cs231n assignment(一) svm线性分类器

最新推荐文章于 2022-05-10 16:58:06 发布

weixin_45268911

最新推荐文章于 2022-05-10 16:58:06 发布

阅读量405

点赞数 1

文章标签：深度学习机器学习 python

本文链接：https://blog.csdn.net/weixin_45268911/article/details/107279945

版权

cs231n assignment(一) svm线性分类器

这是我自己对所学内容的总结与思考，如有错误，欢迎大家指正，若有侵权，烦请告知

一、预备知识

线性分类（实质上类似于模板匹配）——f(x,W)=Wx+b
在本实验中，输入的图像都是32×32×3（=3072），所有图像均属于10个类别中的一个；f(x,W)是10×1的列向量，表示x图像在这10类中的得分；W为10×3072的矩阵；x是3072×1的矩阵，是将一幅图像所有像素展开的结果；b是10×1的常数向量（偏置项），它不与训练数据交互，只是提供给我们一些数据独立的偏好值
svm损失函数

其中，x为输入的图像，y是它的类别

f(xi,W)是预测出的xi的类别

S是每个类别预测出的分数，其中Syi表示真实类别的得分，Sj表示其他类别的得分，这里的1应该表示为△，表示一个安全边界（可以是其他值），如下图所示，横轴是训练样本真实分类的分数，纵轴是损失，可以看出随着真实分类分数的提高，损失会线性下降，直到超过一个阈值，损失降为0，因为这时我们已经完成了正确分类
关于损失函数的几个问题

Q1：SVM损失函数的最小值是0，最大值是无穷大
Q2：初始化W时，如果每个值都很小，而且所有的s都接近于0 ，则损失函数Li 接近于n-1（n为分类数），这可以作为debug的观测条件
Q3：如果把所有类别都求和（包括j=yi），损失函数会加1（因为j=yi时，取1）
Q4：如果使用求平均来代替求和，对损失函数并没有什么影响，只是等比例扩大或缩小了几个倍数
Q5：如果在max项上加一个平方，就成了另一种非线性的度量标准，它会将错误的分类放大到平方倍，因此，到底要不要加平方，是在针对具体问题时应该考虑的

损失函数的正则化
之前的损失函数只关注了训练集，可能会造成过拟合，但是我们真正的目的是让他更好地预测测试集

其中，λR(W)为正则化，它期望选取一个最简约的模型，λ为超参数，可以用交叉验证来确定，R(W)通常有以下几种形式

这里，我们举一个例子，W1[1,0,0,0],W2[0.25,0.25,0.25,0.25],它们与x点乘的结果是一样的；
若使用L2正则化，我们更倾向于W2，因为W2中每个元素的权重几乎相等，而不是像W1一样，将注意力更多地集中在某个或某些特定元素上；
若使用L1正则化，可能会更加倾向于W1（在这个例子中，两者加起来都是1，但L1背后的含义可能是0越多越简约或者说L1倾向于稀疏矩阵，）；
因此，L1和L2度量是否简约的标准不一样。
梯度计算
我感觉在这部分作业中，难点在于是梯度的计算，一直搞不清楚

如果想更多的了解梯度的推导过程，可以参见SVM_LOSS梯度推导
二、实验代码

打开cs231n/classifiers/linear_svm.py

from builtins import range
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):
            if j == y[i]:
                continue
            margin = scores[j] - correct_class_score + 1 # note delta = 1
            if margin > 0:
                loss += margin
                dW[:,y[i]]+=-X[i,:]
                dW[:,j]+=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.
    loss += 0.5*reg * np.sum(W * W)
    dW+=reg*W
    #############################################################################
    # TODO:                                                                     #
    # Compute the gradient of the loss function and store it dW.                #
    # Rather than 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.                                       #
    #############################################################################
    # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

    #pass

    # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
    
    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.                                                           #
    #############################################################################
    # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
    num_train = X.shape[0]
    num_classes = W.shape[1]
    scores = X.dot(W)
    correct_class_score = scores[np.arange(num_train), y]
    correct_class_score = np.reshape(correct_class_score, (num_train, -1))
    margins = scores - correct_class_score + 1
    margins = np.maximum(0, margins)
    margins[np.arange(num_train), y] = 0
    loss += np.sum(margins) / num_train
    loss += 0.5*reg * np.sum(W * W)

  #  pass

    # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

    #############################################################################
    # 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.                                                                     #
    #############################################################################
    # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
    margins[margins > 0] = 1
    row_sum = np.sum(margins, axis=1)
    margins[np.arange(num_train), y] = -row_sum.T
    dW = np.dot(X.T, margins)
    dW /= num_train
    dW += reg * W


  #  pass

    # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

    return loss, dW

在这里插入图片描述

打开 cs231n/classifiers/linear_classifier.py

from __future__ import print_function

from builtins import range
from builtins import object
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.

        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 range(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 (batch_size, dim)   #
            # 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.              #
            #########################################################################
            # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
            batch_inx = np.random.choice(num_train, batch_size)
            X_batch = X[batch_inx, :]
            y_batch = y[batch_inx]
            #pass

            # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

            # 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.          #
            #########################################################################
            # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
            self.W = self.W - learning_rate * grad
            #pass

            # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

            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.            #
        ###########################################################################
        # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
        score = X.dot(self.W)
        y_pred = np.argmax(score, axis=1)
        #pass

        # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
        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)

在这里插入图片描述

最后，我们可看到，准确率大概达到了37.6%，要优于上一节实现的knn算法。

weixin_45268911

关注

1
点赞
踩
4

收藏

觉得还不错? 一键收藏
0
评论
cs231n assignment(一) svm线性分类器

cs231n assignment(一) svm线性分类器一、预备知识线性分类（实质上类似于模板匹配）——f(x,W)=Wx+b在本实验中，输入的图像都是32×32×3（=3072），所有图像均属于10个类别中的一个；f(x,W)是10×1的列向量，表示x图像在这10类中的得分；W为10×3072的矩阵；x是3072×1的矩阵，是将一幅图像所有像素展开的结果；b是10×1的常数向量（偏置项），它不与训练数据交互，只是提供给我们一些数据独立的偏好值svm的折页损失函数其中，x为输入的图像，y为类
复制链接

扫一扫