Testing - not working

[ofirkris]

Hello, thanks for sharing the project.

I tried testing it and have several questions:

1. -l/--level is required for testing in test.py - what should be the value?
2. Does this project support running inference on non-square images like in deep-fill inpainting? how can this be achieved?
3. What values should be in the test.flist file? (it's required too)
   ../flist/celebahq/test.flist

Thanks!

[pilhoon]

I modified here to

parser.add_argument("-l", "--level",  type=int, required=False, default=None)

Maybe the level value depends on your training settings cause train.py also uses the same dataset loader.
This seems to work well, but you know, all a guess.

[Carl-BoKai]

Hello, thanks for sharing the project.

I tried testing it and have a question
run test.py

/usr/local/lib/python2.7/dist-packages/requests/init.py:83: RequestsDependencyWarning: Old version of cryptography ([1, 2, 3]) may cause slowdown.
warnings.warn(warning, RequestsDependencyWarning)
Traceback (most recent call last):
File "test.py", line 36, in
from core.utils import set_device, postprocess, ZipReader, set_seed
ImportError: No module named core.utils

How to deal?Thanks!