想入门pytorch强化学习，就去找pytorch的课来看。B站上播放量最高的就是小土堆的课，整体跟下来感觉内容还是很详细的，但和我的预期不太一样，这个是DL的不是RL的，不过作为对于pytorch使用的初期了解也是很好的，这篇博客就把整个学习过程做一个梳理。
注意：本笔记使用的数据集全部都是CIFAR10，下载比较简单~，下面开始
数据读取
在读取之前，需要先准备好数据了，对于CIFAR10,可以离线下载(网址：https://download.pytorch.org/tutorial/hymenoptera_data.zip)，下载后保存到dataset文件夹，目录结构如下：
下面就是对于图片的读取，起初的读取都是通过PIL，后面会换成dataloader，主要是自己定义了一个类，传递了两个参数，实例如下：
read_data.py
# function：使用PIL完成数据的读取，可查看
from torch.utils.data import Dataset
from PIL import Image
import os
class MyData(Dataset):
def __init__(self, root_dir, label_dir):
self.root_dir = root_dir
self.label_dir = label_dir
self.path = os.path.join(self.root_dir, self.label_dir)
self.img_path = os.listdir(self.path)
def __getitem__(self, idx):
img_name = self.img_path[idx]
img_item_path = os.path.join(self.root_dir, self.label_dir, img_name)
img = Image.open(img_item_path)
img.show()
label = self.label_dir
return img, label
def __len__(self):
return len(self.img_path)
root_dir = "dataset/train"
ants_label_dir = "ants"
ants_datasets = MyData(root_dir, ants_label_dir)
ants_datasets.__getitem__(0) # 输入查看图片编号即可
print(len(ants_datasets))
tensorboard使用
tensorboard是一个可视化工具，可以用来看图片或者分析数据。
使用方法：
1.按照主要模板写框架：
from torch.utils.tensorboard import SummaryWriter
writer = SummaryWriter("logs") # 这个logs是生成日志文件的文件夹名，可随意更换
writer.add_image() # 添加一张图像，第一个参数是tag，第二个是数据本身，第三个是编号
wirter.add_images() # 添加多张图像，第一个是tag，第二个是数据本身，第三个是编号
writer.add_scalar() # 添加数值 第一个参数是tag, 再后是先y后x, 例如：writer.add_scalar("y=2x", 2*i, i)
writer.add_graph(tudui, input) # 查看网络结构，tudui是模型，input是模型输入
writer.close()
执行代码过后就会在logs文件夹下生成event文件：
2.在terminal中按照tensorboard --logdir=logs使用：
3.点进localhost的链接中就可以查看了：
test_tb.py
# function：展示tensorboard的使用
from torch.utils.tensorboard import SummaryWriter
import numpy as np
from PIL import Image
writer = SummaryWriter("logs")
# add_image使用
image_path = "dataset/train/ants/5650366_e22b7e1065.jpg"
image_path1 = "dataset/train/ants/6240329_72c01e663e.jpg"
img_PIL = Image.open(image_path)
img_array = np.array(img_PIL)
img_PIL1 = Image.open(image_path1)
img_array1 = np.array(img_PIL1)
writer.add_image("image", img_array, 1, dataformats='HWC') # 这个通道顺序需要改，tensorboard默认使用的是tensor结构，但这个读的是PIL结构
writer.add_image("image", img_array1, 2, dataformats='HWC')
# add_scalar使用
# for i in range(100):
# writer.add_scalar("y=2x", 2*i, i)
writer.close()
transforms使用
transforms是用来进行数据类型的转换，pytorch中使用的数据格式大多是Tensor，transfroms直接提供了工具
transforms_learn.py
# function：展示transforms的基本使用格式
from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
import numpy as np
writer = SummaryWriter("logs")
# python用法 → tensor数据类型
# 通过transform.ToTensor看两个问题
# 1. transform如何使用
# 2. 为什么需要Tensor
image_path = "dataset/train/ants/522163566_fec115ca66.jpg"
# PIL → Tensor()
img = Image.open(image_path)
tensor_trans = transforms.ToTensor()
tensor_img = tensor_trans(img)
writer.add_image("image", tensor_img, 1)
writer.close()
useful_transforms.py
有几个常见的transforms，可以记一下使用方法：ToTensor(转换为Tensor类型)，Normalize(做正则化)，Resize(调整数据shape)，Compose(将多个transfroms整合在一起)，RandomCrop(随机裁剪数据)，使用方式如下：
# function：展示部分常见transfroms，包括：ToTensor(转换为Tensor类型)，Normalize(做正则化)，Resize(调整数据shape)，Compose(将多个transfroms整合在一起)，RandomCrop(随机裁剪数据)
from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
writer = SummaryWriter("logs")
img = Image.open("dataset/train/ants/5650366_e22b7e1065.jpg")
# ToTensor
trans_totensor = transforms.ToTensor()
img_tensor = trans_totensor(img)
# Normalize
trans_norm = transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
img_norm = trans_norm(img_tensor)
# Resize
# 输入序列(512, 512)或者数值(512, 会生成方阵)
trans_resize = transforms.Resize((512, 512))
img_resize = trans_resize(img)
img_resize = trans_totensor(img_resize)
# Compose
# PIL → PIL → tensor
trans_resize_2 = transforms.Resize(512)
trans_compose = transforms.Compose([trans_resize_2, trans_totensor])
img_resize_2 = trans_compose(img)
# RandomCrop——随机裁剪
trans_ramdom = transforms.RandomCrop(128)
trans_compose_2 = transforms.Compose([trans_ramdom, trans_totensor])
for i in range(10):
img_crop = trans_compose_2(img)
writer.add_image("RandomCrop", img_crop, i)
writer.add_image("ToTensor", img_tensor, 1)
writer.add_image("Norm", img_norm, 2)
writer.add_image("Resize", img_resize, 3)
writer.add_image("Compose", img_resize_2, 4)
writer.close()
dataset_transforms.py
这个主要开始使用dataLoader进行数据提取了，因为图片数据直接是PIL类型，所以在dataloader的时候就要进行transforms，使用方式如下：
import torchvision
from torch.utils.tensorboard import SummaryWriter
from torch.utils.data import DataLoader
# # ====torchvision.datasets使用====
# dataset_transform = torchvision.transforms.Compose([torchvision.transforms.ToTensor()])
# train_set = torchvision.datasets.CIFAR10(root="./dataset", train=True, transform=dataset_transform, download=True)
# test_set = torchvision.datasets.CIFAR10(root="./dataset", train=False, transform=dataset_transform, download=True)
#
# writer = SummaryWriter("dataset_transformer")
# for i in range(10):
# img, target = train_set[i]
# writer.add_image("test_set", img, i)
# writer.close()
# # ====torchvision.DataLoader使用====
test_data = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.Compose([torchvision.transforms.ToTensor()]))
test_loader = DataLoader(dataset=test_data, batch_size=64, shuffle=True, num_workers=0, drop_last=True)
img, target = test_data[0]
print(img.shape)
print(target)
step = 0
writer = SummaryWriter("dataloader")
for data in test_loader:
imgs, targets = data
writer.add_images("dataloader", imgs, step) # 注意：批量添加的时候使用add_images函数
step = step + 1
writer.close()
torch.nn使用
torch.nn是pytorch对于神经网络(neural network)提供的有关操作支持，具体的东西有很多，只讲解了一部分常用的
conv2d
卷积操作的实现(具体啥是卷积，视频里解释的很详细)，我在这里就留个模板了：
nn_conv2d.py
# torch.nn 的卷积conv2d 实例
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 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()
step = 0
writter = SummaryWriter("logs_conv2d")
for data in dataLoader:
imgs, targets = data
output = tudui(imgs)
writter.add_images("input", imgs, step)
output = torch.reshape(output, [-1, 3, 30, 30])
writter.add_images("output", output, step)
step = step + 1
nn.module基本使用
上面的Tudui类继承了nn.module，其实这个是整体pytorch关于神经网络的父类，使用时继承就好了，留一个简单的模板：
nn_module.py
# function：nn.module的基本使用
import torch
from torch import nn
class Tudui(nn.Module):
# 注意父类写的格式
def __init__(self):
super().__init__()
def forward(self, input):
output = input + 1
return output
tudui = Tudui()
x = torch.tensor(1.0)
output = tudui(x)
print(output)
maxpool.py
最大池化的实现：
# function：torch.nn 最大池化maxpool示例
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", download=True, 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, 5, 1, 1],
[2, 1, 0, 1, 2]
], dtype=torch.float32)
input = torch.reshape(input, (-1, 1, 5, 5))
print(input.shape)
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
# ceil_mode为True，保留边框部分(多)
# ceil_mode为False，不保留边框部分(少)
self.maxpool = MaxPool2d(kernel_size=3, ceil_mode=False)
def forward(self, input):
output = self.maxpool(input)
return output
writer = SummaryWriter("log_maxpool")
tudui = Tudui()
output = tudui(input)
step = 0
for data in dataLoader:
imgs, targets = data
writer.add_images("intput", imgs, step)
output = tudui(imgs)
writer.add_images("output", output, step)
step = step + 1
writer.close()
linear.py
线性化的实现：
import torch
import torchvision
from torch import nn
from torch.nn import Linear
from torch.utils.data import DataLoader
dataset = torchvision.datasets.CIFAR10("./dataset", download=True, train=False, transform=torchvision.transforms.ToTensor())
dataLoader = DataLoader(dataset, batch_size=64)
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.Linear = Linear(196608, 10)
def forward(self, input):
output = self.Linear(input)
return output
tudui = Tudui()
for data in dataLoader:
imgs, targets = data
print(imgs.shape)
output = torch.flatten(imgs)
print(output.shape)
output = tudui(output)
print(output.shape)
loss
loss是损失函数，pytorch中提供了几种可以直接使用的，我在这里直接举例了：
nn_loss.py
# function：损失函数使用示例
import torch
from torch.nn import L1Loss
from torch import nn
inputs = torch.tensor([1, 2, 3], dtype=torch.float32)
targets = torch.tensor([1, 2, 5], dtype=torch.float32)
inputs = torch.reshape(inputs, (1, 1, 1, 3))
targets = torch.reshape(targets, (1, 1, 1, 3))
# L1直接损失
loss = L1Loss()
result = loss(inputs, targets)
# 均方差损失
loss_mse = nn.MSELoss()
result_mes = loss_mse(inputs, targets)
x = 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)
print(result_mes)
print(result_cross)
optimal
优化器的使用，有个模板：
optim.zero_grad() # 1.设置梯度为0
result_loss.backward() # 2.计算梯度，进行反向传播
optim.step() # 3.进行梯度更新，调整权重参数(降低loss)
示例如下：
nn_optimal.py
import torch
import torchvision
from torch import nn
from torch.nn import Conv2d, Linear, Sequential
from torch.nn import MaxPool2d
from torch.nn import Flatten
from torch.utils.data import DataLoader, dataloader
from nn_loss import loss
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.model = 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, input):
x = self.model(input)
return x
dataset = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(), download=True)
dataLoader = DataLoader(dataset, batch_size=1)
loss = nn.CrossEntropyLoss()
tudui = Tudui()
optim = torch.optim.SGD(tudui.parameters(), lr=0.01)
for epoch in range(20):
running_loss = 0.0
for data in dataLoader:
imgs, targets = data
outputs = tudui(imgs)
result_loss = loss(outputs, targets)
optim.zero_grad() # 1.设置梯度为0
result_loss.backward() # 2.计算梯度，进行反向传播
optim.step() # 3.进行梯度更新，调整权重参数(降低loss)
running_loss = running_loss + result_loss
print(running_loss)
relu.py
引入非线性(线性的表彰不好)，示例如下：
import torch
import torchvision
from torch import nn
from torch.nn import ReLU
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)
dataset = torchvision.datasets.CIFAR10("./dataset", download=True, train=False, transform=torchvision.transforms.ToTensor())
dataLoader = DataLoader(dataset, batch_size=64)
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.relu = ReLU()
def forward(self, input):
output = self.relu(input)
return output
writer = SummaryWriter("logs_relu")
tudui = Tudui()
output = tudui(input)
step = 0
for data in dataLoader:
imgs, targets = data
writer.add_images("input", imgs, step)
output = tudui(imgs)
writer.add_images("output", output, step)
step = step + 1
writer.close()
print(output)
sequential.py
传统方式写模型，要在forward中一层一层写 结构。使用sequential可以直接在model中进行定义，示例如下：
## 传统方式：自己写模型
# import torch
# from torch import nn
# from torch.nn import Conv2d, Linear, Sequential
# from torch.nn import MaxPool2d
# from torch.nn import Flatten
#
# class Tudui(nn.Module):
# def __init__(self):
# super(Tudui, self).__init__()
# self.conv1 = Conv2d(3, 32, 5, padding=2)
# self.maxpool1 = MaxPool2d(2)
# self.conv2 = Conv2d(32, 32, 5, padding=2)
# self.maxpool2 = MaxPool2d(2)
# self.conv3 = Conv2d(32, 64, 5, padding=2)
# self.maxpool3 = MaxPool2d(2)
# self.flatten = Flatten()
# self.linear1 = Linear(1024, 64)
# self.linear2 = Linear(64, 10)
#
# def forward(self, input):
# x = self.conv1(input)
# x = self.maxpool1(x)
# x = self.conv2(x)
# x = self.maxpool2(x)
# x = self.conv3(x)
# x = self.maxpool3(x)
# x = self.flatten(x)
# x = self.linear1(x)
# x = self.linear2(x)
# return x
#
# tudui = Tudui()
# input = torch.ones((64, 3, 32, 32))
# output = tudui(input)
# print(output.shape)
## 使用Sequential写模型
import torch
from torch import nn
from torch.nn import Conv2d, Linear, Sequential
from torch.nn import MaxPool2d
from torch.nn import Flatten
from torch.utils.tensorboard import SummaryWriter
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.model = 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, input):
x = self.model(input)
return x
writer = SummaryWriter("logs_sequential")
tudui = Tudui()
input = torch.ones((64, 3, 32, 32))
output = tudui(input)
writer.add_graph(tudui, input)
writer.close()
print(output.shape)
整体模型训练
train_cpu.py
示例如下：
import torchvision
from torch.utils.data import DataLoader
import torch
from torch import nn
from torch.utils.tensorboard import SummaryWriter
train_data = torchvision.datasets.CIFAR10("./dataset", train=True, download=True, transform=torchvision.transforms.ToTensor())
test_data = torchvision.datasets.CIFAR10("./dataset", train=False, download=True, transform=torchvision.transforms.ToTensor())
# length
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集长度为：{}".format(train_data_size))
print("测试数据集长度为：{}".format(test_data_size))
# 利用dataloader来加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
# 搭建神经网络
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.model = nn.Sequential(
nn.Conv2d(3, 32, 5, 1, 2),
nn.MaxPool2d(2),
nn.Conv2d(32, 32, 5, 1, 2),
nn.MaxPool2d(2),
nn.Conv2d(32, 64, 5, 1, 2),
nn.MaxPool2d(2),
nn.Flatten(),
nn.Linear(64*4*4, 64),
nn.Linear(64, 10))
def forward(self, input):
x = self.model(input)
return x
### 测试模型正确性
# if __name__ == '__main__':
# tudui = Tudui()
# input = torch.ones((64, 3, 32, 32))
# output = tudui(input)
# print(output.shape)
# 创建网络模型
tudui = Tudui()
# 损失函数
loss_fn = nn.CrossEntropyLoss()
# 优化器
learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.parameters(), lr=learning_rate)
# 设置训练网络的一些参数
total_train_step = 0
total_test_step = 0
# 训练轮数
epoch = 10
# 添加tensorboard
writter = SummaryWriter("logs_train")
total_test_step = 0
for i in range(10):
print("-----第{}轮训练开始----".format(i+1))
# 训练步骤开始
tudui.train() #特定层：Dropout
for data in train_dataloader:
# 1. 数据导入
imgs, targets = data
# 2. 模型导入
outputs = tudui(imgs)
# 3. loss计算
loss = loss_fn(outputs, targets)
# 4. 优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_step = total_train_step + 1
if total_train_step % 100 == 0:
print("训练次数：{}, loss:{}".format(total_train_step, loss.item())) #loss.item()相当于取值
writter.add_scalar("train_loss", loss.item(), total_train_step)
# 测试步骤开始
tudui.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
outputs = tudui(imgs)
loss = loss_fn(outputs, targets)
total_test_loss = total_test_loss + loss.item()
accuracy = (outputs.argmax(1) == targets).sum()
total_accuracy = total_accuracy + accuracy
print("整体测试集上的loss:{}".format(total_test_loss))
print("整体测试集上的正确率：{}".format(total_accuracy/test_data_size))
writter.add_scalar("test_loss", loss.item(), total_test_step)
writter.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
total_test_step = total_test_step + 1
# 保存训练模型
torch.save(tudui, "tudui_{}.pth".format(i))
print("模型已保存！")
writter.close()
train_gpu.py
示例如下：
# 与CPU的区别：在网络模型、数据、损失函数上增加cuda()
import torchvision
from torch.utils.data import DataLoader
import torch
from torch import nn
from torch.utils.tensorboard import SummaryWriter
train_data = torchvision.datasets.CIFAR10("./dataset", train=True, download=True, transform=torchvision.transforms.ToTensor())
test_data = torchvision.datasets.CIFAR10("./dataset", train=False, download=True, transform=torchvision.transforms.ToTensor())
# length
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集长度为：{}".format(train_data_size))
print("测试数据集长度为：{}".format(test_data_size))
# 利用dataloader来加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
# 搭建神经网络
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.model = nn.Sequential(
nn.Conv2d(3, 32, 5, 1, 2),
nn.MaxPool2d(2),
nn.Conv2d(32, 32, 5, 1, 2),
nn.MaxPool2d(2),
nn.Conv2d(32, 64, 5, 1, 2),
nn.MaxPool2d(2),
nn.Flatten(),
nn.Linear(64*4*4, 64),
nn.Linear(64, 10))
def forward(self, input):
x = self.model(input)
return x
### 测试模型正确性
# if __name__ == '__main__':
# tudui = Tudui()
# input = torch.ones((64, 3, 32, 32))
# output = tudui(input)
# print(output.shape)
# 创建网络模型
tudui = Tudui()
tudui = Tudui().cuda()
# 损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.cuda()
# 优化器
learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.parameters(), lr=learning_rate)
# 设置训练网络的一些参数
total_train_step = 0
total_test_step = 0
# 训练轮数
epoch = 10
# 添加tensorboard
writter = SummaryWriter("logs_train")
total_test_step = 0
for i in range(10):
print("-----第{}轮训练开始----".format(i+1))
# 训练步骤开始
tudui.train() #特定层：Dropout
for data in train_dataloader:
# 1. 数据导入
imgs, targets = data
imgs = imgs.cuda()
targets = targets.cuda()
# 2. 模型导入
outputs = tudui(imgs)
# 3. loss计算
loss = loss_fn(outputs, targets)
# 4. 优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_step = total_train_step + 1
if total_train_step % 100 == 0:
print("训练次数：{}, loss:{}".format(total_train_step, loss.item())) #loss.item()相当于取值
writter.add_scalar("train_loss", loss.item(), total_train_step)
# 测试步骤开始
tudui.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
imgs = imgs.cuda()
targets = targets.cuda()
outputs = tudui(imgs)
loss = loss_fn(outputs, targets)
total_test_loss = total_test_loss + loss.item()
accuracy = (outputs.argmax(1) == targets).sum()
total_accuracy = total_accuracy + accuracy
print("整体测试集上的loss:{}".format(total_test_loss))
print("整体测试集上的正确率：{}".format(total_accuracy/test_data_size))
writter.add_scalar("test_loss", loss.item(), total_test_step)
writter.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
total_test_step = total_test_step + 1
# 保存训练模型
torch.save(tudui, "tudui_{}.pth".format(i))
print("模型已保存！")
writter.close()
模型保存
model_save.py
示例如下：
# function：训练模型的保存
import torch
import torchvision
vgg16 = torchvision.models.vgg16(pretrained=False)
# 保存方式1
torch.save(vgg16, "vgg16_method1.pth")
# 保存方式2(官方推荐)
torch.save(vgg16.state_dict(), "vgg16_method2.pth")
模型加载
model_loader
示例如下：
# function：现有模型加载
import torch
import torchvision
model = torch.load("vgg16_method1.pth")
print(model)
vgg16 = torchvision.models.vgg16(pretrained=False)
vgg16.load_state_dict(torch.load("vgg16_method2.pth"))
# model = torch.load("vgg16_method2.pth") # 直接是字典权重
print(model)
模型使用
model_use.py
示例如下：
# function：自找图片，验证train.py训练的模型准确性
import torch
import torchvision
from PIL import Image
from torch import nn
image_path = "dog.png"
image = Image.open(image_path)
transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32, 32)), torchvision.transforms.ToTensor()])
image = transform(image)
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.model = nn.Sequential(
nn.Conv2d(3, 32, 5, 1, 2),
nn.MaxPool2d(2),
nn.Conv2d(32, 32, 5, 1, 2),
nn.MaxPool2d(2),
nn.Conv2d(32, 64, 5, 1, 2),
nn.MaxPool2d(2),
nn.Flatten(),
nn.Linear(64*4*4, 64),
nn.Linear(64, 10))
def forward(self, input):
x = self.model(input)
return x
model = torch.load("tudui_9.pth")
image = torch.reshape(image, (1, 3, 32, 32))
image = image.cuda()
model.eval()
with torch.no_grad():
output = model(image)
print(output.argmax(1))
预模型使用
premodel_use.py
示例如下：
# function：使用现有网络对现有数据集进行训练
import torchvision
from torch import nn
vgg16_false = torchvision.models.vgg16(pretrained=False)
vgg16_true = torchvision.models.vgg16(pretrained=True)
print(vgg16_true)
train_data = torchvision.datasets.CIFAR10("./dataset", train=True, download=True, transform=torchvision.transforms.ToTensor())
# CIFAR10最终的输出结果是10类，所以必须按照原来的增加一层
vgg16_true.classifier.add_module('add_linear', nn.Linear(1000, 10))
print(vgg16_true)
# CIFAR10最终的输出结果是10类，也可以在原来基础上做改动
vgg16_false.classifier[6] = nn.Linear(4096, 10)
print(vgg16_false)
以上简单的了解了下pytorch的基础，学习仍在继续，继续加油~
