chainer / pg-dl-tutorial Goto Github PK

View Code? Open in Web Editor NEW

6.0 14.0 20.0 560 KB

Python 82.04% Shell 17.96%

pg-dl-tutorial's People

Contributors

Stargazers

Watchers

Forkers

kumea odanado naoyashiga adamrocker hillbig toslunar jettan embeddedsamurai msakai aidy1991 gwtnb okuta bobosui kmaehashi delta2323 afcarl

pg-dl-tutorial's Issues

Use Chainer v3

Add two official tutorial contents to Playground

Chainer dev team is writing tutorials along with this content index: chainer/chainer#2576
Some chapters can be written as the contests for PG with executable code snippets.
We are planning to write the below two chapters for PG first, then convert them to the official tutorial document.

Beginner's Tutorial
1.1 Basic functionality
1.2 Write a training code (Under review: #2736)
1.3 Try Trainer class (Under review: #2620)
1.4 Try your own task
a. Without Trainer
b. With Trainer
Customizing Chainer Tutorial -> PG
2.1 Optimizer
2.2 Function
2.3 Link
2.4 Dataset
2.5 Updater
2.6 Extension
2.7 Contribute

Error: Timeout

I just see this error in the page ciFAR-10の学習：総結合層を使った学習 after clicking the Run button.

Traceback (most recent call last):
  File "/var/sandbox/main.py", line 86, in <module>
    trainer.run()
  File "/usr/local/lib/python2.7/dist-packages/chainer/training/trainer.py", line 266, in run
    update()
  File "/usr/local/lib/python2.7/dist-packages/chainer/training/updater.py", line 170, in update
    self.update_core()
  File "/usr/local/lib/python2.7/dist-packages/chainer/training/updater.py", line 182, in update_core
    optimizer.update(loss_func, *in_vars)
  File "/usr/local/lib/python2.7/dist-packages/chainer/optimizer.py", line 392, in update
    loss = lossfun(*args, **kwds)
  File "/usr/local/lib/python2.7/dist-packages/chainer/links/model/classifier.py", line 68, in __call__
    self.loss = self.lossfun(self.y, t)
  File "/usr/local/lib/python2.7/dist-packages/chainer/functions/loss/softmax_cross_entropy.py", line 169, in softmax_cross_entropy
    return SoftmaxCrossEntropy(use_cudnn, normalize, cache_score)(x, t)
Error: Timeout

Port some contents from chainer-notebooks

It should be easy to port these contents to playground.
https://github.com/mitmul/chainer-notebooks

name 'Chain' is not defined

I got this error when clicking Run button in the page Chainerの基本：Optimization

Traceback (most recent call last):
  File "/var/sandbox/main.py", line 7, in <module>
    class Linear(Chain):
NameError: name 'Chain' is not defined
Program exited.

No such file or directory: 'result/cg.dot'

I got this error after clicking Run button in the page Chainerの基本：MNIST 例

Traceback (most recent call last):
  File "/var/sandbox/main.py", line 73, in <module>
    trainer.run()
  File "/usr/local/lib/python2.7/dist-packages/chainer/training/trainer.py", line 269, in run
    entry.extension(self)
  File "/usr/local/lib/python2.7/dist-packages/chainer/training/extensions/computational_graph.py", line 57, in dump_graph
    with open(out_path, 'w') as f:
IOError: [Errno 2] No such file or directory: 'result/cg.dot'
�[J
Program exited.

Error: chainer.utils.type_check.InvalidType in 002chainer/001

When I run the ansewr.py in the 002chainer/001 'Chainerの基本：Variable', I got the following error.

Traceback (most recent call last):
  File "/var/sandbox/main.py", line 7, in <module>
    y = np.linalg.norm(x**2 - 2 * x + 1)
  File "/usr/local/lib/python2.7/dist-packages/numpy/linalg/linalg.py", line 2113, in norm
    x = asarray(x)
  File "/usr/local/lib/python2.7/dist-packages/numpy/core/numeric.py", line 474, in asarray
    return array(a, dtype, copy=False, order=order)
  File "/usr/local/lib/python2.7/dist-packages/chainer/functions/array/get_item.py", line 71, in get_item
    return GetItem(slices)(x)
  File "/usr/local/lib/python2.7/dist-packages/chainer/function.py", line 189, in __call__
    self._check_data_type_forward(in_data)
  File "/usr/local/lib/python2.7/dist-packages/chainer/function.py", line 272, in _check_data_type_forward
    type_check.InvalidType(e.expect, e.actual, msg=msg), None)
  File "/usr/local/lib/python2.7/dist-packages/six.py", line 718, in raise_from
    raise value
chainer.utils.type_check.InvalidType: 
Invalid operation is performed in: GetItem (Forward)

Expect: in_types[0].ndim >= 1
Actual: 0 < 1

Use Chainer v2

NameError: name 'chainer' is not defined

I got the below error when clicking Run button on the page 畳み込みニューラルネットワークを使った画像認識

Traceback (most recent call last):
  File "/var/sandbox/main.py", line 3, in <module>
    train, test = chainer.datasets.get_cifar100()
NameError: name 'chainer' is not defined
Program exited.

001/012 目的関数を定義する (5)

なぜ，確率分布の場合，二乗誤差ではなくクロスエントロピー損失関数を使うのか考えてみてください

Do this mean propery a below sentence?

なぜ，分類問題の場合，二乗誤差ではなくクロスエントロピー損失関数を使うのか考えてみてください

002chainer/004: Functionを利用するには，そのcallオブジェクトを呼び出します。

https://play.chainer.org/book/1/2/5

Functionを利用するには，そのcallオブジェクトを呼び出します。

正しくは「Functionを利用するには，その__call__メソッドを呼び出します」などでしょうか？

Consider to use Python 3

Variable.backprop()

https://play.chainer.org/book/1/1/15

Does Variable have backprop() method?
I think it is Variable.backward().

【Typo?】 https://play.chainer.org/book/1/1/21

def __init__(self, n_units, n_out):
    super(MLP, self).__init__()
    self.add_link("l1", L.Linear(None, n_units))
    self.add_link("l2", L.Linear(None, n_units))
    self.add_link("l2", L.Linear(None, n_out))

"l2"は"l3"では？

Error: Too many outputResult

In the page Chainerの基本：Variable, I got this error when clicking Run button

[  3.  10.   4.]
Traceback (most recent call last):
  File "/var/sandbox/main.py", line 7, in <module>
    y = np.linalg.norm(x**2 - 2 * x + 1)
  File "/usr/local/lib/python2.7/dist-packages/numpy/linalg/linalg.py", line 2113, in norm
    x = asarray(x)
  File "/usr/local/lib/python2.7/dist-packages/numpy/core/numeric.py", line 474, in asarray
    return array(a, dtype, copy=False, order=order)
  File "/usr/local/lib/python2.7/dist-packages/chainer/functions/array/get_item.py", line 71, in get_item
    return GetItem(slices)(x)
  File "/usr/local/lib/python2.7/dist-packages/chainer/function.py", line 189, in __call__
    self._check_data_type_forward(in_data)
  File "/usr/local/lib/python2.7/dist-packages/chainer/function.py", line 272, in _check_data_type_forward
    type_check.InvalidType(e.expect, e.actual, msg=msg), None)
  File "/usr/local/lib/python2.7/dist-packages/six.py", line 718, in raise_from
    raise value
chainer.utils.type_check.InvalidType: 
Error: Too many outputResult

And I think the filename is a typo: ansewr.py should be answer.py ?