小土堆-pytorch-卷积层05_笔记

从零实现卷积层

一.数据下载和自定义卷积层的实现

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.data import DataLoader

dataset =torchvision.datasets.CIFAR10("../data",train=False,transform=torchvision.transforms.ToTensor(),download=True) #不需要训练数据集 train=False

dataloader=DataLoader(dataset,batch_size=64)

class Tudui(nn.Module):

    def __init__(self):
        super(Tudui,self).__init__()
        self.conv1=Conv2d(in_channels=3,out_channels=6,kernel_size=3,stride=1,padding=0)

    def forward(self,x):
        x=self.conv1(x)
        return x

tudui = Tudui()
print(tudui)

二. 输出 卷积后tensor的形状

for data in dataloader:
    imgs,targets=data
    output =tudui(imgs)
    print(output.shape)

三.对比输入与输出的形状

for data in dataloader:
    imgs,targets=data
    output =tudui(imgs)
    print(imgs.shape)
    print(output.shape)

 彩色图片是3channel的 通过卷积之后变为了6个channel

 四.引入tensorboard

错误示范:

# 错误示范 错误原因:彩色图片是3个channel 6个channel不知道如何显示 reshape
writer=SummaryWriter("../log1")
step=0
for data in dataloader:
    imgs,targets=data
    output =tudui(imgs)
    print(imgs.shape)
    print(output.shape)
    # 输入大小:torch.Size([64, 3, 32, 32])
    writer.add_images("input",imgs,step)
    # 输出大小:torch.Size([64, 6, 30, 30])
    writer.add_images("output",output,step)
    step=step+1

正确示范:

# 正确示范
writer=SummaryWriter("../log1")
step=0
for data in dataloader:
    imgs,targets=data
    output =tudui(imgs)
    print(imgs.shape)
    print(output.shape)
    # 输入大小:torch.Size([64, 3, 32, 32])
    writer.add_images("input",imgs,step)
    # 输出大小:torch.Size([64, 6, 30, 30])
    output=torch.reshape(output,(-1,3,30,30)) # 当你不知道第一个数的值的时候 -1是根据后面的自动调整
    writer.add_images("output",output,step)
    step=step+1