train_cifar.py

from __future__ import print_function
import argparse

import chainer
import chainer.links as L
from chainer import training
from chainer.training import extensions

import models.VGG
from datasets.UCF11 import UCF11Dataset


def main():
    parser = argparse.ArgumentParser(description='Chainer UCF11.py example:')
    parser.add_argument('--batchsize', '-b', type=int, default=64,
                        help='Number of images in each mini-batch')
    parser.add_argument('--learnrate', '-l', type=float, default=0.05,
                        help='Learning rate for SGD')
    parser.add_argument('--epoch', '-e', type=int, default=300,
                        help='Number of sweeps over the dataset to train')
    parser.add_argument('--gpu', '-g', type=int, default=0,
                        help='GPU ID (negative value indicates CPU)')
    parser.add_argument('--out', '-o', default='result',
                        help='Directory to output the result')
    parser.add_argument('--resume', '-r', default='',
                        help='Resume the training from snapshot')
    args = parser.parse_args()

    print('GPU: {}'.format(args.gpu))
    print('# Minibatch-size: {}'.format(args.batchsize))
    print('# epoch: {}'.format(args.epoch))
    print('')

    # Set up a neural network to train.
    # Classifier reports softmax cross entropy loss and accuracy at every
    # iteration, which will be used by the PrintReport extension below.
    print('Using CIFAR100 dataset.')
    class_labels = 11
    train = UCF11Dataset('images/')
    test = UCF11Dataset('images/')
    #train, test = get_ucf11()
    model = L.Classifier(models.VGG.VGG3D(class_labels))
    if args.gpu >= 0:
        # Make a specified GPU current
        chainer.cuda.get_device_from_id(args.gpu).use()
        model.to_gpu()  # Copy the model to the GPU

    optimizer = chainer.optimizers.MomentumSGD(args.learnrate)
    optimizer.setup(model)
    optimizer.add_hook(chainer.optimizer.WeightDecay(5e-4))

    train_iter = chainer.iterators.SerialIterator(train, args.batchsize)
    test_iter = chainer.iterators.SerialIterator(test, args.batchsize,
                                                 repeat=False, shuffle=False)
    # Set up a trainer
    updater = training.StandardUpdater(train_iter, optimizer, device=args.gpu)
    trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=args.out)

    # Evaluate the model with the test dataset for each epoch
    trainer.extend(extensions.Evaluator(test_iter, model, device=args.gpu))

    # Reduce the learning rate by half every 25 epochs.
    trainer.extend(extensions.ExponentialShift('lr', 0.5),
                   trigger=(25, 'epoch'))

    # Dump a computational graph from 'loss' variable at the first iteration
    # The "main" refers to the target link of the "main" optimizer.
    trainer.extend(extensions.dump_graph('main/loss'))

    # Take a snapshot at each epoch
    trainer.extend(extensions.snapshot(), trigger=(args.epoch, 'epoch'))

    # Write a log of evaluation statistics for each epoch
    trainer.extend(extensions.LogReport())

    # Print selected entries of the log to stdout
    # Here "main" refers to the target link of the "main" optimizer again, and
    # "validation" refers to the default name of the Evaluator extension.
    # Entries other than 'epoch' are reported by the Classifier link, called by
    # either the updater or the evaluator.
    trainer.extend(extensions.PrintReport(
        ['epoch', 'main/loss', 'validation/main/loss',
         'main/accuracy', 'validation/main/accuracy', 'elapsed_time']))

    # Print a progress bar to stdout
    trainer.extend(extensions.ProgressBar())

    if args.resume:
        # Resume from a snapshot
        chainer.serializers.load_npz(args.resume, trainer)

    # Run the training
    trainer.run()


if __name__ == '__main__':
    main()