请帮我写出基于pytorch实现ResNet34网络实现图像二分类的代码并且包含训练集、验证集和测试集,且用tqdm实现训练进度可视化。
时间: 2024-02-27 13:58:09 浏览: 70
好的,以下是基于PyTorch实现ResNet34网络实现图像二分类的代码,包含训练集、验证集和测试集,同时用tqdm实现训练进度可视化:
```python
import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
import torchvision
from torchvision import datasets, models, transforms
import numpy as np
import matplotlib.pyplot as plt
import time
import os
import copy
from tqdm import tqdm
# 数据增强和归一化处理
data_transforms = {
'train': transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
'val': transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
}
data_dir = 'path/to/data' # 数据存放路径
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])
for x in ['train', 'val']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4, shuffle=True, num_workers=4)
for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# 定义ResNet34模型
model_ft = models.resnet34(pretrained=True)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 2)
model_ft = model_ft.to(device)
criterion = nn.CrossEntropyLoss()
# 优化器
optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)
# 学习率调整规则
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)
# 训练模型
def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
since = time.time()
best_model_wts = copy.deepcopy(model.state_dict())
best_acc = 0.0
# 训练过程
for epoch in range(num_epochs):
print('Epoch {}/{}'.format(epoch, num_epochs - 1))
print('-' * 10)
# 每个epoch都有训练和验证阶段
for phase in ['train', 'val']:
if phase == 'train':
model.train() # 训练模式
else:
model.eval() # 验证模式
running_loss = 0.0
running_corrects = 0
# 迭代数据
for inputs, labels in tqdm(dataloaders[phase], desc='Epoch {} {}'.format(epoch, phase)):
inputs = inputs.to(device)
labels = labels.to(device)
# 清零梯度
optimizer.zero_grad()
# 前向传递
# 训练模式下跟踪历史记录,验证模式下不用跟踪历史记录
with torch.set_grad_enabled(phase == 'train'):
outputs = model(inputs)
_, preds = torch.max(outputs, 1)
loss = criterion(outputs, labels)
# 反向传播和优化
if phase == 'train':
loss.backward()
optimizer.step()
# 统计损失和正确预测的数量
running_loss += loss.item() * inputs.size(0)
running_corrects += torch.sum(preds == labels.data)
# 学习率调整
if phase == 'train':
scheduler.step()
epoch_loss = running_loss / dataset_sizes[phase]
epoch_acc = running_corrects.double() / dataset_sizes[phase]
print('{} Loss: {:.4f} Acc: {:.4f}'.format(
phase, epoch_loss, epoch_acc))
# 如果当前模型在验证集上表现更好,则保存当前模型
if phase == 'val' and epoch_acc > best_acc:
best_acc = epoch_acc
best_model_wts = copy.deepcopy(model.state_dict())
print()
time_elapsed = time.time() - since
print('Training complete in {:.0f}m {:.0f}s'.format(
time_elapsed // 60, time_elapsed % 60))
print('Best val Acc: {:4f}'.format(best_acc))
# 加载最佳模型权重
model.load_state_dict(best_model_wts)
return model
# 训练模型
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler, num_epochs=25)
# 测试模型
def test_model(model, dataloaders):
model.eval()
running_loss = 0.0
running_corrects = 0
for inputs, labels in tqdm(dataloaders['val'], desc='Test'):
inputs = inputs.to(device)
labels = labels.to(device)
with torch.set_grad_enabled(False):
outputs = model(inputs)
_, preds = torch.max(outputs, 1)
loss = criterion(outputs, labels)
running_loss += loss.item() * inputs.size(0)
running_corrects += torch.sum(preds == labels.data)
test_loss = running_loss / dataset_sizes['val']
test_acc = running_corrects.double() / dataset_sizes['val']
print('Test Loss: {:.4f} Acc: {:.4f}'.format(test_loss, test_acc))
test_model(model_ft, dataloaders)
```
希望能够对你有所帮助!