Switch branches/tags
Nothing to show
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
106 lines (84 sloc) 4.06 KB
from __future__ import print_function
import argparse
import chainer
import chainer.functions as F
import chainer.links as L
from chainer import training
from import extensions
from chainer import serializers
from my_mlp import MyMLP
from my_dataset import MyDataset
def main():
parser = argparse.ArgumentParser(description='Train custom dataset')
parser.add_argument('--batchsize', '-b', type=int, default=10,
help='Number of images in each mini-batch')
parser.add_argument('--epoch', '-e', type=int, default=20,
help='Number of sweeps over the dataset to train')
parser.add_argument('--gpu', '-g', type=int, default=-1,
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')
parser.add_argument('--unit', '-u', type=int, default=50,
help='Number of units')
args = parser.parse_args()
print('GPU: {}'.format(args.gpu))
print('# unit: {}'.format(args.unit))
print('# Minibatch-size: {}'.format(args.batchsize))
print('# epoch: {}'.format(args.epoch))
# 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.
model = MyMLP(args.unit)
if args.gpu >= 0:
chainer.cuda.get_device(args.gpu).use() # Make a specified GPU current
model.to_gpu() # Copy the model to the GPU
# Setup an optimizer
optimizer = chainer.optimizers.MomentumSGD()
# Load the dataset and separate to train data and test data
dataset = MyDataset('data/my_data.csv')
train_ratio = 0.7
train_size = int(len(dataset) * train_ratio)
train, test = chainer.datasets.split_dataset_random(dataset, train_size, seed=13)
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))
# Dump a computational graph from 'loss' variable at the first iteration
# The "main" refers to the target link of the "main" optimizer.
# Take a snapshot at each epoch
#trainer.extend(extensions.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(extensions.snapshot(), trigger=(1, 'epoch'))
# Write a log of evaluation statistics for each epoch
# 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.
['epoch', 'main/loss', 'validation/main/loss', 'elapsed_time']))
# Plot graph for loss for each epoch
if extensions.PlotReport.available():
['main/loss', 'validation/main/loss'],
x_key='epoch', file_name='loss.png'))
print('Warning: PlotReport is not available in your environment')
# Print a progress bar to stdout
if args.resume:
# Resume from a snapshot
serializers.load_npz(args.resume, trainer)
# Run the training
serializers.save_npz('{}/mymlp.model'.format(args.out), model)
if __name__ == '__main__':