CDCD
CDCD copied to clipboard
L-YeZhu
[ICLR2023] Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation (CDCD).
Hello, Ms. Zhu I was wondering if you have released the implementation for the genre accuracy metric
Dear Ms.Zhu: I hope this email finds you well. My name is zhaoyang Zhang, and I am a fellow researcher in the field of generating music through dance, much like...
`extra_file_path` in [code1](https://github.com/L-YeZhu/CDCD/blob/667f9c0156e68d6e884a1ad5201ae1928098b02d/synthesis/data/aist_dataset.py#L43) is None. This results in the `__getitem__()` returns NoneType for negative_music in [code2](https://github.com/L-YeZhu/CDCD/blob/667f9c0156e68d6e884a1ad5201ae1928098b02d/synthesis/data/aist_dataset.py#L109).
I load the genre label.npy in the data folder, the shape is (6632,10), while the aist train dataset only has 2581 audios and motions. why?
Hi, I was wondering if you have released the implementation for the genre accuracy metric.
What specific changes are to be done to get inference from those inference files @L-YeZhu @kyleolsz
This is an awesome work! I want to compare with it in our new works. But I have some error when downloading the checkpoint. Could you please check the url...
