You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When i run the training process of your code, i got an error "tensorflow.python.framework.errors_impl.InvalidArgumentError: num_lower must be negative or less or equal to number of rows (0) got: 150"
Can u help me figure it out? thanks in advance
The text was updated successfully, but these errors were encountered:
Hi, the error is from this function: asam.py/asat(), and the kernel function is tf.linalg.band_part().
The frame number of audios which is fed into the model is 200 (you can see it in mtfaa_net.py). And I guess you changed the frame number to a smaller value. So you can:
use the default value of frame number (i.e. 200), that is you need feed a longer audio to the model;
change the default value of a_frames(which is 300 now) to a smaller value to satisfy your frame number;
When i run the training process of your code, i got an error "tensorflow.python.framework.errors_impl.InvalidArgumentError: num_lower must be negative or less or equal to number of rows (0) got: 150"
Can u help me figure it out? thanks in advance
The text was updated successfully, but these errors were encountered: