Generate feature failure

Help
#1

I get this error when I try to generate features,

*Creating windows from 1 files...*
*Job started*
*Scheduling job in cluster...*

*Attached to job 1994967...*
*[1/1] Creating windows from files...*
*[1/1] Creating windows from files...*
* *
*Traceback (most recent call last):*
*  File "/app/input-block-preprocessing/downsample.py", line 86, in <module>*
*    window = sn.resample_poly(window, target_freq, sample_freq, axis=ds_axis)*
*  File "/usr/local/lib/python3.7/dist-packages/scipy/signal/signaltools.py", line 3089, in resample_poly*
*    h = firwin(2 * half_len + 1, f_c, window=window)*
*  File "/usr/local/lib/python3.7/dist-packages/scipy/signal/fir_filter_design.py", line 457, in firwin*
*    m = np.arange(0, numtaps) - alpha*
*ValueError: Maximum allowed size exceeded*
*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)*

*Job failed (see above)*

I tried adjusting window size, window increase and frequency with no luck.

Can you please help me

#2

Hello @Peak,

I just had a look at your project and your dataset is too big (2104 hours), can you try splitting your dataset into smaller samples (about 1 min for each samples for example) and reduce the size of your dataset (two or three hours).
I have seen that you are sampling at 1Hz, maybe you can add a bit more than three hours with this sampling rate but better to start small and increase progressively.

Feel free to send me an email at louis@edgeimpulse.com with some details of your project and I might increase a bit your job limit compute time. However, within the free tier version, you probably won’t be able to train a model using your full dataset.

Best regards,

Louis