这部分分为一个一个模块,最后归纳出了一个完整的模型训练套路,部分重要代码整理如下:
model.py
import torch
from torch import nn
# 搭建神经网络
class Network(nn.Module):
def __init__(self):
super().__init__()
self.model = 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, 1, 2),
nn.MaxPool2d(2),
nn.Flatten(),
nn.Linear(64*4*4, 64),
nn.Linear(64, 10)
)
def forward(self, x):
x = self.model(x)
return x
if __name__ == '__main__':
network = Network()
input = torch.ones((64, 3, 32, 32))
output = network(input)
print(output.shape)
train.py
import torchvision.datasets
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import time
from model import *
# 准备数据集
train_data = torchvision.datasets.CIFAR10("./dataset", train=True, transform=torchvision.transforms.ToTensor(),
download=True)
test_data = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(),
download=True)
# length
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为: {}".format(train_data_size))
print(f"测试数据集的长度为: {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)
# 创建网络模型
network = Network()
# 损失函数
loss_fn = nn.CrossEntropyLoss()
# 优化器
# learning_rate = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(network.parameters(), lr=learning_rate)
# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 10
# 添加tensorboard
writer = SummaryWriter("logs_train")
start_time = time.time()
for i in range(epoch):
print("-----------第 {} 轮训练开始----------".format(i+1))
# 训练步骤开始
network.train()
for data in train_dataloader:
imgs, targets = data
outputs = network(imgs)
loss = loss_fn(outputs, targets)
# 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:
end_time = time.time()
print(end_time - start_time)
print("训练次数: {}, loss: {}".format(total_train_step, loss.item()))
writer.add_scalar("train_loss", loss.item(), total_train_step)
# 测试步骤开始
network.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
outputs = network(imgs)
loss = loss_fn(outputs, targets)
total_test_loss = total_test_loss + loss
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))
writer.add_scalar("test_loss", total_test_loss, total_test_step)
writer.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
total_test_step = total_test_step + 1
torch.save(network, "network_{}.pth".format(i))
print("模型已保存")
writer.close()
train_gpu_1.py
import torchvision.datasets
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import time
from model import *
# 准备数据集
train_data = torchvision.datasets.CIFAR10("./dataset", train=True, transform=torchvision.transforms.ToTensor(),
download=True)
test_data = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(),
download=True)
# length
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为: {}".format(train_data_size))
print(f"测试数据集的长度为: {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)
# 创建网络模型
network = Network()
# 损失函数
loss_fn = nn.CrossEntropyLoss()
# 优化器
# learning_rate = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(network.parameters(), lr=learning_rate)
# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 10
# 添加tensorboard
writer = SummaryWriter("logs_train")
start_time = time.time()
for i in range(epoch):
print("-----------第 {} 轮训练开始----------".format(i+1))
# 训练步骤开始
network.train()
for data in train_dataloader:
imgs, targets = data
outputs = network(imgs)
loss = loss_fn(outputs, targets)
# 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:
end_time = time.time()
print(end_time - start_time)
print("训练次数: {}, loss: {}".format(total_train_step, loss.item()))
writer.add_scalar("train_loss", loss.item(), total_train_step)
# 测试步骤开始
network.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
outputs = network(imgs)
loss = loss_fn(outputs, targets)
total_test_loss = total_test_loss + loss
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))
writer.add_scalar("test_loss", total_test_loss, total_test_step)
writer.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
total_test_step = total_test_step + 1
torch.save(network, "network_{}.pth".format(i))
print("模型已保存")
writer.close()
train_gpu_2.py
import torchvision.datasets
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import time
from model import *
# 准备数据集
train_data = torchvision.datasets.CIFAR10("./dataset", train=True, transform=torchvision.transforms.ToTensor(),
download=True)
test_data = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(),
download=True)
# length
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为: {}".format(train_data_size))
print(f"测试数据集的长度为: {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)
# 创建网络模型
network = Network()
# 损失函数
loss_fn = nn.CrossEntropyLoss()
# 优化器
# learning_rate = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(network.parameters(), lr=learning_rate)
# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 10
# 添加tensorboard
writer = SummaryWriter("logs_train")
start_time = time.time()
for i in range(epoch):
print("-----------第 {} 轮训练开始----------".format(i+1))
# 训练步骤开始
network.train()
for data in train_dataloader:
imgs, targets = data
outputs = network(imgs)
loss = loss_fn(outputs, targets)
# 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:
end_time = time.time()
print(end_time - start_time)
print("训练次数: {}, loss: {}".format(total_train_step, loss.item()))
writer.add_scalar("train_loss", loss.item(), total_train_step)
# 测试步骤开始
network.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
outputs = network(imgs)
loss = loss_fn(outputs, targets)
total_test_loss = total_test_loss + loss
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))
writer.add_scalar("test_loss", total_test_loss, total_test_step)
writer.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
total_test_step = total_test_step + 1
torch.save(network, "network_{}.pth".format(i))
print("模型已保存")
writer.close()
model_load.py
import torch
import torchvision.models
from torch import nn
from model_save import *
# 方式1-》保存方式1,加载模型
# model = torch.load("vgg16_method1.pth")
# print(model)
# 方式2-》加载模型
vgg16 = torchvision.models.vgg16(weights=None)
vgg16.load_state_dict(torch.load("vgg16_method2.pth"))
# model = torch.load("vgg16_method2.pth")
# print(vgg16)
# 陷阱1
class Network(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(3, 64, 3)
def forward(self, x):
return x
model = torch.load("network_method1.pth")
print(model)
model_save.py
import torch
import torchvision.models
from torch import nn
vgg16 = torchvision.models.vgg16(weights=None)
# 保存方式1.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")
# 陷阱1
class Network(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(3, 64, 3)
def forward(self, x):
return x
network = Network()
torch.save(network, "network_method1.pth")
model_pretraining.py
import torchvision.datasets
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', transform=torchvision.transforms.ToTensor(),
train=True, download=True)
vgg16_true.classifier.add_module('add_linear', nn.Linear(1000, 10))
print(vgg16_true)
print(vgg16_false)
vgg16_false.classifier[6] = nn.Linear(4096, 10)
print(vgg16_false)
test.py
import torch
import torchvision.transforms
from PIL import Image
from torch import nn
img_path = "dog.png"
image = Image.open(img_path)
print(image)
transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32, 32)),
torchvision.transforms.ToTensor()])
image = transform(image)
print(image.shape)
# 搭建神经网络
class Network(nn.Module):
def __init__(self):
super().__init__()
self.model = 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, 1, 2),
nn.MaxPool2d(2),
nn.Flatten(),
nn.Linear(64*4*4, 64),
nn.Linear(64, 10)
)
def forward(self, x):
x = self.model(x)
return x
model = torch.load("network_29.pth", map_location=torch.device('cpu'))
print(model)
image = torch.reshape(image, (1, 3, 32, 32))
model.eval()
with torch.no_grad():
output = model(image)
print(output)
print(output.argmax(1))
本文参考小土堆教程视频。