facebookresearch / multimodal

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.
BSD 3-Clause "New" or "Revised" License
1.47k stars 140 forks source link

mini-imageNet #515

Open HeYiyang2 opened 12 months ago

HeYiyang2 commented 12 months ago

Due to the large size of the ImageNet dataset, I am using the MiniImageNet dataset. I modified the YAML file accordingly. datasets: target: flava.definitions.TrainingDatasetsInfo selected:

ebsmothers commented 11 months ago

Hi @HeYiyang2 apologies for the delayed response. How did you download the local dataset? I think load_from_disk should only be used in cases where the directory is created as a result of a call to save_to_disk. See e.g. this comment