Spijkervet / CLMR

Official PyTorch implementation of Contrastive Learning of Musical Representations
https://arxiv.org/abs/2103.09410
Apache License 2.0
311 stars 48 forks source link

the pretrained model on GTZAN #8

Closed gzy-rgb closed 3 years ago

gzy-rgb commented 3 years ago

hello, I appreciate your work in music representation. But i have a question: how many epochs do you train the model for the GTZAN dataset? Can you release the pretrained model of GTZAN?

Spijkervet commented 3 years ago

Hi there! In our paper, we don't pre-train on GTZAN - we only use it for linear evaluation (using a pre-trained network from either MagnaTagATune or MSD).