ubclaunchpad / minutes

:telescope: Speaker diarization via transfer learning
https://medium.com/ubc-launch-pad-software-engineering-blog/speaker-diarisation-using-transfer-learning-47ca1a1226f4
27 stars 5 forks source link

ValueError: Error when checking input: expected conv1d_1_input to have shape (129, 214) but got array with shape (129, 590) #132

Open feemthan opened 6 years ago

feemthan commented 6 years ago

Hi ,

While running the example code provided , I am getting the above error . How to change the shape of the layers ?

chadlagore commented 6 years ago

Feels like it has to do with ms_per_observation parameter—your input is wider (ie longer observations) than the parent model expects. I'd like to see your code, but options are: