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

Scene chainer #5

Open
wants to merge 6 commits into
base: devel
Choose a base branch
from
Open

Scene chainer #5

wants to merge 6 commits into from

Conversation

Mostafa3zazi
Copy link
Member

No description provided.

Then you can use my script above for training.

## I want to fine-tune CNN part.
Officially, this doesn’t support the CNN tuning. That’s what I did in the original paeper. However, informally, I made it to train CNN part too... but I didn't document it, now, after two years, I don't remember very much. `train_image_caption_model.py` is the script to train the CNN part. I also remember that I tried to use another preprocessed json than I document here. Currently I have the `_dic` file and the main processed file separately but I combined them. The script to generate a preprocessed file in the new format (i.e that one compatible with `train_image_caption_model.py` ) should be `code/preprocess_captions.py`. That's what I vaguely remember.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Add your own README file, and reference the original file with proper credits.

"fenced-in": 8513,
"fences": 8720,
"fencing": 7675,
"fende
Copy link
Member

@mhashim6 mhashim6 Feb 24, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Provide an Arabic version of this file, you can use this code for translation.

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

Successfully merging this pull request may close these issues.

2 participants