train_test.py

"""General-purpose training script for image-to-image translation.

This script works for various models (with option '--model': e.g., pix2pix, cyclegan, colorization) and
different datasets (with option '--dataset_mode': e.g., aligned, unaligned, single, colorization).
You need to specify the dataset ('--dataroot'), experiment name ('--name'), and model ('--model').

It first creates model, dataset, and visualizer given the option.
It then does standard network training. During the training, it also visualize/save the images, print/save the loss plot, and save models.
The script supports continue/resume training. Use '--continue_train' to resume your previous training.

Example:
    Train a CycleGAN model:
        python train.py --dataroot ./datasets/maps --name maps_cyclegan --model cycle_gan
    Train a pix2pix model:
        python train.py --dataroot ./datasets/facades --name facades_pix2pix --model pix2pix --direction BtoA

See options/base_options.py and options/train_options.py for more training options.
See training and test tips at: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/docs/tips.md
See frequently asked questions at: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/docs/qa.md
"""
import logging
import os
import sys
import time
from options.train_options import TrainOptions
from data import create_dataset
from models import create_model
from util import html
from util.visualizer import Visualizer
from util.util import make_dataframe, Metrics

if __name__ == '__main__':
    opt = TrainOptions().parse()  # get training options
    dataset = create_dataset(opt)  # create a dataset given opt.dataset_mode and other options
    dataset_size = len(dataset)  # get the number of images in the dataset.
    print('The number of training images = %d' % dataset_size)

    opt_val = TrainOptions().parse()  # create options for your validation dataset
    # opt_val.dataroot = '/home/dataset/npy_test/npy_256'
    opt_val.phase = 'test'  # specify where your test images are saved
    opt_val.preprocess = 'center'  # you don't want data-augmentation in validation, unless you're using U-Net, then you might need to crop! If so, just remove this line.
    # opt_val.crop_size = 128      # when model name == STGAN
    opt_val.no_flip = True
    opt_val.serial_batches = True  # with this option, it's always the same test image that is saved during training, which helps with seeing the evolution of the performance
    opt_val.batch_size = 1
    dataval = create_dataset(opt_val)  # create the validation dataset
    print('The number of validation images = %d' % len(dataval))

    model = create_model(opt)  # create a model given opt.model and other options
    model.setup(opt)  # regular setup: load and print networks; create schedulers
    visualizer = Visualizer(opt)  # create a visualizer that display/save images and plots
    total_iters = 0  # the total number of training iterations

    # path of test metrics save to disk
    frames_meta = make_dataframe(nbr_rows=len(dataval))
    metric_dir = os.path.join(opt.results_dir, opt.name, 'metrics')
    if not os.path.exists(metric_dir):
        os.makedirs(metric_dir)
    # define logging
    logging.basicConfig(filename=opt.checkpoints_dir + '/' + opt.name + "/train_log.txt", level=logging.INFO,
                        format='[%(asctime)s.%(msecs)03d] %(message)s', datefmt='%H:%M:%S')
    logging.getLogger().addHandler(logging.StreamHandler(sys.stdout))
    for epoch in range(opt.epoch_count,
                       opt.n_epochs + opt.n_epochs_decay + 1):  # outer loop for different epochs; we save the model by <epoch_count>, <epoch_count>+<save_latest_freq>
        epoch_start_time = time.time()  # timer for entire epoch
        iter_data_time = time.time()  # timer for data loading per iteration
        epoch_iter = 0  # the number of training iterations in current epoch, reset to 0 every epoch
        visualizer.reset()  # reset the visualizer: make sure it saves the results to HTML at least once every epoch
        model.update_learning_rate()  # update learning rates in the beginning of every epoch.
        model.train()  # begin to train
        for i, data in enumerate(dataset):  # inner loop within one epoch
            iter_start_time = time.time()  # timer for computation per iteration
            if total_iters % opt.print_freq == 0:
                t_data = iter_start_time - iter_data_time

            total_iters += opt.batch_size
            epoch_iter += opt.batch_size
            model.set_input(data)  # unpack data from dataset and apply preprocessing
            model.optimize_parameters()  # calculate loss functions, get gradients, update network weights

            if total_iters % opt.display_freq == 0:  # display images on visdom and save images to a HTML file
                save_result = total_iters % opt.update_html_freq == 0
                model.compute_visuals()
                visualizer.display_current_results(model.get_current_visuals(), epoch, save_result)

            if total_iters % opt.print_freq == 0:  # print training losses and save logging information to the disk
                losses = model.get_current_losses()
                t_comp = (time.time() - iter_start_time) / opt.batch_size
                visualizer.print_current_losses(epoch, epoch_iter, losses, t_comp, t_data)
                if opt.display_id > 0:
                    visualizer.plot_current_losses(epoch, float(epoch_iter) / dataset_size, losses)

            if total_iters % opt.save_latest_freq == 0:  # cache our latest model every <save_latest_freq> iterations
                print('saving the latest model (epoch %d, total_iters %d)' % (epoch, total_iters))
                save_suffix = 'iter_%d' % total_iters if opt.save_by_iter else 'latest'
                model.save_networks(save_suffix)

            iter_data_time = time.time()
        # test for per train epoch
        model.eval()
        for i, testdata in enumerate(dataval):
            model.set_input(testdata)  # unpack data from data loader
            model.test()  # run inference
            visuals = model.get_current_visuals()  # get image results
            Metrics(i, frames_meta, visuals, metric_dir)

        # save metrics csvfile to disk
        frames_meta_filename = os.path.join(metric_dir, "inference.csv")
        frames_meta.to_csv(frames_meta_filename, sep=',')

        if epoch % opt.save_epoch_freq == 0:  # cache our model every <save_epoch_freq> epochs
            print('saving the model at the end of epoch %d, iters %d' % (epoch, total_iters))
            model.save_networks('latest')
            model.save_networks(epoch)

        print('End of epoch %d / %d \t Time Taken: %d sec' % (
            epoch, opt.n_epochs + opt.n_epochs_decay, time.time() - epoch_start_time))