Pytorch 加载部分预训练模型并冻结某些层

1 pytorch的版本：

2 数据下载地址：

3 原始版本代码下载：

4 直接上代码：

1 pytorch的版本：

2 数据下载地址：

<https://download.pytorch.org/tutorial/hymenoptera_data.zip>

3 原始版本代码下载：

https://pytorch.org/tutorials/_downloads/transfer_learning_tutorial.py

4 直接上代码：

# -*- coding: utf-8 -*-
# @File    : test4.py
# @Blog    : https://blog.csdn.net/caomin1haofrom __future__ import print_function, divisionimport torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copydevice = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")plt.ion()   # interactive mode######################################################################
# 1.定义模型，  2.加载部分预训练数据，  3.冻结部分层
######################################
#1.定义模型
model_conv = models.resnet18()
num_ftrs = model_conv.fc.in_features
model_conv.fc = nn.Linear(num_ftrs, 2)'''
#打印模型的结构
print('###打印模型model_conv的结构####')
print(model_conv)
print('\n')print('###打印模型model_conv加载参数前的初始值####')
print(list(model_conv.parameters()))
print('\n')
'''#############################################
#2.加载部分预训练数据
pretrained_dict = torch.load('./08 transfer_learning/resnet18-5c106cde.pth')
'''
for k,v in pretrained_dict.items():print(k)
'''
#删除预训练模型跟当前模型层名称相同，层结构却不同的元素;这里有两个'fc.weight'、'fc.bias'
pretrained_dict.pop('fc.weight')
pretrained_dict.pop('fc.bias')#自己的模型参数变量
model_dict = model_conv.state_dict()
#去除一些不需要的参数
pretrained_dict = {k: v for k, v in pretrained_dict.items() if k in model_dict}#参数更新
model_dict.update(pretrained_dict)# 加载我们真正需要的state_dict
model_conv.load_state_dict(model_dict)'''
print('###打印模型model_conv加载参数后的参数值####')
print(list(model_conv.parameters()))
print('\n')
'''
#############################################
#3.冻结部分层
#将满足条件的参数的 requires_grad 属性设置为False
for name, value in model_conv.named_parameters():if (name != 'fc.weight') and (name != 'fc.bias'):value.requires_grad = False
'''
#打印各层的requires_grad属性
print('###打印模型model_conv参数的requires_grad属性####')
for name, param in model_conv.named_parameters():print(name,param.requires_grad)
'''# filter 函数将模型中属性 requires_grad = True 的参数选出来
params_conv = filter(lambda p: p.requires_grad, model_conv.parameters())
model_conv = model_conv.to(device)criterion = nn.CrossEntropyLoss()# Observe that only parameters of final layer are being optimized as
# opoosed to before.
optimizer_conv = optim.SGD(params_conv, lr=0.001, momentum=0.9)# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)######################################################################
# Training the model
#编写一个通用函数来训练模型。
# 下面将说明： * 调整学习速率 * 保存最好的模型
#下面的参数scheduler是一个来自 torch.optim.lr_scheduler 的学习速率调整类的对象(LR scheduler object)。def train_model(model, criterion, optimizer, scheduler, num_epochs=25):since = time.time()best_model_wts = copy.deepcopy(model.state_dict())best_acc = 0.0for epoch in range(num_epochs):print('Epoch {}/{}'.format(epoch, num_epochs - 1))print('-' * 10)# 每个epoch都有一个训练和验证阶段for phase in ['train', 'val']:if phase == 'train':scheduler.step()model.train()  # Set model to training modeelse:model.eval()   # Set model to evaluate moderunning_loss = 0.0running_corrects = 0#  迭代数据.for inputs, labels in dataloaders[phase]:inputs = inputs.to(device)labels = labels.to(device)# zero the parameter gradientsoptimizer.zero_grad()# forward# track history if only in trainwith torch.set_grad_enabled(phase == 'train'):outputs = model(inputs)_, preds = torch.max(outputs, 1)loss = criterion(outputs, labels)# 后向+仅在训练阶段进行优化if phase == 'train':loss.backward()optimizer.step()# statisticsrunning_loss += loss.item() * inputs.size(0)running_corrects += torch.sum(preds == labels.data)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))# 深度复制moif phase == 'val' and epoch_acc > best_acc:best_acc = epoch_accbest_model_wts = copy.deepcopy(model.state_dict())print()time_elapsed = time.time() - sinceprint('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######################################################################
# 可视化部分训练图像，以便了解数据扩充。def imshow(inp, title=None):"""Imshow for Tensor."""inp = inp.numpy().transpose((1, 2, 0))mean = np.array([0.485, 0.456, 0.406])std = np.array([0.229, 0.224, 0.225])inp = std * inp + meaninp = np.clip(inp, 0, 1)plt.imshow(inp)if title is not None:plt.title(title)plt.pause(0.001)  # pause a bit so that plots are updated######################################################################
# Visualizing the model predictions
# 一个通用的展示少量预测图片的函数def visualize_model(model, num_images=6):was_training = model.trainingmodel.eval()images_so_far = 0fig = plt.figure()with torch.no_grad():for i, (inputs, labels) in enumerate(dataloaders['val']):inputs = inputs.to(device)labels = labels.to(device)outputs = model(inputs)_, preds = torch.max(outputs, 1)for j in range(inputs.size()[0]):images_so_far += 1ax = plt.subplot(num_images//2, 2, images_so_far)ax.axis('off')ax.set_title('predicted: {}'.format(class_names[preds[j]]))imshow(inputs.cpu().data[j])if images_so_far == num_images:model.train(mode=was_training)returnmodel.train(mode=was_training)######################################################################
#训练集数据扩充和归一化
#在验证集上仅需要归一化
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 = './08 transfer_learning/hymenoptera_data'
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'].classesdevice = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")if __name__ == '__main__':# Train and evaluate 2# 训练模型 在CPU上，与前一个场景相比，这将花费大约一半的时间，因为不需要为大多数网络计算梯度。但需要计算转发。model_conv = train_model(model_conv, criterion, optimizer_conv,exp_lr_scheduler, num_epochs=11)visualize_model(model_conv)plt.ioff()plt.show()

部分运行结果：