Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Error when using ICNet model #10

Open
htadashi opened this issue Oct 25, 2018 · 2 comments
Open

Error when using ICNet model #10

htadashi opened this issue Oct 25, 2018 · 2 comments

Comments

@htadashi
Copy link

Hi!

First of all, thanks for sharing your very helpful code.
Following the README.md, I have downloaded icnet.npy from Google Drive link to the model/cityscapes folder.

However, when I run

python inference.py --img-path input/outdoor_1.png --model icnet

the following error happens:

Traceback (most recent call last):
  File "inference.py", line 65, in <module>
    main()
  File "inference.py", line 44, in main
    model = ICNet()
  File "/home/tadashi/ML/semantic-segmentation-tensorflow/model.py", line 907, in __init__
    super().__init__({'data': self.img_tf}, num_classes, is_training)
TypeError: super() takes at least 1 argument (0 given)
@LinRui9531
Copy link

Did you deal with this error? I also have this error.

@mgei
Copy link

mgei commented Apr 21, 2019

Workaround in Python 2 change in model.py line 907 to

super(ICNet, self).__init__({'data': self.img_tf}, num_classes, is_training)

See also https://stackoverflow.com/questions/38963018/typeerror-super-takes-at-least-1-argument-0-given-error-is-specific-to-any

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants