1. 卷积层 convolution layers
import torch
import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriterdataset = torchvision.datasets.CIFAR10('./dataset',train=False,transform=torchvision.transforms.ToTensor(),download=True)
dataloader = DataLoader(dataset,batch_size=64)class Mynn(nn.Module):def __init__(self):super(Mynn, 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 xmynn = Mynn()writer = SummaryWriter('logs')
step = 0for data in dataloader:imgs, targets = dataoutput = mynn(imgs)print(imgs.shape)#torch.Size([64, 3, 32, 32])print(output.shape)#torch.Size([64, 6, 30, 30])output = torch.reshape(output, (-1, 3, 30, 30)) #-1即通道数改变后网络自动计算新的batchsize数量writer.add_images('nn_conv2d', output,step) #output为6维 不能直接显示 需要先转换维step += 1writer.close()
2. 最大池化 maxpooling layers
import torch
import torchvision
from torch import nn
from torch.nn import MaxPool2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriterdataset = torchvision.datasets.CIFAR10('./dataset',train=False,transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset,batch_size=64)# input = torch.tensor([[1, 2, 0, 3, 1],
# [0, 1, 2, 3, 1],
# [1, 2, 1, 0, 0],
# [5, 2, 3, 1, 1],
# [2, 1, 0, 1, 1]], dtype=torch.float32)
#
# input = torch.reshape(input, (-1, 1, 5, 5))
# print(input.shape)
#
#
class Mynn(nn.Module):def __init__(self):super(Mynn,self).__init__()self.maxpool1 = MaxPool2d(kernel_size=3,ceil_mode=True)def forward(self,input):output = self.maxpool1(input)return outputmynn = Mynn()# output=mynn(input)
# print(output)writer = SummaryWriter('logs')for epoch in range(3):step = 0for data in dataloader:imgs, targets = datawriter.add_images('epoch_imgs:{} '.format(epoch),imgs,step)output = mynn(imgs)# print(output.shape)writer.add_images('epoch_maxpool:{} '.format(epoch), output, step)step = step+1writer.close()
3. 非线性激活
import torch
import torchvision
from torch import nn
from torch.nn import ReLU, Sigmoid
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter# input = torch.tensor([[1, -0.5],
# [-1, 3]])
#
# input= torch.reshape(input, (-1, 1, 2, 2))
# print(input.shape)
#
# class NnRelu(nn.Module):
# def __init__(self):
# super(NnRelu, self).__init__()
# self.relu1 = ReLU(inplace=False)
#
# def forward(self, input):
# output = self.relu1(input)
# return output
#
# nnrelu = NnRelu()
#
# output = nnrelu(input)
# print(output.shape)
# print(output)dataset = torchvision.datasets.CIFAR10('./dataset',train=False, transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=64)class NnSigmoid(nn.Module):def __init__(self):super(NnSigmoid, self).__init__()self.sigmoid1 = Sigmoid()def forward(self, input):output = self.sigmoid1(input)return outputnnsig = NnSigmoid()writer = SummaryWriter('logs')step = 0
for data in dataloader:imgs, targets = datawriter.add_images('input', imgs, step)output = nnsig(imgs)writer.add_images('output', output, step)step = step+1writer.close()
4. 线性层和其他
import torch
import torchvision
from torch import nn
from torch.nn import Linear
from torch.utils.data import DataLoader#仿照VGG16最后的展平操作 1X1X4096->1X1x1000dataset = torchvision.datasets.CIFAR10('./dataset', train=False, transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset,batch_size=64,drop_last=True)class NnLinear(nn.Module):def __init__(self):super(NnLinear, self).__init__()self.linear1 = Linear(196608, 10) #这里的inpt_fetures为下方提前算出的196608 输出10自己设定的def forward(self,input):output = self.linear1(input)return outputnnreliear = NnLinear()for data in dataloader:imgs, targets = dataprint(imgs.shape)# input = torch.reshape(imgs,(1,1,1,-1))# print(input.shape)# # input = imgs.reshape(1, 1, 1, -1)input = torch.flatten(imgs)print(input.shape)output = nnreliear(input)print(output.shape)
