zhjohnchan/M3AE
[MICCAI-2022] This is the official implementation of Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training.
Python
Issues
- 0
visualization code
#24 opened by Victory0622 - 3
- 0
Epochs of Pretrained M3AE Model?
#23 opened by Kwon-YJ - 7
- 1
MELINDA dataset
#22 opened by dominCodebug - 0
The "init_weights" function for model initialization.
#21 opened by Pyy-hah - 0
visualization results
#20 opened by 825632955 - 2
- 0
- 2
retrieval taking too long
#15 opened by stha-prashant - 1
Question about recall calculation
#16 opened by stha-prashant - 2
- 1
Hello, when I debug M3AE, I found that the table value here is empty [ ], is there any problem with the code here? Or do I need to modify where
#12 opened by cl-red - 5
- 9
HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/downloaded/roberta-base/resolve/main/vocab.json
#1 opened by 1112321sfdsaf - 1
MELINDA dataset
#8 opened by bjz205588 - 0
download medicat
#11 opened by cl-red - 0
download medicat
#10 opened by cl-red - 2
question about prepro/make_arrow.py
#9 opened by Adam-lxd - 3
ValueError: Connection error, and we cannot find the requested files in the cached path. Please try again or make sure your Internet connection is on.
#7 opened by helenypzhang - 2
missing roco_train_references.jsonl file
#6 opened by helenypzhang - 2
MELINDA dataset
#5 opened by helenypzhang - 1
seems to be a subtle typo
#4 opened by baeseongsu - 3
Split for VQARAD
#3 opened by GanjinZero