missing_aware_prompts
missing_aware_prompts copied to clipboard
YiLunLee
Multimodal Prompting with Missing Modalities for Visual Recognition, CVPR'23
Thx for your great work! I have some questions about your code. 1. Did you set the random seed to 0 for all experiments? 2. I reproduced as you did...
I notice that the class Hatememes set the text_column_name to 'plots' as follows `class HateMemesDataset(BaseDataset): def __init__(self, *args, split="", missing_info={}, **kwargs): assert split in ["train", "val", "test"] self.split = split...
Thanks for your work! The UPMC-Food-101 dataset contains rich textual information, is it appropriate to only use the sample titles? I also noticed that the maximum text length is set...
When i test with weights i trained on a datasets, e.g., MM-IMDb, i used to get different results with that it got during training. How about solving this issue?
Thanks for your interesting work! When I download the UPMC Food-101 dataset, the link https://visiir.isir.upmc.fr/explore is invalid with 502 bad gateway. I have downloaded the images of UPMC Food-101 from...
hateful to hatefull old: ``` elif args.dataset.lower() == 'hateful_memes': from vilt.utils.write_hatememes import make_arrow make_arrow(f'{args.root}/Hatefull_Memes', './datasets/Hatefull_Memes') ``` new: ``` elif args.dataset.lower() == 'hatefull_memes': from vilt.utils.write_hatememes import make_arrow make_arrow(f'{args.root}/Hatefull_Memes', './datasets/Hatefull_Memes') ```
Hi, thanks for the excellent work! I am confused by the number of prompts, i.e., M^2 -1. When M=3, why the number of prompts is 8? Suppose there are a,...
python run.py with data_root=./datasets/mmimdb num_gpus=1 num_nodes=1 per_gpu_batchsize=4 task_finetune_mmimdb load_path=./pretrained_weights/vilt_200k_mlm_itm.ckpt exp_name=./output/mmimdb Thanks for your impressive work, Following the above training setting, I got the results "40.23" on mmimdb dataset. So l...
