学习笔记|Pytorch使用教程11(nn网络层-卷积层)

学习笔记|Pytorch使用教程11

本学习笔记主要摘自“深度之眼”，做一个总结，方便查阅。 使用Pytorch版本为1.2

1d/2d/3d卷积卷积–nn.Conv2d()转置卷积–nn.ConvTranspose

一.1d/2d/3d卷积

AlexNet卷积可视化，发现卷积核学习到的是边缘，条纹，色彩这一些细节模式。 卷积维度：一般情况下，卷积核在几个维度上滑动，就是几维卷积。

一维卷积： 二维卷积： 三维卷积：

二.卷积–nn.Conv2d()

1.nn.Conv2d() 功能：对多个二维信号进行二维卷积 主要参数：

in_channels：输入通道out_channels：输出通道，等价于卷积核个数kernel_size：卷积核尺寸stride：步长padding：填充个数dilation：空洞卷积大小groups：分组卷积设置bias：偏置

空洞卷积：

尺寸计算：

简化版： out ${}_{\text{size }}=\frac{I{n}_{\text{size }}-{\text{kernel}}_{\text{size}}}{\text{stride}}+1$ 完整版： $H_{out}=\lfloor \frac{H_{in}+2\times \text{ padding }[0]-\text{ dilation }[0]\times (\text{ kerneL size }[0]-1)-1}{\text{ stride }[0]}+1\rfloor$

测试代码：

import os import torch.nn as nn from PIL import Image from torchvision import transforms from matplotlib import pyplot as plt from tools.common_tools import transform_invert#, set_seed import random random.seed(1) #set_seed(3) # 设置随机种子 # ================================= load img ================================== path_img = os.path.join(os.path.dirname(os.path.abspath(__file__)), "lena.png") img = Image.open(path_img).convert('RGB') # 0~255 # convert to tensor img_transform = transforms.Compose([transforms.ToTensor()]) img_tensor = img_transform(img) img_tensor.unsqueeze_(dim=0) # C*H*W to B*C*H*W # ================================= create convolution layer ================================== # ================ 2d flag = 1 # flag = 0 if flag: conv_layer = nn.Conv2d(3, 1, 3) # input:(i, o, size) weights:(o, i , h, w) nn.init.xavier_normal_(conv_layer.weight.data) # calculation img_conv = conv_layer(img_tensor) # ================ transposed # flag = 1 flag = 0 if flag: conv_layer = nn.ConvTranspose2d(3, 1, 3, stride=2) # input:(i, o, size) nn.init.xavier_normal_(conv_layer.weight.data) # calculation img_conv = conv_layer(img_tensor) # ================================= visualization ================================== print("卷积前尺寸:{}\n卷积后尺寸:{}".format(img_tensor.shape, img_conv.shape)) img_conv = transform_invert(img_conv[0, 0:1, ...], img_transform) img_raw = transform_invert(img_tensor.squeeze(), img_transform) plt.subplot(122).imshow(img_conv, cmap='gray') plt.subplot(121).imshow(img_raw) plt.show() import numpy as np import torch import torchvision.transforms as transforms from PIL import Image import random def set_seed(seed=1): random.seed(seed) np.random.seed(seed) torch.manual_seed(seed) torch.cuda.manual_seed(seed) def transform_invert(img_, transform_train): """ 将data 进行反transfrom操作 :param img_: tensor :param transform_train: torchvision.transforms :return: PIL image """ if 'Normalize' in str(transform_train): norm_transform = list(filter(lambda x: isinstance(x, transforms.Normalize), transform_train.transforms)) mean = torch.tensor(norm_transform[0].mean, dtype=img_.dtype, device=img_.device) std = torch.tensor(norm_transform[0].std, dtype=img_.dtype, device=img_.device) img_.mul_(std[:, None, None]).add_(mean[:, None, None]) img_ = img_.transpose(0, 2).transpose(0, 1) # C*H*W --> H*W*C if 'ToTensor' in str(transform_train): #img_ = np.array(img_) * 255 img_ = img_.cpu().detach().numpy() * 255 if img_.shape[2] == 3: img_ = Image.fromarray(img_.astype('uint8')).convert('RGB') elif img_.shape[2] == 1: img_ = Image.fromarray(img_.astype('uint8').squeeze()) else: raise Exception("Invalid img shape, expected 1 or 3 in axis 2, but got {}!".format(img_.shape[2]) ) return img_

输出：

卷积前尺寸:torch.Size([1, 3, 512, 512]) 卷积后尺寸:torch.Size([1, 1, 510, 510])

修改随机种子： 运算过程参考图示：

三.转置卷积–nn.ConvTranspose

转置卷积又称反卷积（Deconvolution）和部分跨越卷积（Fractionally-strided Convolution），用于对图像进行上采样（Upsample）。

参见知乎高票答案。 理解卷积 以及Github 1.nn.ConvTranspose2d 功能：转置卷积实现上采样 主要参数：

in_channels：输入通道out_channels：输出通道，等价于卷积核个数kernel_size：卷积核尺寸stride：步长padding：填充个数dilation：空洞卷积大小groups：分组卷积设置bias：偏置尺寸计算： 简化版（与正常卷积想法）： out size $=\left({\text{ in }}_{\text{size }}-1\right)\ast$ stride $+$ kernel ${}_{\text{size }}$ 完整版： $H_{\text{out}}=\left(H_{\text{in}}-1\right)\times$ stride $[0]-2\times$ padding $[0]+$ dilation $[0]\times$ (kernel size $[0]-1$ ) $+$ output-padding $[0]+1$

测试代码：

# ================ transposed flag = 1 # flag = 0 if flag: conv_layer = nn.ConvTranspose2d(3, 1, 3, stride=2) # input:(i, o, size) nn.init.xavier_normal_(conv_layer.weight.data) # calculation img_conv = conv_layer(img_tensor)

输出：

卷积前尺寸:torch.Size([1, 3, 512, 512]) 卷积后尺寸:torch.Size([1, 1, 1025, 1025])

棋盘效应：推荐文章《DeconOlutioN and Checkerboard Artifacts.》