.loss的计算,根据上面给出的公式计算即可

         一个实现max(x,0)的小技巧：

margin = (margin > 0) * margin

    2.导数的计算

        根据loss function的公式以及svm_loss_naive的计算过程，我们可以总结出：每个正确的分类即margin<0对dW无贡献，每个错误的分类会产生两个贡献，一个是对正确分类产生-xi贡献，对其对应的错误分类产生xi贡献(对W求偏导的结果)。因此以共对正确分类产生sum(margin>0)次贡献，对每一个错误分类产生一次贡献

可以由以下代码实现，最后加上正则化的导数即为最后的dW

margins01 = 1 * (margins > 0)
  margins01[rows,y] = -1*np.sum(margins01, axis=1)
  dW = np.dot(X.transpose(), margins01)
  dW /= num_train

import numpy as np
from random import shuffle
#from past.builtins import xrange

def 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) # initialize the gradient as zero

  # compute the loss and the gradient
  num_classes = W.shape[1]
  num_train = X.shape[0]
  loss = 0.0
  for i in range(num_train):
    scores = X[i].dot(W)
    correct_class_score = scores[y[i]]
    for j in range(num_classes):
      margin = scores[j] - correct_class_score + 1# note delta = 1
       #margin = X[i]*W[j] - X[i]*W[y[i]] - 1，后续分别对W[j]与W[y[i]]求偏导
    #该类的分数至少要比其它类的分数高1
      if margin > 0:
        if j != y[i]:
        #如果是同一类，则跳过，因为此时margin为delta.
          loss += margin
          dW[:, y[i]] += -1 * X[i]
          dW[:, j] += 1 * X[i]

  # 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
  dW /= num_train

  # Add regularization to the loss.
  #W * W  ==  np.square(W,W),对矩阵中的元素进行操作 
  loss += reg * np.sum(W * W)
  dW += 2*reg*W
  #broadcast,加上正则项后的dW
  #############################################################################
  # TODO:                                                                     #
  # Compute the gradient of the loss function and store it dW.                #
  # 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, dW


def svm_loss_vectorized(W, X, y, reg):
  """
  Structured SVM loss function, vectorized implementation.

  Inputs and outputs are the same as svm_loss_naive.
  """
  loss = 0.0
  dW = np.zeros(W.shape) # initialize the gradient as zero

  #############################################################################
  # TODO:                                                                     #
  # Implement a vectorized version of the structured SVM loss, storing the    #
  # result in loss.                                                           #
  #############################################################################
  scores = np.dot(X,W)
  #scores:[num_train,C]
  num_train = X.shape[0]
  rows = range(num_train)
  correct_class_score = scores[rows,y]
  #correct_class_score:[1,num_train]
  margins = np.maximum(0,scores-np.reshape(correct_class_score,[num_train,1])+1)
  margins[rows,y] = 0
  loss = np.sum(margins)
  loss /= num_train
  loss += 0.5 * reg * np.sum(W * W)
  #############################################################################
  #                             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.                                                                     #
  #############################################################################
  margins01 = 1 * (margins > 0)
  margins01[rows,y] = -1*np.sum(margins01, axis=1)
  dW = np.dot(X.transpose(), margins01)
  dW /= num_train
  dW += reg * W
  #############################################################################
  #                             END OF YOUR CODE                              #
  #############################################################################

  return loss, dW

linear_classifier.py

利用np.random.choice()进行又放回的抽样（速度更快），返回的choice作为抽样的索引；其余与梯度下降一样。

from __future__ import print_function

import numpy as np
from cs231n.classifiers.linear_svm import *
from cs231n.classifiers.softmax import *
from past.builtins import xrange


class LinearClassifier(object):

  def __init__(self):
    self.W = None

  def train(self, X, y, learning_rate=1e-3, reg=1e-5, num_iters=100,
            batch_size=200, verbose=False):
    """
    Train this linear classifier using stochastic gradient descent.
    使用SGD训练线性分类器
    Inputs:
    - X: A numpy array of shape (N, D) containing training data; there are N
      training samples each of dimension D.
    - y: A numpy array of shape (N,) containing training labels; y[i] = c
      means that X[i] has label 0 <= c < C for C classes.
    - learning_rate: (float) learning rate for optimization.
    - reg: (float) regularization strength.
    - num_iters: (integer) number of steps to take when optimizing
    - batch_size: (integer) number of training examples to use at each step.
    - verbose: (boolean) If true, print progress during optimization.

    Outputs:
    A list containing the value of the loss function at each training iteration.
    """
    num_train, dim = X.shape
    num_classes = np.max(y) + 1 # assume y takes values 0...K-1 where K is number of classes
    if self.W is None:
      # lazily initialize W
      self.W = 0.001 * np.random.randn(dim, num_classes)

    # Run stochastic gradient descent to optimize W
    loss_history = []
    for it in xrange(num_iters):
      X_batch = None
      y_batch = None

      #########################################################################
      # TODO:                                                                 #
      # Sample batch_size elements from the training data and their           #
      # corresponding labels to use in this round of gradient descent.        #
      # Store the data in X_batch and their corresponding labels in           #
      # y_batch; after sampling X_batch should have shape (dim, batch_size)   #
      # and y_batch should have shape (batch_size,)                           #
      #                                                                       #
      # Hint: Use np.random.choice to generate indices. Sampling with         #
      # replacement is faster than sampling without replacement.  
      #有放回的抽样比无放回的抽样更快
      #########################################################################
      choice = np.random.choice(num_train, batch_size, replace=True)
      X_batch = X[choice]
      y_batch = y[choice]
      #########################################################################
      #                       END OF YOUR CODE                                #
      #########################################################################

      # evaluate loss and gradient
      loss, grad = self.loss(X_batch, y_batch, reg)
      loss_history.append(loss)

      # perform parameter update
      #########################################################################
      # TODO:                                                                 #
      # Update the weights using the gradient and the learning rate.          #
      #########################################################################
      self.W -= learning_rate * grad
      #########################################################################
      #                       END OF YOUR CODE                                #
      #########################################################################

      if verbose and it % 100 == 0:
        print('iteration %d / %d: loss %f' % (it, num_iters, loss))

    return loss_history

  def predict(self, X):
    """
    Use the trained weights of this linear classifier to predict labels for
    data points.

    Inputs:
    - X: A numpy array of shape (N, D) containing training data; there are N
      training samples each of dimension D.

    Returns:
    - y_pred: Predicted labels for the data in X. y_pred is a 1-dimensional
      array of length N, and each element is an integer giving the predicted
      class.
    """
    y_pred = np.zeros(X.shape[0])
    ###########################################################################
    # TODO:                                                                   #
    # Implement this method. Store the predicted labels in y_pred.            #
    ###########################################################################
    scores = np.dot(X, self.W)
    y_pred = np.argmax(scores, axis=1)
    ###########################################################################
    #                           END OF YOUR CODE                              #
    ###########################################################################
    return y_pred
  
  def loss(self, X_batch, y_batch, reg):
    """
    Compute the loss function and its derivative. 
    Subclasses will override this.

    Inputs:
    - X_batch: A numpy array of shape (N, D) containing a minibatch of N
      data points; each point has dimension D.
    - y_batch: A numpy array of shape (N,) containing labels for the minibatch.
    - reg: (float) regularization strength.

    Returns: A tuple containing:
    - loss as a single float
    - gradient with respect to self.W; an array of the same shape as W
    """
    pass


class LinearSVM(LinearClassifier):
  """ A subclass that uses the Multiclass SVM loss function """

  def loss(self, X_batch, y_batch, reg):
    return svm_loss_vectorized(self.W, X_batch, y_batch, reg)


class Softmax(LinearClassifier):
  """ A subclass that uses the Softmax + Cross-entropy loss function """

  def loss(self, X_batch, y_batch, reg):
    return softmax_loss_vectorized(self.W, X_batch, y_batch, reg)

data_preprocessing&test

0均值

mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
X_dev -= mean_image

X增加全为1的一列，使得W增加一行（bias项），如此训练时只用考虑W

X_train = np.hstack([X_train, np.ones((X_train.shape[0], 1))])
X_val = np.hstack([X_val, np.ones((X_val.shape[0], 1))])
X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))])
X_dev = np.hstack([X_dev, np.ones((X_dev.shape[0], 1))])

以正态分布初始化W，预期loss应为C-1 = 10-1 = 9

from cs231n.classifiers.linear_svm import svm_loss_naive
import time

# generate a random SVM weight matrix of small numbers
W = np.random.randn(3073, 10) * 0.0001 

loss, grad = svm_loss_naive(W, X_dev, y_dev, 0.000005)
print('loss: %f' % (loss, ))

loss: 9.254977

##SVM正常工作

调参  tune hyperparameters(regularization strength、learning rate)

遍历两个超参数的候选范围（two loops），每次都将SVM实例化利用当前参数训练和预测，利用打擂台的方式找到最高的正确率以及相对应的svm，也可根据输出的accuracy将超参数的候选范围进一步缩小，找到最优的参数（开始时选择较小的迭代次数可以节省时间，确定一个更小的范围后可以再考虑使用更大的迭代次数）

# Use the validation set to tune hyperparameters (regularization strength and
# learning rate). You should experiment with different ranges for the learning
# rates and regularization strengths; if you are careful you should be able to
# get a classification accuracy of about 0.4 on the validation set.
learning_rates = [1e-7, 5e-5]
regularization_strengths = [2.5e4, 5e4]

# results is dictionary mapping tuples of the form
# (learning_rate, regularization_strength) to tuples of the form
# (training_accuracy, validation_accuracy). The accuracy is simply the fraction
# of data points that are correctly classified.
results = {}
best_val = -1   # The highest validation accuracy that we have seen so far.
best_svm = None # The LinearSVM object that achieved the highest validation rate.

################################################################################
# TODO:                                                                        #
# Write code that chooses the best hyperparameters by tuning on the validation #
# set. For each combination of hyperparameters, train a linear SVM on the      #
# training set, compute its accuracy on the training and validation sets, and  #
# store these numbers in the results dictionary. In addition, store the best   #
# validation accuracy in best_val and the LinearSVM object that achieves this  #
# accuracy in best_svm.                                                        #
#                                                                              #
# Hint: You should use a small value for num_iters as you develop your         #
# validation code so that the SVMs don't take much time to train; once you are #
# confident that your validation code works, you should rerun the validation   #
# code with a larger value for num_iters.                                      #
################################################################################
for lr in learning_rates:
    for reg in regularization_strengths:
        svm = LinearSVM()
        svm.train(X_train, y_train, lr, reg, num_iters=2000, verbose=False)
        y_train_pred = svm.predict(X_train)
        y_val_pred = svm.predict(X_val)
        training_accuracies = np.mean(y_train == y_train_pred)
        validation_accuracies = np.mean(y_val == y_val_pred)
        results[(lr, reg)] = (training_accuracies, validation_accuracies)
        if validation_accuracies > best_val:
            best_val = validation_accuracies
            best_svm = svm
################################################################################
#                              END OF YOUR CODE                                #
################################################################################
    
# Print out results.
for lr, reg in sorted(results):
    train_accuracy, val_accuracy = results[(lr, reg)]
    print('lr %e reg %e train accuracy: %f val accuracy: %f' % (
                lr, reg, train_accuracy, val_accuracy))
    
print('best validation accuracy achieved during cross-validation: %f' % best_val)

output

一番调参后，得到accuracy超过40%的W，算是把这个作业给完成了