2019-03-05深度学习——线性分类器LinearClass

使用SVM Loss与Gradient Descent
先回顾一下整体步骤

• 导入图片
• 每一张图片进入分类器得到分数
• 所得分数与该张图的正确标签得分协同计算svm_loss
• 为了使svm_loss降低，对svm_loss的表达式进行求导得到梯度表达式（计算梯度的输入为loss与x）
• 利用梯度表达式计算出当loss与x所对应的梯度
• 更新权重矩阵
• 权重矩阵 = 权重矩阵 - 步长 * 梯度
• 用新的权重矩阵计算下一张图片

代码如下（暂时是这样的思路 ，后面仍会改进）

import numpy as np
import pickle
# 字符定义
# X 数据集(训练集与测试集)
# Y 标签集
# x 一个数据
# y 一个标签
# Ypred 预测标签集
# W 权重
# b 偏移
# dw 梯度
# learning_rate 步长
# scores 得分

# 超参数 
learning_rate = 0.01
# 迭代次数
times = 10

filename = 'xxxx'
filename_test = 'xxxx'

class LinearC:
    """docstring for NearestNeighbor"""
    def __init__(self):
        self.W = np.random.rand(10, 3072) * 0.001
        # self.b = np.zeros((10,1))

# 导入数据
    def load_file(self, filename):
        with open(filename, 'rb') as fo:
            data = pickle.load(fo, encoding='latin1')
        return data

# 计算梯度
    def evaluate_gradient(self, x, y):
        scores = self.W.dot(np.matrix(x).T) # + self.b
        # print(scores - scores[y] + 1)
        margins = np.maximum(0, scores - scores[y] + 1)
        margins[y] = 0
        
        self.loss.append(np.sum(margins))

        binary = margins
        binary[margins > 0] = 1
        binary[y] = -np.sum(binary)
        dW = binary * x
        return dW       

    def train(self, X, Y):
        for count in range(times):
            num = X.shape[0]
            self.loss = []
            for i in range(num):
                dW = self.evaluate_gradient(X[i], Y[i])
                self.W = self.W - learning_rate * dW

            # print(self.W)
            # square = 0
            # for i in range(self.W.shape[0]):
            #   for j in range(self.W.shape[1]):
            #       square += self.W[i,j] * self.W[i,j] 
            average_loss = np.sum(np.matrix(self.loss))/num
            print(average_loss)

# 使用模型进行预测，X是test集的数据
    def predict(self, X):
        num_test = X.shape[0]# test数据个数
        Ypred = np.zeros(num_test)# 初始化预测结果
        for i in range(num_test):
            scores = self.W.dot(np.matrix(X[i]).T) # + self.b
            Ypred[i] = np.argmax(scores)
        return Ypred

net = LinearC()

data = net.load_file(filename)
test_batch = net.load_file(filename_test)

net.train(data1['data'], data1['labels'])
result = net.predict(test_batch['data'])

print(result)