train_model_server/utils/Train_resnet.py

from __future__ import print_function, division

import shutil

import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
import torch.backends.cudnn as cudnn
import numpy as np
from torchvision import datasets, models, transforms
import time
import os
import zipfile
import copy
import platform
from torch.utils.tensorboard import SummaryWriter

cudnn.benchmark = True

data_phase = ['train', 'val']
database_dir = './data'
output_dir = './runs'  # 模型保存和日志备份大目录
newest_log = './newest_log'  # 最新日志保存目录
log_port = 6667  # tensorboard日志端口
writer: SummaryWriter

# 用异步接收请求判断
task_list = ['train', 'data_process']
running_task = set()
exit_flag = False


def print_progress_bar(iteration, total, prefix='', suffix='', decimals=1, length=100, fill='█', print_end="\r"):
    # 计算完成百分比
    percent_complete = f"{(100 * (iteration / float(total))):.{decimals}f}"
    # 计算进度条填充长度
    filled_length = int(length * iteration // total)
    # 创建进度条字符串
    bar = fill * filled_length + '-' * (length - filled_length)
    # 打印进度条
    print(f'\r{prefix} |{bar}| {percent_complete}% {suffix}', end=print_end)
    # 完成时打印新行
    if iteration == total:
        print()


# 备份log
def move_log(model_save_dir):
    log_name = os.listdir(newest_log)[0]
    log_path = os.path.join(newest_log, log_name)
    save_path = os.path.join(model_save_dir, log_name)

    shutil.copy(log_path, save_path)
    print('log 已备份')


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

    for epoch in range(num_epochs):
        print(f'Epoch {epoch + 1}/{num_epochs}')
        print('-' * 10)

        for phase in data_phase:
            if phase == 'train':
                model.train()
            else:
                model.eval()

            running_loss = 0.0
            running_corrects = 0

            l = len(dataloaders[phase])
            print_progress_bar(0, l, prefix='进度:', suffix='完成', length=50)

            # Iterate over data.
            for i, (inputs, labels) in enumerate(dataloaders[phase]):
                inputs = inputs.to(device)
                labels = labels.to(device)

                optimizer.zero_grad()

                with torch.set_grad_enabled(phase == 'train'):
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1)
                    loss = criterion(outputs, labels)

                    # backward + optimize only if in training phase
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()

                # statistics
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)

                # 更新进度条
                print_progress_bar(i + 1, l, prefix='进度:', suffix='完成', length=50)

            if phase == 'train':
                scheduler.step()

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects.double() / dataset_sizes[phase]

            writer.add_scalar(phase + " loss", epoch_loss, epoch + 1)
            writer.add_scalar(phase + " accuracy", epoch_acc, epoch + 1)

            print(f'{phase} Loss: {epoch_loss:.6f} Acc: {epoch_acc:.6f}')

            # deep copy the model
            if phase == 'val' and epoch_acc >= best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())
                print('copy best model')

        print()

    time_elapsed = time.time() - since
    print(f'Training complete in {time_elapsed // 60:.0f}m {time_elapsed % 60:.0f}s')
    print(f'Best val Acc: {best_acc:4f}')

    # 加载在验证集中表现最好的模型
    model.load_state_dict(best_model_wts)

    return model


def train(epoch=30, save_path='resnet.pt', model_path=None,
          freeze=7, learn_rate=0.01, momentum=0.9, decay=0.7):
    # 如果不加载训练过的模型则加载预训练模型
    if model_path is None or model_path == '':
        model = models.resnet50(pretrained=True)
        # 修改最后一层
        num_features = model.fc.in_features
        model.fc = nn.Linear(num_features, class_num)
    else:
        model = torch.load(model_path)
        old_cls_num = model.fc.out_features
        if class_num == old_cls_num:
            print('分类头适合, 进行训练')
        else:
            # 修改最后一层
            num_features = model.fc.in_features
            model.fc = nn.Linear(num_features, class_num)
            print(f"修改分类头: {old_cls_num} --> {class_num}")

    model = model.to(device)

    criterion = nn.CrossEntropyLoss()
    optimizer_ft = optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
    exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)

    # 冻结部分参数
    for i, c in enumerate(model.children()):
        if i == freeze:
            break
        for param in c.parameters():
            param.requires_grad = False

    for param in model.parameters():
        print(param.requires_grad)

    model = train_model(model, criterion, optimizer_ft,
                        exp_lr_scheduler, num_epochs=epoch)

    torch.save(model, save_path)


'''
    epoch: 训练次数
    save_path: 模型保存路径

    model_path: 加载的模型路径 
    freeze_num: 冻结层数

    '''
def load_param(epoch, data_dir, model_path, freeze, learn_rate, momentum, decay):
    global device, class_num, dataloaders, dataset_sizes, output_dir, writer

    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

    data_transforms = {
        'train': transforms.Compose([
            transforms.Resize((224, 224)),
            transforms.RandAugment(),
            transforms.RandomPerspective(distortion_scale=0.5, p=0.5),
            transforms.ColorJitter(brightness=0.2, contrast=0.2),
            transforms.RandomApply([transforms.GaussianBlur(5)], p=0.3),
            transforms.ToTensor(),
            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
        ]),
        'val': transforms.Compose([
            transforms.Resize((224, 224)),
            transforms.ToTensor(),
            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
        ]),
    }

    image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])
                      for x in data_phase}
    dataloaders = {
        x: torch.utils.data.DataLoader(image_datasets[x], batch_size=32, shuffle=True, num_workers=16, pin_memory=True)
        for x in data_phase}
    dataset_sizes = {x: len(image_datasets[x]) for x in data_phase}
    class_names = image_datasets['train'].classes

    class_num = len(class_names)
    print('class:', class_num)

    print(f"输入参数: 训练次数: {epoch}, 模型路径: {model_path}")

    model_id = len(os.listdir(output_dir)) + 1
    model_save_dir = os.path.join(output_dir, str(model_id))
    if not os.path.exists(model_save_dir):
        os.mkdir(model_save_dir)

    # 删除旧的log
    if len(os.listdir(newest_log)) > 0:
        os.remove(os.path.join(newest_log, os.listdir(newest_log)[0]))
    writer = SummaryWriter(newest_log)
    writer.add_text('model', "model id: " + str(model_id))

    save_path = os.path.join(model_save_dir, 'resnet50_out' + str(class_num) + '.pt')

    train(epoch=epoch,
          save_path=save_path,
          model_path=model_path,
          freeze=freeze,
          learn_rate=learn_rate,
          momentum=momentum,
          decay=decay)

    writer.flush()
    writer.close()
    move_log(model_save_dir)