How to train PromptPAR using our own dataset

Question

How to train PromptPAR using our own dataset

Closed this issue 3 months ago · 5 comments

Thank you for sharing the code, but how to train PromptPAR using our own dataset?

Answer 1 · 2024-07-15T07:56:53.000Z

You can refer to the code in /dataset/prepocess to generate pkl files of your own dataset for training. Just include the image path and onehot labels

Answer 2 · 2024-07-16T11:40:17.000Z

Thanks for reply. There are more than 10 files in the folder. Not clear which file (or files) I need to read to get our own dataset?

Answer 3 · 2024-07-16T11:48:54.000Z

You can refer to pa100k.py because he is simple enough, you just need to modify attr_words, pa100k_data (annotation file) to your own dataset.

Answer 4 · 2024-07-18T08:07:46.000Z

Thank for the reply. but I am not able to find the file pa100k.py in the folder /dataset/preprocess as you indicated. the files in the folder are listed below. Please let me know if that is the right folder. Thank you

Answer 5 · 2024-07-20T03:07:32.000Z

you can find it in PromptPAR