神经网络基本使用

最新推荐文章于 2024-08-30 22:25:47 发布

木木_l

最新推荐文章于 2024-08-30 22:25:47 发布

阅读量506

点赞数 9

分类专栏：土堆|Pytorch 文章标签：神经网络深度学习 pytorch

本文链接：https://blog.csdn.net/weixin_47622017/article/details/136620125

版权

土堆|Pytorch 专栏收录该内容

16 篇文章 1 订阅

订阅专栏

本文介绍了使用PyTorch实现的基础深度学习模块，包括卷积层、最大池化层以及非线性激活（ReLU和Sigmoid）。通过CIFAR-10数据集实例展示了如何在模型中运用这些组件，并使用TensorBoard记录和可视化训练过程。

摘要由CSDN通过智能技术生成

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 SummaryWriter

dataset = 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 x


mynn = Mynn()

writer = SummaryWriter('logs')
step = 0

for data in dataloader:
    imgs, targets = data
    output = 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 += 1

writer.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 SummaryWriter

dataset = 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 output

mynn = Mynn()

# output=mynn(input)
# print(output)

writer =  SummaryWriter('logs')

for epoch in range(3):
    step = 0
    for data in dataloader:
        imgs, targets = data
        writer.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+1

writer.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 output

nnsig = NnSigmoid()

writer = SummaryWriter('logs')

step = 0
for data in dataloader:
    imgs, targets = data
    writer.add_images('input', imgs, step)
    output = nnsig(imgs)
    writer.add_images('output', output, step)
    step = step+1
    
writer.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->1X1x1000

dataset = 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 output

nnreliear = NnLinear()

for data in dataloader:
    imgs, targets = data
    print(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)