Created
July 20, 2017 06:23
-
-
Save koreyou/78dddf5a250c9ff1a7dca0d1f9afcefe to your computer and use it in GitHub Desktop.
To report at https://github.com/chainer/chainer/issues/3027
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
import chainer | |
import chainer.functions as F | |
import chainer.links as L | |
from chainer import training | |
from chainer.training import extensions | |
# Network definition | |
class MLP(chainer.Chain): | |
def __init__(self, n_out): | |
super(MLP, self).__init__() | |
with self.init_scope(): | |
self.l1 = L.Linear(None, n_out) | |
def __call__(self, x): | |
return self.l1(x) | |
# 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(10)) | |
# Make a specified GPU current | |
chainer.cuda.get_device_from_id(0).use() | |
model.to_gpu() # Copy the model to the GPU | |
# Setup an optimizer | |
optimizer = chainer.optimizers.Adam() | |
optimizer.setup(model) | |
# Load the MNIST dataset | |
train, _ = chainer.datasets.get_mnist() | |
train_iter = chainer.iterators.SerialIterator(train, 32) | |
# Set up a trainer | |
updater = training.StandardUpdater(train_iter, optimizer, device=0) | |
trainer = training.Trainer(updater, (5, 'epoch'), out='result') | |
trainer.extend(extensions.ParameterStatistics(model)) | |
# Write a log of evaluation statistics for each epoch | |
trainer.extend(extensions.LogReport()) | |
# Run the training | |
trainer.run() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment