You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for your wonderful work on GAN generated image detection. Since most experiments in your paper are performed on person instead of other objects, we have tried to test your model on the dataset provided by CNNDetector ([33] in your paper). The experiment is performed on a workstation with Windows system, and we follow the guide in Readme (what we modified is only the data path), but we cannot run it correctly. It shows "TypeError: cannot serialize '_io.TextIOWrapper' object", at 'for i, data in enumerate(dl):' in test.py.
Would you pleased provide some advice ? Hope for your reply soon.
The text was updated successfully, but these errors were encountered:
Hi, unfortunately I haven't tested it on a Windows system. I'm not certain if it would be caused by input path; seems that the UnpairedDataset object takes in a path which is directly a folder of images (without subfolders). One difference to note between CNNDetector and the models here is that these models were trained exclusively on face domain.
Thank you for your wonderful work on GAN generated image detection. Since most experiments in your paper are performed on person instead of other objects, we have tried to test your model on the dataset provided by CNNDetector ([33] in your paper). The experiment is performed on a workstation with Windows system, and we follow the guide in Readme (what we modified is only the data path), but we cannot run it correctly. It shows "TypeError: cannot serialize '_io.TextIOWrapper' object", at 'for i, data in enumerate(dl):' in test.py.
Would you pleased provide some advice ? Hope for your reply soon.
The text was updated successfully, but these errors were encountered: