search

antoyang / FrozenBiLM

[NeurIPS 2022] Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
https://arxiv.org/abs/2206.08155
Apache License 2.0
156 stars 24 forks source link

Problems in reproducing the code process #17

Closed LazyCat-show closed 8 months ago

LazyCat-show commented 1 year ago

Hello, thank you very much for being able to share your work,！I've run into a couple of problems in trying to reproduce your work:

  1. running main.py, videoqa.py gives an error:“ERROR:root:No token file found. Also make sure that a [prod] section with a 'token = value' assignment exists.”
  2. how to set combine_datasets and combine_datasets_val I hope you can take time out of your busy schedule to help me out!
antoyang commented 1 year ago
  1. I have never faced that one. Can you provide some context so that I can help you?
  2. combine_datasets/combine_datasets_val refer to the datasets you want to use for training/testing (for instance ivqa).