ml-4m
ml-4m copied to clipboard
apple
4M: Massively Multimodal Masked Modeling
Thanks for providing the traning source for FM model. I notice that there is the scripts **_fourm/vq/__init__.py_** to pause the pre-trained tokens. However, there is no scripts that can parse...
I am working on precomputing tokens for each modality in my 4M training pipeline. I’m using grayscale semantic segmentation masks as input, but I’m encountering an issue where the regenerated...
It seems like run_training_4m.py uses the arg `text_tokenizer_path `to define the path of the text tokenizer, however the config files have this same variable called `tokenizer_path`. I believe they were...
I asked about data loading and preperation in this issue: https://github.com/apple/ml-4m/issues/25#issue-2526543321 However I still cannot load detection label correctly even I have prepare the label in .json file as requested,...
Tried the notebooks kept receiving the following error: ModuleNotFoundError: No module named 'fourm'. I used the forum instead of cpu.
