how load model and predict

[pekingzlj]

I has trained following your code.But how to predict an audio by the trainned model.I think it is good if the code has a predict code.Can you share your webchat.

[qiuqiangkong]

Hi, We are using Google's bottleneck feature. So if you want to predict a new waveform, you need to use the bottleneck feature extractor from Google. We have not done this yet. Please feel free to add my WeChat "richard2357"! Best wishes, Qiuqiang

…

________________________________ From: pekingzlj <[email protected]> Sent: 13 November 2017 07:57:40 To: qiuqiangkong/ICASSP2018_audioset Cc: Subscribed Subject: [qiuqiangkong/ICASSP2018_audioset] how load model and predict (#3) I has trained following your code.But how to predict an audio by the trainned model.I think it is good if the code has a predict code.Can you share your webchat. — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub<#3>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AMt5ye_-K3licUS-yGKOzkQZ1_ASbJQeks5s1_Z0gaJpZM4QbXk1>.