HPS file missing for TVQA task and eval_videoQA.py fails because of this (how to fix)?

linjieli222 / HERO

Research code for EMNLP 2020 paper "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"

https://arxiv.org/abs/2005.00200

MIT License

230 stars 34 forks source link

HPS file missing for TVQA task and eval_videoQA.py fails because of this (how to fix)? #43

Closed yrf1 closed 2 years ago

yrf1 commented 2 years ago

Hi, line 42 in _evalvideoQA.py reads the hps file: hps_file = f'{opts.output_dir}/log/hps.json' However, no hps file is available from running the download script of _scripts/downloadtvqa.sh

Am I missing sth here, or is there a fix that can be posted?

yrf1 commented 2 years ago

Update: maybe the hps file can be found from config/train-tvqa-8gpu.json Tho documentation would be helpful for ppl coming across in the future:)

linjieli222 commented 2 years ago

Thanks for your comments. hps_file is the configuration stored during training. If you run train_videoQA.py first then run eval_videoQA.py, you will see such file in the folder where you save the trained model (i.e., the output_dir specified for training). hps_file can be different from config/train-tvqa-8gpu.json if you are not using our default setting for training the video QA model.