datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
imagenet-cimagenetNWPU-CaptionMAD-sysDSIC-Cityscapes_dataThis is the Cityscapes dataset used to train the models in the GitHub repository https://github.com/abilalk02/D-SIC. The original complete dataset can be found here: https://www.cityscapes-dataset.com/.
The train and test datasets should be downloaded and saved as .tar files in the 'data/train/without_captions' and 'data/test/without_captions' folders in the GitHub repository respectively. D-SIC is trained without text caption conditioning. Thus, the .txt files are empty.
DTD