search

andrewowens / multisensory

Code for the paper: Audio-Visual Scene Analysis with Self-Supervised Multisensory Features
http://andrewowens.com/multisensory/
Apache License 2.0
220 stars 61 forks source link

Questions about the files in ".txt" format used to train the "shift" model #18

Open yxixi opened 5 years ago

yxixi commented 5 years ago

I noticed videos from AudioSet were used to train the "shift" model. In "shift_params.py", there are params such as: train_list = '/data/ssd1/owens/audioset-vid-v21/small_train.txt', test_list = '/data/ssd1/owens/audioset-vid-v21/small_train.txt', train_list = '/data/scratch/owens/audioset-vid-v21/train_tfs.txt', test_list = '/data/scratch/owens/audioset-vid-v21/test_tfs.txt', However, I didn't find any available files in ".txt" format at the website : https://research.google.com/audioset/ Could you provide those ".txt" files to train the "shift" model? Thank you for your help! Looking for your reply:)

LingYeAI commented 5 years ago

Same question.

ruizewang commented 5 years ago

Same question.