search

GeWu-Lab / OGM-GE_CVPR2022

The repo for "Balanced Multimodal Learning via On-the-fly Gradient Modulation", CVPR 2022 (ORAL)
MIT License
221 stars 18 forks source link

Code doesn't find 'stat.txt',' my_train.txt', or 'my_test.txt' files. #7

Open Kelebrimbor97 opened 2 years ago

Kelebrimbor97 commented 2 years ago

Hi,

I tried to run this code for the test set directly using the provided checkpoints using the command : python main.py --ckpt_path OGM-GE_CVPR2022/ckpt/AVE_concat/archive/data --dataset AVE --alpha 0.3

I also made some changes to the main.py code like setting tensorboard requirement to False

I also changed the formats from .txt. to .csv for CREMAD in dataset.py and then ran this for CREMAD where it gave the error that ValueError: num_samples should be a positive integer value, but got num_samples=0

Please help.

xiaokangpeng commented 2 years ago

Hi,

I tried to run this code for the test set directly using the provided checkpoints using the command : python main.py --ckpt_path OGM-GE_CVPR2022/ckpt/AVE_concat/archive/data --dataset AVE --alpha 0.3

I also made some changes to the main.py code like setting tensorboard requirement to False

I also changed the formats from .txt. to .csv for CREMAD in dataset.py and then ran this for CREMAD where it gave the error that ValueError: num_samples should be a positive integer value, but got num_samples=0

Please help.

Hello,

It's because the dataset.py is prepared for 'AVE' task by default. For CREMAD the dataset should be slightly different, here we provide a demo dataset.py file for CREMAD that you can use as a reference. https://zenodo.org/record/6597205

Best, Xiaokang,