vincent-zhq/unis-mmc

Code for UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning (ACL 2023)

Hi there 👋

unis-mmc's Issues

where is the Path/To/Dataset_Home_Directory/Food101/texts_txt/filet_mignon/filet_mignon_226.txt? you don't give it

where is text_txt

Hello, dataloader.py part, where is the file in the /text_txt/ folder in this code text_path = self.args.data_dir + '/texts_txt/' + annotation + '/' + id.replace(".jpg", ".txt").

No such file or directory: 'Path/To/Dataset_Home_Directory\\Food101/texts_txt/lasagna/lasagna_666.txt'

Hello, I would like to ask how to use the train.csv and test.csv you provided. Where should I put it? I put it in the Food101 directory at the specified location according to the code, and run python main.py --seeds 4.

Then the following error occurred;
FileNotFoundError: [Errno 2] No such file or directory: 'Path/To/Dataset_Home_Directory\Food101/texts_txt/lasagna/lasagna_666.txt'

Then I downloaded the data set and didn't see a similar file.

Could you please take the time to call me back? Thank you very much.

pretained问题

麻烦想问下这个文件夹里的预训练模型是要自己下载嘛，代码里没有直接调用？复现的时候报错Can't load tokenizer for 'Path/To/Pretrained/bert_base_uncased/'

新数据问题

使用你的模型的这段代码，在新数据中是不是也需要标签信息？

The question of Pre-training

In your paper, the accuracy of the food data set reached 94%. What version of bert and vit did you use? When I reproduced your code, I found that you only provided the base version.