DanceRevolution
DanceRevolution copied to clipboard
stonyhu
Code for paper Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning
Are there an original videos in the data set, so that 3D pose can be extracted through dynamic capture tool. Thanks.
Is it better to have a longer music length in the dataset? The length of a song is about 6 minutes, and the model is rigid and sluggish in about...
`Traceback (most recent call last): File "inference2.py", line 315, in main() File "inference2.py", line 294, in main for batch in tqdm(test_loader, desc='Generating dance poses'): File "/home/tanrongyuan/.conda/envs/u2netNew/lib/python3.6/site-packages/tqdm/std.py", line 1178, in __iter__...
Hi, it seems that when extracting onset envelope, you use the audio percussive generated by the effects.hpss function as input of onset.onset_strength function instead of the raw spectrogram. I wonder...
Thx for ur work. It is very hard to follow if there no evaluation code ~
i have trained a model and hope to generate whole dance pose through my music
Can you tell me how much the loss of the test set is after training? I think my loss is too large
