About the storage location of the results (like the generated caption and trace)

facebookresearch / connect-caption-and-trace

A unified framework to jointly model images, text, and human attention traces.

77 stars 7 forks source link

About the storage location of the results (like the generated caption and trace) #8

Open yuhufeng opened 2 years ago

yuhufeng commented 2 years ago

Hi, @zihangm,

Thanks for your excellent work! I have successfully run the code, but I can't find where those results are stored. After the training, just one new folder called "eval_result" appears, which only contains the image caption of the eval part.

I would appreciate it if you could share with me the right way to use this code.

Thanks, yuhu

zihangm commented 2 years ago

The model parameters are saved in the folder whole name is specified by "--id"; "eval_result" contains the generated captions; The current code does not save the generated trace by default (the corresponding code is commented). To save the generated trace, you can use the code in #412--#433 in "captioning/utils/eval_utils_joint.py".

yuhufeng commented 2 years ago

Thank you!