train.py

import time
from options.train_options import TrainOptions
from data import CreateDataLoader
from models import create_model
from util.visualizer import Visualizer
from torch.utils.tensorboard import SummaryWriter
import os
import random
import numpy as np
import torch
torch.backends.cudnn.benchmark = True

def set_seed(seed):
    torch.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)
    torch.backends.cudnn.deterministic = True
    torch.backends.cudnn.benchmark = False
    np.random.seed(seed)
    random.seed(seed)
    os.environ['PYTHONHASHSEED'] = str(seed)

def runner():
    opt = TrainOptions().parse()
    if opt.seed > 0:
        set_seed(opt.seed)
        print('Set random seed %s' % opt.seed)
    data_loader = CreateDataLoader(opt)
    dataset = data_loader.load_data()
    dataset_size = len(data_loader)
    print('#training images = %d' % dataset_size)

    model = create_model(opt)
    not_d = True if 'fe' in opt.netD else False
    model.setup(opt, not_D=not_d)
    visualizer = Visualizer(opt)
    total_steps = 0
    writer = SummaryWriter('./checkpoints/' + opt.name)

    for epoch in range(opt.epoch_count, opt.niter + opt.niter_decay + 1):
        epoch_start_time = time.time()
        iter_data_time = time.time()
        epoch_iter = 0

        for i, data in enumerate(dataset):
            iter_start_time = time.time()
            if total_steps % opt.print_freq == 0:
                t_data = iter_start_time - iter_data_time
            visualizer.reset()
            total_steps += opt.batch_size
            epoch_iter += opt.batch_size
            if epoch == opt.epoch_count and i == 0 and 'cut' in opt.model:
                model.data_dependent_initialize(data)
                # regular setup: load and print networks; create schedulers
                model.setup(opt, not_F=not opt.continue_train, not_D=not not_d) 
                
            model.register_layer_output(data)
            model.set_input(data)
            model.optimize_parameters()

            if total_steps % opt.display_freq == 0:
                save_result = total_steps % opt.update_html_freq == 0
                visualizer.display_current_results(model.get_current_visuals(), epoch, save_result)

            if total_steps % opt.print_freq == 0:
                losses = model.get_current_losses()
                model.print_networks_name(writer, total_steps)
                # model.print_layer_output(writer, total_steps)
                t = (time.time() - iter_start_time) / opt.batch_size
                visualizer.print_current_losses(epoch, epoch_iter, losses, t, t_data)
                if opt.display_id > 0:
                    visualizer.plot_current_losses(epoch, float(epoch_iter) / dataset_size, opt, losses)

            if total_steps % opt.save_latest_freq == 0:
                print('saving the latest model (epoch %d, total_steps %d)' %
                      (epoch, total_steps))
                model.save_networks('latest')

            iter_data_time = time.time()
        if epoch % opt.save_epoch_freq == 0:
            print('saving the model at the end of epoch %d, iters %d' %
                  (epoch, total_steps))
            model.save_networks('latest')
            model.save_networks(epoch)

        print('End of epoch %d / %d \t Time Taken: %d sec' %
              (epoch, opt.niter + opt.niter_decay, time.time() - epoch_start_time))
        model.update_learning_rate()


if __name__ == '__main__':
    runner()