Created
December 27, 2016 02:07
-
-
Save corochann/180c29d0037d50ebceb295d8cafe1e3c to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
from __future__ import print_function | |
import argparse | |
import numpy as np | |
import matplotlib.pyplot as plt | |
import chainer | |
import chainer.functions as F | |
import chainer.links as L | |
from chainer import training | |
from chainer.training import extensions | |
from chainer import cuda | |
# Network definition | |
class MLP(chainer.Chain): | |
def __init__(self, n_units, n_out): | |
super(MLP, self).__init__( | |
# the size of the inputs to each layer will be inferred | |
l1=L.Linear(None, n_units), # n_in -> n_units | |
l2=L.Linear(None, n_units), # n_units -> n_units | |
l3=L.Linear(None, n_out), # n_units -> n_out | |
) | |
def __call__(self, x): | |
h1 = F.relu(self.l1(x)) | |
h2 = F.relu(self.l2(h1)) | |
return self.l3(h2) | |
def main(): | |
parser = argparse.ArgumentParser(description='Chainer example: MNIST') | |
parser.add_argument('--batchsize', '-b', type=int, default=100, | |
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=1000, | |
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)) | |
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. | |
model = L.Classifier(MLP(args.unit, 10)) | |
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 | |
xp = np if args.gpu < 0 else cuda.cupy | |
# Setup an optimizer | |
optimizer = chainer.optimizers.Adam() | |
optimizer.setup(model) | |
# Load the MNIST dataset | |
train, test = chainer.datasets.get_mnist() | |
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. | |
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() | |
# ----- Predict ----- | |
# predicting label (number) of test images using trained model | |
# load model | |
chainer.serializers.load_npz('result/snapshot_iter_12000', trainer) | |
classifier_model = trainer.updater.get_optimizer('main').target | |
mlp_model = classifier_model.predictor | |
# show graphical results of first 15 data to understand what's going on in inference stage | |
plt.figure(figsize=(15, 10)) | |
for i in range(15): | |
x = chainer.Variable(xp.asarray([test[i][0]])) # test data | |
# t = Variable(xp.asarray([test[i][1]])) # labels | |
y = mlp_model(x) | |
np.set_printoptions(precision=2, suppress=True) | |
print('{}-th image: answer = {}, predict = {}'.format(i, test[i][1], F.softmax(y).data)) | |
prediction = y.data.argmax(axis=1) | |
test_image = (test[i][0] * 255).astype(np.int32).reshape(28, 28) | |
plt.subplot(3, 5, i+1) | |
plt.imshow(test_image, cmap='gray') | |
plt.title("No.{0} / Answer:{1}, Predict:{2}".format(i, test[i][1], prediction)) | |
plt.axis("off") | |
plt.tight_layout() | |
plt.savefig('{}/predict.png'.format(args.out)) | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment