使用代码，看卷积是如何计算的。

torch.nn
torch.nn.functional

srtide 的用法，代表卷积核的步幅

import torch
import torch.nn.functional as F
#  这个是输入的一个二维矩阵
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]])kernel = torch.tensor([[1,2,1],[0,1,0],[2,1,0]])# 尺寸变化,5*5 ,3*3
input = torch.reshape(input, (1,1,5,5))
kernel  = torch.reshape(kernel, (1,1,3,3))print(input.shape)
print(kernel.shape)
# stride 代表每次移动的次数或者步幅
output = F.conv2d(input, kernel, stride=1)
print(output)output2 = F.conv2d(input, kernel, stride=2)
print(output2)output3 = F.conv2d(input, kernel, stride=1,padding=1)
print(output3)

padding 的用法为1的时候，代表把之前的矩阵四周拓展一个像素，

卷积层的使用

图片的一般都是二维矩阵，都使用CONV2D，1D 和3D用的较少

CLASStorch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', device=None, dtype=None)[SOURCE

in_channels 输入的通道数
out_channels 输出的通道数
kernel_size 卷积核的大小
stride=1 卷积核的步幅大小
padding =0 对原始数据的一个填充数
dilation =1 卷积核的对应位
groups =1
bias =True 对卷积后的数是否加减一个数
padding_mode=‘zeros’

Parameters:
输入的通道数
in_channels (int) – Number of channels in the input image
输出的通道数 当等于2，就会出现2个卷积核，就会有两个输出
out_channels (int) – Number of channels produced by the convolution
卷积核的大小例如设置为3， 卷积核就是3*3，训练过程中不断的调整。
kernel_size (int or tuple) – Size of the convolving kernel
卷积核移动的步幅
stride (int or tuple, optional) – Stride of the convolution. Default: 1
填充
padding (int, tuple or str, optional) – Padding added to all four sides of the input. Default: 0
填充的地方设置为0
padding_mode (str, optional) – 'zeros', 'reflect', 'replicate' or 'circular'. Default: 'zeros'dilation (int or tuple, optional) – Spacing between kernel elements. Default: 1groups (int, optional) – Number of blocked connections from input channels to output channels. Default: 1
偏置
bias (bool, optional) – If True, adds a learnable bias to the output. Default: True

动图，蓝色部分为输入图像，青色部分为输出图像

卷积层，

池化层
最常用的nn.MaxPool2d

torch.nn.MaxPool2d(kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False)

kernel_size (Union[int, Tuple[int, int]]) – the size of the window to take a max overstride (Union[int, Tuple[int, int]]) – the stride of the window. Default value is kernel_sizepadding (Union[int, Tuple[int, int]]) – Implicit negative infinity padding to be added on both sidesdilation (Union[int, Tuple[int, int]]) – a parameter that controls the stride of elements in the windowreturn_indices (bool) – if True, will return the max indices along with the outputs. Useful for torch.nn.MaxUnpool2d laterceil_mode (bool) – when True, will use ceil instead of floor to compute the output shape

cell_mode 为True的时候，要保留最大的值，当cell_mode为False的时候，不保留最大值。

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("../data", train=False, download=True,transform=torchvision.transforms.ToTensor())dataloader = DataLoader(dataset, batch_size=64)class Tudui(nn.Module):def __init__(self):super(Tudui, self).__init__()self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=False)def forward(self, input):output = self.maxpool1(input)return outputtudui = Tudui()writer = SummaryWriter("../logs_maxpool")
step = 0
for data in dataloader:imgs, targets = datawriter.add_images("input", imgs, step)output = tudui(imgs)writer.add_images("output", output, step)step = step + 1writer.close()

为什么池化的作用，保留输入的一个特征，同时把数据量减小，数据量减小了，训练的更快
经过一层卷积之后，来一层池化，然后再来一次非线性激活。

非线性激活层，RELU

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 SummaryWriterinput = torch.tensor([[1, -0.5],[-1, 3]])input = torch.reshape(input, (-1, 1, 2, 2))
print(input.shape)dataset = torchvision.datasets.CIFAR10("../data", train=False, download=True,transform=torchvision.transforms.ToTensor())dataloader = DataLoader(dataset, batch_size=64)class Tudui(nn.Module):def __init__(self):super(Tudui, self).__init__()self.relu1 = ReLU()self.sigmoid1 = Sigmoid()def forward(self, input):output = self.sigmoid1(input)return outputtudui = Tudui()writer = SummaryWriter("../logs_relu")
step = 0
for data in dataloader:imgs, targets = datawriter.add_images("input", imgs, global_step=step)output = tudui(imgs)writer.add_images("output", output, step)step += 1writer.close()

非线性变换的主要目的就是网络中引入一些非线性特征，非线性越多，才会训练出符合各种曲线，各种特征的一个模型，

正则化层

线性层

import torch
import torchvision
from torch import nn
from torch.nn import Linear
from torch.utils.data import DataLoaderdataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(),download=True)dataloader = DataLoader(dataset, batch_size=64)class Tudui(nn.Module):def __init__(self):super(Tudui, self).__init__()self.linear1 = Linear(196608, 10)def forward(self, input):output = self.linear1(input)return outputtudui = Tudui()for data in dataloader:imgs, targets = dataprint(imgs.shape)output = torch.flatten(imgs)print(output.shape)output = tudui(output)print(output.shape)

Sequential

CIFAR 10 model 结构， 的网络结构

import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.tensorboard import SummaryWriterclass Tudui(nn.Module):def __init__(self):super(Tudui, self).__init__()self.model1 = Sequential(Conv2d(3, 32, 5, padding=2),MaxPool2d(2),Conv2d(32, 32, 5, padding=2),MaxPool2d(2),Conv2d(32, 64, 5, padding=2),MaxPool2d(2),Flatten(),Linear(1024, 64),Linear(64, 10))def forward(self, x):x = self.model1(x)return xtudui = Tudui()
print(tudui)
input = torch.ones((64, 3, 32, 32))
output = tudui(input)
print(output.shape)writer = SummaryWriter("../logs_seq")
writer.add_graph(tudui, input)
writer.close()

损失函数与反向传播
3.1 计算实际输出和目标之间的差距（损失函数）
3.2 为更新输出提供一定的依据（反向传播） grad 梯度下降
当使用反向传播的时候，每个节点，或者每个要更新的参数，都会求出一个对应的梯度，然后对参数进行优化，最终达到Loss降低的目的， 梯度下降

误差Loss 越小越好

Loss Function用于分析实际输出与目标之间的差距。

1、L1Loss

2、MSELoss 平方差

3、CrossEntropyLoss（交叉熵损失）
当训练分类问题的时候，

-0.2+ln(exp(0.1)+exp(0.2)+exp(0.3))

# Loss Function：(CrossEntropyLoss)https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html#torch.nn.CrossEntropyLoss
import torch
from torch import nnx = torch.tensor([0.1, 0.2, 0.3])
y = torch.tensor([1])
x = torch.reshape(x, (1, 3))
loss_cross = nn.CrossEntropyLoss()result_cross = loss_cross(x, y)
print(result_cross)   # tensor(1.1019)

运行结果

tensor(1.1019)Process finished with exit code 0

3.4交叉熵在神经网络的运用

import torch
from torch import nn
import torchvision# 准备数据集：
from torch.utils.data import DataLoaderdataset = torchvision.datasets.CIFAR10("./7dataset", train=False, download=True,transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=1, drop_last=True)# 搭建神经网络：
class Model(nn.Module):def __init__(self):super(Model, self).__init__()self.model1 = nn.Sequential(nn.Conv2d(3, 32, 5, padding=2),nn.MaxPool2d(2),nn.Conv2d(32, 32, 5, padding=2),nn.MaxPool2d(2),nn.Conv2d(32, 64, 5, padding=2),nn.MaxPool2d(2),nn.Flatten(),nn.Linear(1024, 64),nn.Linear(64, 10))def forward(self, x):x = self.model1(x)return xif __name__ == "__main__":loss = nn.CrossEntropyLoss()model_1 = Model()for data in dataloader:imgs, targets = dataoutputs = model_1(imgs)result_loss = loss(outputs, targets)print(result_loss)   # 计算神经网络输出与实际的误差# 反向传播，梯度下降result_loss.backward()   # 能够生成梯度print("ok")

优化器
反向传播可以求出每个需要调节的参数，每个参数对应的梯度，有了梯度就可以利用优化器，这个优化器对参数进行调整，以达到整体误差降低的目的。
Torch.optim
设置

# 官方文档：https://pytorch.org/docs/stable/optim.html
# lr（learning rate）：学习速率
import torch
import torchvision
from torch import nn
from torch.utils.data import DataLoaderdataset = torchvision.datasets.CIFAR10("../7. dataset", train=False, transform=torchvision.transforms.ToTensor(),download=True)dataloader = DataLoader(dataset, batch_size=1, drop_last=True)class Model(nn.Module):def __init__(self):super(Model, self).__init__()self.model1 = nn.Sequential(nn.Conv2d(3, 32, 5, padding=2),nn.MaxPool2d(2),nn.Conv2d(32, 32, 5, padding=2),nn.MaxPool2d(2),nn.Conv2d(32, 64, 5, padding=2),nn.MaxPool2d(2),nn.Flatten(),nn.Linear(1024, 64),nn.Linear(64, 10))def forward(self, x):x = self.model1(x)return xloss = nn.CrossEntropyLoss()
model_1 = Model()# 1. 设置优化器：（设置随机梯度下降优化器）
optim = torch.optim.SGD(model_1.parameters(), lr=0.01)  # lr不能设置得太大或太小，太大模型会不稳定，太小模型训练会很慢（推荐开始选择较大的lr，后面选择较小的lr）for epcoh in range(5):   # 循环几次就是尽行几轮学习running_loss = 0.0   # 保存整体误差总和for data in dataloader:  # 仅进行了一轮的学习imgs, targets = dataoutputs = model_1(imgs)result_loss = loss(outputs, targets)optim.zero_grad()  # 2. 调用优化器，让网络中的每一个参数的梯度置零result_loss.backward()  # 反向传播，求出每一个节点的梯度optim.step()  # 3. 调用优化器，对每一个参数进行调优# print(result_loss)running_loss += result_loss   # 整体误差总和print(running_loss)

现有网络模型的使用
安装scipy
卸载了
pip uninstall scipy

pip install scipy
下载数据集ImageNet，数据集太大了

1. 加载VGG模型
2. pretrained=False

# 文档：https://arxiv.org/abs/1409.1556
# 官方地址：https://pytorch.org/vision/stable/models.html#classification
# 常用 VGG16 或 VGG19
# 需要安装scipy模块：pip install scipy
import torchvision.datasets# train_data = torchvision.datasets.ImageNet("../19. dataset_image_net", split="train", download=True,
#                                            transform=torchvision.transforms.ToTensor())
# 由于ImageNet的训练数据集不被公开访问了，所以不能这样下载了（该数据集有140多G，太大了）vgg16_false = torchvision.models.vgg16(pretrained=False)   # 加载网络模型，不会下载（等同于前面我们写的Model()网络架构） 参数是默认的参数
# vgg16_true = torchvision.models.vgg16(pretrained=True)   # 会从网上下载网络模型，参数是已经被训练好的参数
print(vgg16_false)

2. pretrained=True

# 文档：https://arxiv.org/abs/1409.1556
# 官方地址：https://pytorch.org/vision/stable/models.html#classification
# 常用 VGG16 或 VGG19
# 需要安装scipy模块：pip install scipy
import torchvision.datasets# train_data = torchvision.datasets.ImageNet("../19. dataset", split="train", download=True,
#                                            transform=torchvision.transforms.ToTensor())
# 由于ImageNet的训练数据集不被公开访问了，所以不能这样下载了（该数据集有140多G，太大了）# vgg16_false = torchvision.models.vgg16(pretrained=False)   # 加载网络模型，不会下载（等同于前面我们写的Model()网络架构） 参数是默认的参数
vgg16_true = torchvision.models.vgg16(pretrained=True)   # 会从网上下载网络模型，参数是已经被训练好的参数
# Downloading: "https://download.pytorch.org/models/vgg16-397923af.pth" to C:\Users\lv/.cache\torch\hub\checkpoints\vgg16-397923af.pth# print(vgg16_false)
print(vgg16_true)

运行结果，从运行结果中可以看出，最后的结果可以看出，也是分类的模型，

D:\Anaconda\envs\pytorch\python.exe "C:/Users/lv/Desktop/Pytorch/1. Pytorch的使用（第一次）/src/19. VGG模型_pretrained（现有网络模型的使用）.py"
Downloading: "https://download.pytorch.org/models/vgg16-397923af.pth" to C:\Users\lv/.cache\torch\hub\checkpoints\vgg16-397923af.pth
100.0%
VGG((features): Sequential((0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(1): ReLU(inplace=True)(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(3): ReLU(inplace=True)(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(6): ReLU(inplace=True)(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(8): ReLU(inplace=True)(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(11): ReLU(inplace=True)(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(13): ReLU(inplace=True)(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(15): ReLU(inplace=True)(16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(18): ReLU(inplace=True)(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(20): ReLU(inplace=True)(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(22): ReLU(inplace=True)(23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(25): ReLU(inplace=True)(26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(27): ReLU(inplace=True)(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(29): ReLU(inplace=True)(30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False))(avgpool): AdaptiveAvgPool2d(output_size=(7, 7))(classifier): Sequential((0): Linear(in_features=25088, out_features=4096, bias=True)(1): ReLU(inplace=True)(2): Dropout(p=0.5, inplace=False)(3): Linear(in_features=4096, out_features=4096, bias=True)(4): ReLU(inplace=True)(5): Dropout(p=0.5, inplace=False)(6): Linear(in_features=4096, out_features=1000, bias=True))
)Process finished with exit code 0

一般情况使用vgg16作为一个前置的网络结构，在vgg16后面加一些网络特征，去实现一个功能。
2. 修改VGG网络模型

# 文档：https://arxiv.org/abs/1409.1556
# 官方地址：https://pytorch.org/vision/stable/models.html#classification
# 常用 VGG16 或 VGG19
# 需要安装scipy模块：pip install scipy
import torchvision.datasets
from torch import nn# train_data = torchvision.datasets.ImageNet("../19. dataset", split="train", download=True,
#                                            transform=torchvision.transforms.ToTensor())
# 由于ImageNet的训练数据集不被公开访问了，所以不能这样下载了（该数据集有140多G，太大了）vgg16_false = torchvision.models.vgg16(pretrained=False)   # 加载网络模型，不会下载（等同于前面我们写的Model()网络架构） 参数是默认的参数
vgg16_true = torchvision.models.vgg16(pretrained=True)   # 会从网上下载网络模型，参数是已经被训练好的参数
# Downloading: "https://download.pytorch.org/models/vgg16-397923af.pth" to C:\Users\lv/.cache\torch\hub\checkpoints\vgg16-397923af.pth# print(vgg16_false)
# print(vgg16_true)train_data = torchvision.datasets.CIFAR10("../19. dataset", train=True, transform=torchvision.transforms.ToTensor(), download=True)
# 添加操作：
vgg16_true.add_module('add_linear1', nn.Linear(1000, 10))   # 添加一个线性层(添加在最后面)
# print(vgg16_true)
vgg16_true.classifier.add_module("add_linear2", nn.Linear(1000, 10))  # 添加到classifier里面
print(vgg16_true)print(vgg16_false)
# 修改操作：
vgg16_false.classifier[6] = nn.Linear(in_features=4096, out_features=10)
print(vgg16_false)

运行结果

D:\Anaconda\envs\pytorch\python.exe "C:/Users/lv/Desktop/Pytorch/1. Pytorch的使用（第一次）/src/19. VGG模型_pretrained（现有网络模型的使用）.py"
Files already downloaded and verified
VGG((features): Sequential((0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(1): ReLU(inplace=True)(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(3): ReLU(inplace=True)(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(6): ReLU(inplace=True)(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(8): ReLU(inplace=True)(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(11): ReLU(inplace=True)(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(13): ReLU(inplace=True)(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(15): ReLU(inplace=True)(16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(18): ReLU(inplace=True)(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(20): ReLU(inplace=True)(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(22): ReLU(inplace=True)(23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(25): ReLU(inplace=True)(26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(27): ReLU(inplace=True)(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(29): ReLU(inplace=True)(30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False))(avgpool): AdaptiveAvgPool2d(output_size=(7, 7))(classifier): Sequential((0): Linear(in_features=25088, out_features=4096, bias=True)(1): ReLU(inplace=True)(2): Dropout(p=0.5, inplace=False)(3): Linear(in_features=4096, out_features=4096, bias=True)(4): ReLU(inplace=True)(5): Dropout(p=0.5, inplace=False)(6): Linear(in_features=4096, out_features=1000, bias=True)(add_linear2): Linear(in_features=1000, out_features=10, bias=True))(add_linear1): Linear(in_features=1000, out_features=10, bias=True)
)
VGG((features): Sequential((0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(1): ReLU(inplace=True)(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(3): ReLU(inplace=True)(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(6): ReLU(inplace=True)(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(8): ReLU(inplace=True)(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(11): ReLU(inplace=True)(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(13): ReLU(inplace=True)(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(15): ReLU(inplace=True)(16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(18): ReLU(inplace=True)(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(20): ReLU(inplace=True)(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(22): ReLU(inplace=True)(23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(25): ReLU(inplace=True)(26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(27): ReLU(inplace=True)(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(29): ReLU(inplace=True)(30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False))(avgpool): AdaptiveAvgPool2d(output_size=(7, 7))(classifier): Sequential((0): Linear(in_features=25088, out_features=4096, bias=True)(1): ReLU(inplace=True)(2): Dropout(p=0.5, inplace=False)(3): Linear(in_features=4096, out_features=4096, bias=True)(4): ReLU(inplace=True)(5): Dropout(p=0.5, inplace=False)(6): Linear(in_features=4096, out_features=1000, bias=True))
)
VGG((features): Sequential((0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(1): ReLU(inplace=True)(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(3): ReLU(inplace=True)(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(6): ReLU(inplace=True)(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(8): ReLU(inplace=True)(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(11): ReLU(inplace=True)(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(13): ReLU(inplace=True)(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(15): ReLU(inplace=True)(16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(18): ReLU(inplace=True)(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(20): ReLU(inplace=True)(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(22): ReLU(inplace=True)(23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(25): ReLU(inplace=True)(26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(27): ReLU(inplace=True)(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(29): ReLU(inplace=True)(30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False))(avgpool): AdaptiveAvgPool2d(output_size=(7, 7))(classifier): Sequential((0): Linear(in_features=25088, out_features=4096, bias=True)(1): ReLU(inplace=True)(2): Dropout(p=0.5, inplace=False)(3): Linear(in_features=4096, out_features=4096, bias=True)(4): ReLU(inplace=True)(5): Dropout(p=0.5, inplace=False)(6): Linear(in_features=4096, out_features=10, bias=True))
)Process finished with exit code 0

模型的保存
模型的加载
完整的模型训练套路-GPU训练
完整的模型验证套路
在看下github上

模型的保存，有两种方式

import torch
import torchvisionvgg16 = torchvision.models.vgg16(pretrained=False)# 保存方式1,保存模型结构+模型参数
torch.save(vgg16, "vgg16_method1.pth")# 保存方式2  模型参数 官方推荐
torch.save(vgg16.state_dict(), "vgg16_method2.pth")

模型加载也有对应的两种方式

import torch# 方式一，保存方式1，加载模型
model = torch.load("vgg16_method1.pth")
# print(model)# 方式二，加载模型
model = torch.load("vgg16_method2.pth")print(model)

完整的模型验证套路