M3AE
M3AE copied to clipboard
zhjohnchan
[MICCAI-2022] This is the official implementation of Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training.
Hi, Thanks for your excellent work and share this awesome repo. When I run your code, I found a warning "Missing logger folder: result/task_pretrain_m3ae-seed0-from_" I checked the /result folder and...
Hey, Thanks very much for the excellent work and repo. When I run 'bash run_scripts/pretrain_m3ae.sh', I got the above exception. I tried to click this link and found that the...
Excellent work! As for VQA-RAD dataset of the VQA task, I download the checkpoint you provided and run the test script. The effect was shown below.  But paper's 
Hello, I've been exploring your project and am particularly interested in the model initialization process. I noticed that during model initialization, the `init_weights` function from `m3ae_utils.py` is utilized to initialize...
Hello, thank you for your excellent work. I am very interested in your research, but I am not sure how the visualization results of the RAD dataset are obtained. If...
The code can run normally. But when I use debug training data, the program stops and the data cannot be read. I want to know how to use debug to...
Hello, may I ask if I am running "bash run_ Scripts/finetunem3ae. sh" , what is the reason for the error "wandb. errors. UsageError: api_key not configured (no ty). call wandb....
I have an out-of-bounds problem with the targets array when performing a fine-tuning med-vqa task, and I observe that the max_label_size is set to 79. Is this because the med-vqa...
How many epochs was the pretrained model of M3AE trained for? I couldn't find any clues in the paper, GitHub repository, or the released checkpoint files. Thank you.
It’s a great piece of work! Could you please share the visualization code?
Metadata
Owner
Metadata
[MICCAI-2022] This is the official implementation of Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training.