Open superhg2012 opened 6 years ago
Hi, Unfortunately this is the best model checkpoint that i have for now. It tuned out that models from youtube-8m are not very suitable for audio classification. I have plans to try some sort of RNN model. It should be much better. Until then, You can try it yourself.
thanks for reply! One more question, how can I get my own pca matrix instead of the one in your project?
hi, could you share a well pre_trained youtube8m-model? The existing you provided in your project youtube_model.ckpt.data-00000-of-00001 is not very accurate when run the demo server.