简单卷积公式
卷积公式
卷积和池化概念的介绍
An Intuitive Explanation of Convolutional Neural Networks
讲得更深的卷积池化介绍
用Pytorch搭建CNN
流程介绍外加代码实例（核心流程）
以下是上面核心流程的Comment
1.卷积核的搭建
卷积核（kernel）和过滤器（filter）的区别_Medlen-CSDN博客_卷积核和过滤器是一样的吗
卷积核（kernel）和过滤器（filter）的区别
import numpy as np
def convolution(img, kernel, padding=1, stride=1):
"""
img: input image with one channel
kernel: convolution kernel
"""
h, w = img.shape
kernel_size = kernel.shape[0]
# 获取扩增之后的图像
ph, pw = h + 2 * padding, w + 2 * padding
padding_img = np.zeros((ph, pw))
padding_img[padding:h + padding, padding:w + padding] = img
# 获取经过卷积之后的完整图像
result_h = (h + 2 * padding - kernel_size) // stride + 1
result_w = (w + 2 * padding - kernel_size) // stride + 1
result = np.zeros((result_h, result_w))
# 进行卷积运算
x, y = 0, 0
for i in range(0, ph - kernel_size + 1, stride):
for j in range(0, pw - kernel_size + 1, stride):
roi = padding_img[i:i + kernel_size, j:j + kernel_size]
result[x, y] = np.sum(roi * kernel)
y += 1
y = 0
x += 1
return result
def myconv2d(features, weights, padding=0, stride=1):
"""
features: input, in_channel * h * w
weights: kernel, out_channel * in_channel * kernel_size * kernel_size
return output with out_channel
"""
in_channel, h, w = features.shape
out_channel, _, kernel_size, _ = weights.shape
# height and width of output image
output_h = (h + 2 * padding - kernel_size) // stride + 1
output_w = (w + 2 * padding - kernel_size) // stride + 1
output = np.zeros((out_channel, output_h, output_w))
# call convolution out_channel * in_channel times
for i in range(out_channel):
weight = weights[i]
for j in range(in_channel):
feature_map = features[j]
kernel = weight[j]
output[i] += convolution(feature_map, kernel, padding, stride)
return output
Python numpy函数：shape用法_Daisy_HJL的博客-CSDN博客
Shape的用法
import torch
import torch.nn.functional as F
input_tensor = torch.tensor(input_data).unsqueeze(0).float()
F.conv2d(input_tensor, weight=torch.tensor(weights_data).float(), bias=None, stride=3, padding=3)
def convolutionV2(img, kernel, padding=(0,0), stride=(1,1)):
h, w = img.shape
kh, kw = kernel.shape
# height and width of image with padding
ph, pw = h + 2 * padding[0], w + 2 * padding[1]
padding_img = np.zeros((ph, pw))
padding_img[padding[0]:int(h + padding[0]), padding[1]:int(w + padding[1])] = img
# height and width of output image
result_h = (h + 2 * padding[0] - kh) // stride[0] + 1
result_w = (w + 2 * padding[1] - kw) // stride[1] + 1
result = np.zeros((result_h, result_w))
# convolution
x, y = 0, 0
for i in range(0, ph - kh + 1, stride[0]):
for j in range(0, pw - kw + 1, stride[1]):
roi = padding_img[i:i+kh, j:j+kw]
result[x, y] = np.sum(roi * kernel)
y += 1
y = 0
x += 1
return result
import torch
import torch.nn as nn
x = torch.randn(1, 1, 32, 32)
conv_layer = nn.Conv2d(in_channels=1, out_channels=3, kernel_size=3, stride=1, padding=0)
y = conv_layer(x)
print(x.shape)
print(y.shape)