【智能计算系统】卷积神经网络

参考课程：https://novel.ict.ac.cn/aics/

卷积层

import numpy as np
import time  # 导入时间模块

class ConvolutionalLayer(object):
    def __init__(self, kernel_size, channel_in, channel_out, padding, stride):
        # 卷积层的初始化
        self.kernel_size = kernel_size  # 卷积核大小
        self.channel_in = channel_in  # 输入通道数
        self.channel_out = channel_out  # 输出通道数
        self.padding = padding  # 填充大小
        self.stride = stride  # 步长
        print('\tConvolutional layer with kernel size %d, input channel %d, output channel %d.' % (self.kernel_size, self.channel_in, self.channel_out))
        
    def init_param(self, std=0.01):  # 参数初始化
        self.weight = np.random.normal(loc=0.0, scale=std, size=(self.channel_in, self.kernel_size, self.kernel_size, self.channel_out))  # 初始化权重
        self.bias = np.zeros([self.channel_out])  # 初始化偏置
        
    def forward(self, input):  # 前向传播的计算
        start_time = time.time()
        self.input = input # [N, C, H, W]
        
        # 计算填充后的输入高度和宽度
        height = self.input.shape[2] + self.padding * 2
        width = self.input.shape[3] + self.padding * 2
        self.input_pad = np.zeros([self.input.shape[0], self.input.shape[1], height, width])  # 创建填充后的输入
        
        # 填充输入
        self.input_pad[:, :, self.padding:height-self.padding, self.padding:width-self.padding] = self.input
        
        height_out = (height - self.kernel_size) / self.stride + 1  # 计算输出特征图的高度
        width_out = (width - self.kernel_size) / self.stride + 1  # 计算输出特征图的宽度
        
        self.output = np.zeros([self.input.shape[0], self.channel_out, height_out, width_out])  # 初始化输出特征图
        
        # 执行卷积操作
        for idxn in range(self.input.shape[0]):  # 遍历输入的样本
            for idxc in range(self.channel_out):  # 遍历输出通道数
                for idxh in range(height_out):  # 遍历输出特征图的高度
                    for idxw in range(width_out):  # 遍历输出特征图的宽度
                        # 计算当前位置的卷积
                        hs = idxh * self.stride
                        ws = idxw * self.stride
                        self.output[idxn, idxc, idxh, idxw] = np.sum(self.weight[:, :, :, idxc] * \
                        self.input_pad[idxn, :, hs:hs+self.kernel_size, ws:ws+self.kernel_size]) + \
                        self.bias[idxc]  # 计算卷积加偏置项
        
        return self.output  # 返回输出特征图
    
    def load_param(self, weight, bias):  # 参数加载
        assert self.weight.shape == weight.shape
        assert self.bias.shape == bias.shape
        self.weight = weight
        self.bias = bias