Pytorch之模型微调（Finetune）——手写数字集为例
文章目录
前言
模型微调在迁移学习中（Transfer Learning）中是非常常用技术，接下来我将以用ResNet18来对手写数字集进行分类为例，讲述如何使用pytorch进行模型微调。
一、Transfer Learning and Model Finetune
1.Transform Learning（迁移学习）
Transform Learning：迁移学习机器学习的分支，研究源域（source domain）知识如何应用到目标域（target domain）。我们首先在一个基础数据集和基础任务上训练一个基础网络，然后我们再微调一下学到的特征，或者说将它们迁移到第二个目标网络中，用目标数据集和目标任务训练网络。如果特征是泛化的，那么这个过程会奏效，也就是说，这些特征对基础任务和目标任务都是适用的，而不是特定的适用于某个基础任务。
简单来说：就是就是把已学训练好的模型参数迁移到新的模型来帮助新模型训练。
2.Model Finetune（模型微调）
Model Finetune：一种模型的迁移学习
二、Pytorch中的Finetune
1.模型微调的步骤
1.获取预训练模型参数
2.加载模型（load_state_dict）
3.修改输出层
2.模型微调训练方法
1.固定预训练的参数（requires_grad = False; lr = 0）
2.Feature Extractor 较小的学习率（params_group）
3.Pytorch——基于Resnet18蚂蚁蜜蜂二分类源码
import os
import numpy as np
import torch
import torch.nn as nn
from torch.utils.data import DataLoader
import torchvision.transforms as transforms
import torch.optim as optim
from matplotlib import pyplot as plt
from tools.my_dataset import AntsDataset
from tools.common_tools import set_seed
import torchvision.models as models
import torchvision
BASEDIR = os.path.dirname(os.path.abspath(__file__))
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print("use device :{}".format(device))
set_seed(1) # 设置随机种子
label_name = {
"ants": 0, "bees": 1}
# 参数设置
MAX_EPOCH = 25
BATCH_SIZE = 16
LR = 0.001
log_interval = 10
val_interval = 1
classes = 2
start_epoch = -1
lr_decay_step = 7
# ============================ step 1/5 数据 ============================
data_dir = os.path.join(BASEDIR,"hymenoptera_data")
train_dir = os.path.join(data_dir, "train")
valid_dir = os.path.join(data_dir, "val")
norm_mean = [0.485, 0.456, 0.406]
norm_std = [0.229, 0.224, 0.225]
train_transform = transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(norm_mean, norm_std),
])
valid_transform = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(norm_mean, norm_std),
])
# 构建MyDataset实例
train_data = AntsDataset(data_dir=train_dir, transform=train_transform)
valid_data = AntsDataset(data_dir=valid_dir, transform=valid_transform)
# 构建DataLoder
train_loader = DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
valid_loader = DataLoader(dataset=valid_data, batch_size=BATCH_SIZE)
# ============================ step 2/5 模型 ============================
# 1/3 构建模型
resnet18_ft = models.resnet18()
# 2/3 加载参数
# flag = 0
flag = 1
if flag:
path_pretrained_model = os.path.join(BASEDIR, "finetune_resnet18-5c106cde.pth")
state_dict_load = torch.load(path_pretrained_model)
resnet18_ft.load_state_dict(state_dict_load)
# 法1 : 冻结卷积层
flag_m1 = 0
# flag_m1 = 1
if flag_m1:
for param in resnet18_ft.parameters():
param.requires_grad = False
print("conv1.weights[0, 0, ...]:\n {}".format(resnet18_ft.conv1.weight[0, 0, ...]))
# 3/3 替换fc层
num_ftrs = resnet18_ft.fc.in_features
resnet18_ft.fc = nn.Linear(num_ftrs, classes)
resnet18_ft.to(device)
# ============================ step 3/5 损失函数 ============================
criterion = nn.CrossEntropyLoss() # 选择损失函数
# ============================ step 4/5 优化器 ============================
# 法2 : conv 小学习率
# flag = 0
flag = 1
if flag:
fc_params_id = list(map(id, resnet18_ft.fc.parameters())) # 返回的是parameters的 内存地址
base_params = filter(lambda p: id(p) not in fc_params_id, resnet18_ft.parameters())
optimizer = optim.SGD([
{
'params': base_params, 'lr': LR*0}, # 0，如果设置为0 ，也是一种冻结卷积层的方法，
{
'params': resnet18_ft.fc.parameters(), 'lr': LR}], momentum=0.9)
else:
optimizer = optim.SGD(resnet18_ft.parameters(), lr=LR, momentum=0.9) # 选择优化器
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=lr_decay_step, gamma=0.1) # 设置学习率下降策略
# ============================ step 5/5 训练 ============================
train_curve = list()
valid_curve = list()
for epoch in range(start_epoch + 1, MAX_EPOCH):
loss_mean = 0.
correct = 0.
total = 0.
resnet18_ft.train()
for i, data in enumerate(train_loader):
# forward
inputs, labels = data
inputs, labels = inputs.to(device), labels.to(device)
outputs = resnet18_ft(inputs)
# backward
optimizer.zero_grad()
loss = criterion(outputs, labels)
loss.backward()
# update weights
optimizer.step()
# 统计分类情况
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).squeeze().cpu().sum().numpy()
# 打印训练信息
loss_mean += loss.item()
train_curve.append(loss.item())
if (i+1) % log_interval == 0:
loss_mean = loss_mean / log_interval
print("Training:Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} Acc:{:.2%}".format(
epoch, MAX_EPOCH, i+1, len(train_loader), loss_mean, correct / total))
loss_mean = 0.
# if flag_m1:
print("epoch:{} conv1.weights[0, 0, ...] :\n {}".format(epoch, resnet18_ft.conv1.weight[0, 0, ...]))
scheduler.step() # 更新学习率
# validate the model
if (epoch+1) % val_interval == 0:
correct_val = 0.
total_val = 0.
loss_val = 0.
resnet18_ft.eval()
with torch.no_grad():
for j, data in enumerate(valid_loader):
inputs, labels = data
inputs, labels = inputs.to(device), labels.to(device)
outputs = resnet18_ft(inputs)
loss = criterion(outputs, labels)
_, predicted = torch.max(outputs.data, 1)
total_val += labels.size(0)
correct_val += (predicted == labels).squeeze().cpu().sum().numpy()
loss_val += loss.item()
loss_val_mean = loss_val/len(valid_loader)
valid_curve.append(loss_val_mean)
print("Valid:\t Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} Acc:{:.2%}".format(
epoch, MAX_EPOCH, j+1, len(valid_loader), loss_val_mean, correct_val / total_val))
resnet18_ft.train()
train_x = range(len(train_curve))
train_y = train_curve
train_iters = len(train_loader)
valid_x = np.arange(1, len(valid_curve)+1) * train_iters*val_interval # 由于valid中记录的是epochloss，需要对记录点进行转换到iterations
valid_y = valid_curve
plt.plot(train_x, train_y, label='Train')
plt.plot(valid_x, valid_y, label='Valid')
plt.legend(loc='upper right')
plt.ylabel('loss value')
plt.xlabel('Iteration')
plt.show()
参考
深度之眼Pytorch框架班