Description
Task Introduction Anime Face Generation
TODO
- Train your own anime face generator using Generative Adversarial Networks.
Dataset
Crypko
https://crypko.ai/#
Data Collections
Thanks to Arvin Liu for collecting this dataset.
Data Format
- The download link is in the sample code.
- Unzip zip, the data format is as below:
- faces/
○ 0.jpg
○ 1.jpg
○ …
- Total 71314 .jpg files in a folder.
- DO NOT use any extra data and pretrained models.
JudgeBoi
- 5 submission quota per day, reset at midnight.
- Users not in whitelist will have no quota.
- Only *.tgz file is allowed, file size should be smaller than 2MB.
- The countdown timer on the homepage is for reference only.
- We do limit the number of connections and request rate for each ip. If you cannot access the website temporarily, please wait patiently.
- Please do not attempt to attack JudgeBoi, thank you.
- Every Wednesday and Saturday from 0:00 to 3:00 is our system maintenance time. If the website cannot be used during this time, please wait patiently for the completion of the maintenance.
JudgeBoi
- Since the evaluation metric in this homework requires GPU computation, the JudgeBoi server cannot serve too many submissions at the same time.
- Under normal circumstances, JudgeBoi will complete the evaluation within one minute. If pending conditions are encountered, it may be longer. Please wait patiently after you submit.
- However, if you have waited more than two minutes for the progress bar to finish, please refresh the page and try to upload again.
- Please DO NOT upload at the last minute; no one knows if you can upload successfully.
NTU Cool
- Upload your code to NTU Cool.
○ TAs will check your code if necessary.
- If you beat the boss baseline in JudgeBoi, you may submit a report named pdf to explain the method you use to obtain the extra 0.5 pt.
○ The FID score assesses the similarity between two datasets of images, which is the lower the better in this task.
Evaluation Metrics
- AFD (anime face detection) rate
○ To detect whether an anime face is in a given image.
○ The detection rate is the higher the beter.
