Deadlineexceed , I am using Audio classification and NN block

I have done everything, reduced window size, reduced Epoch but this persists, kindly help me out so that I use default 100 Epoch size.

I am doing audio classification, I have 10 sec .wav files, I am using windowing size 5000ms, If I use 10,000ms size this causes loss in accuracy, I have 3 classes; Aircraft, fireworks/tools and Environmental sounds. Therefor I reduced the Epoch but still the problem of Deadlineexceed arises.
The project ID is 74645. Kindly extend this time for me so that I am able to complete training my model.

Hello @rahmad,

I just increased your limits.
However, I only see one class in your project, maybe you removed some data to try a lighter model. Anyway, it should be fine now.

Best regards,

Louis

Thankyou. I will try it again with all the 3 classes

1 Like

**I have uploaded two classes each containing 2 sec .wav files sampled at 48000Hz, I am getting this errror, I don’t know how to deal with this one, Kindly help me out, I am stuck with my project. Regards **
Traceback (most recent call last):
File “/app/input-block-preprocessing/downsample.py”, line 94, in
features_file[total_window_count] = window
ValueError: could not broadcast input array from shape (96001) into shape (96002)
Error windowing Downsample error code was not 0, but was 1
Downsample error code was not 0, but was 1

Application exited with code 1 (Error)