Run out of input workaround and error with train_loop() (warnings.warn('genfromtxt:Empty input file:"%s"'%fname)

Asked 2 months ago, Updated 2 months ago, 4 views

Nice to meet you.I'm a python beginner.

I am currently working on this site.
"""Learn and recognize your own image set in depth with the NIN of the Chainer"""

$python 0-E 20000 train.txt test.txt2>&1|teelog

Now that I've done this,

Traceback (most recent call last):
  File "", line 66, in<module>
    mean_image=pickle.load(open(args.mean, 'rb')))
EOFError:Ran out of input


My environment is Python 3.5.2::Anaconda 4.2.0 (x86_64).

Thank you for your cooperation.


Find this article and

cPickle.UnpicklingError on Chainer

The error content is different, but I did it

File "", line 67, in<module>
  File "~/site-packages/numpy/lib/", line 392, in load,1)#back-up
IOError: [Errno22] Invalid argument

You get the error

Additional 2



I rewritten it to , and it worked somehow.However,

`~/.pyenv/versions/anaconda3-4.2.0/lib/python3.5/site-packages/numpy/lib/ input file:"mean.npy"warnings.warn('genfromxt:Empy' file%)%" input file:"%"

The error appears.(There is an error, but it is still running at the terminal.)
There seems to be a problem with train_loop() on

Please take care of the above as well.

Additional 3

Probably solved it.

The file mean.npy generated just before this execution is 0 bytes, and I re-generated it and started running it without any errors.

Because I don't use GPU, epoch1 takes a long time (learning rate 0.01) and I'm worried, but I'm running it without any errors.
The above issues are

mean_image=np.load(open(args.mean, 'rb')))

I wrote it like this, and it passed.

Note: Thank you for moving!
Note 2: Thank you for editing! It's easier to see!

python python3 chainer

2022-09-30 11:40

1 Answers

The mean.npy file I generated just before my execution is 0 bytes, and when I re-generated it, there was no error and I started running it.

2022-09-30 11:40

If you have any answers or tips

© 2022 OneMinuteCode. All rights reserved.