Skip to content

Commit

Permalink
update
Browse files Browse the repository at this point in the history
  • Loading branch information
chaoyi-wu committed Aug 8, 2023
1 parent 896164c commit 0ad576d
Show file tree
Hide file tree
Showing 5 changed files with 8 additions and 2 deletions.
Binary file added Images/GIF.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added Images/result_rationale.pdf
Binary file not shown.
Binary file added Images/result_report.pdf
Binary file not shown.
Binary file added Images/result_report_generation.pdf
Binary file not shown.
10 changes: 8 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,16 +4,22 @@ The official code for "Towards Generalist Foundation Model for Radiology"
[ArXiv](http://arxiv.org/abs/2308.02463)

[Website](https://chaoyi-wu.github.io/RadFM/)

<img src="https://github.com/chaoyi-wu/PMC-LLaMA/blob/main/figures/zero-shot_cases.png"/>

## Quick Start:
Download [Model checkpoint](https://huggingface.co/chaoyi-wu/RadFM) and check `./src/test.py` for how to generate text with our model.

BTW, make sure you have a large GPU. :)

## Pre-train:
Our pre-train code is given in ```./src/train.py```.
* Check the [data_csv](https://huggingface.co/datasets/chaoyi-wu/RadFM_data_csv) (uploading) to get how different datasets are processed and down load them into `./src/Dataset/data_csv`
* Modify the path as you disire, and check ```./src/train.py``` to pre-train.

## Case Study:

<img src="https://github.com/chaoyi-wu/RadFM/blob/main/figures/zero-shot_cases.png"/>
<img src="https://github.com/chaoyi-wu/PMC-LLaMA/blob/main/figures/zero-shot_cases.png"/>
<img src="https://github.com/chaoyi-wu/PMC-LLaMA/blob/main/figures/zero-shot_cases.png"/>
## To-do List:
- Polish the code for easier usage.
- Update an easy sample for a quick start.
Expand Down

0 comments on commit 0ad576d

Please sign in to comment.