airkjw/RETFound
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add_notebook

Browse Source
This commit is contained in:
rmaphoh
2023-12-15 12:31:15 +00:00
parent a91abec5cd
commit de202be699
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6 -6
View File
@@ -8,21 +8,21 @@ Please contact **ykzhoua@gmail.com** or **yukun.zhou.19@ucl.ac.uk** if you have
Keras version implemented by Yuka Kihara can be found [here](https://github.com/uw-biomedical-ml/RETFound_MAE) Keras version implemented by Yuka Kihara can be found [here](https://github.com/uw-biomedical-ml/RETFound_MAE)
### Key features ### 📝Key features
- RETFound is pre-trained on 1.6 million retinal images with self-supervised learning - RETFound is pre-trained on 1.6 million retinal images with self-supervised learning
- RETFound has been validated in multiple disease detection tasks - RETFound has been validated in multiple disease detection tasks
- RETFound can be efficiently adapted to customised tasks - RETFound can be efficiently adapted to customised tasks
### News ### 🎉News
- 2023/12: [Colab notebook](https://colab.research.google.com/drive/1_X19zdMegmAlqPAEY0Ao659fzzzlx2IZ?usp=sharing) is now online - free GPU & simple operation!!! - 🎄2023/12: [Colab notebook](https://colab.research.google.com/drive/1_X19zdMegmAlqPAEY0Ao659fzzzlx2IZ?usp=sharing) is now online - free GPU & simple operation!!!
- 2023/09: a [visualisation demo](https://github.com/rmaphoh/RETFound_MAE/blob/main/RETFound_visualize.ipynb) is added - 2023/09: a [visualisation demo](https://github.com/rmaphoh/RETFound_MAE/blob/main/RETFound_visualize.ipynb) is added
- 2023/10: change the hyperparameter of [input_size](https://github.com/rmaphoh/RETFound_MAE#:~:text=finetune%20./RETFound_cfp_weights.pth%20%5C-,%2D%2Dinput_size%20224,-For%20evaluation%20only) for any image size - 2023/10: change the hyperparameter of [input_size](https://github.com/rmaphoh/RETFound_MAE#:~:text=finetune%20./RETFound_cfp_weights.pth%20%5C-,%2D%2Dinput_size%20224,-For%20evaluation%20only) for any image size
### Install environment ### 🔧Install environment
1. Create environment with conda: 1. Create environment with conda:
@@ -40,7 +40,7 @@ pip install -r requirement.txt
``` ```
### Fine-tuning with RETFound weights ### 🌱Fine-tuning with RETFound weights
To fine tune RETFound on your own data, follow these steps: To fine tune RETFound on your own data, follow these steps:
@@ -146,7 +146,7 @@ print("Model = %s" % str(model))
``` ```
### Citation ### 📃Citation
If you find this repository useful, please consider citing this paper: If you find this repository useful, please consider citing this paper:
``` ```