Questions about the files in ".txt" format used to train the "shift" model
yxixi opened this issue · 2 comments
yxixi commented
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
Same question.
ruizewang commented
Same question.