Found input variables with inconsistent numbers of samples

Hello,

I’m attempting to complete the audio classification tutorial. I got tot he model testing phase and realized my model had only 60% accuracy so I added more training data. I first tried to click on the “Retrain model” tab then “Train model.” That gives me this error:

Creating job… OK (ID: 189109)

Retraining MFCC…

Cannot start job. There already is a job with key “dsp-3” running.

Job failed (see above)

I also tried to go back to the Impulse design section to retrace my steps and try to run the model again there. Then I got this error:

Creating job... OK (ID: 189110)

Copying features from processing blocks...
Copying features from processing blocks OK

Training model
Job started
Traceback (most recent call last):
  File "/home/train.py", line 245, in <module>
    X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=RANDOM_SEED)
  File "/usr/local/lib/python3.7/site-packages/sklearn/model_selection/_split.py", line 2096, in train_test_split
    arrays = indexable(*arrays)
  File "/usr/local/lib/python3.7/site-packages/sklearn/utils/validation.py", line 230, in indexable
    check_consistent_length(*result)
  File "/usr/local/lib/python3.7/site-packages/sklearn/utils/validation.py", line 205, in check_consistent_length
    " samples: %r" % [int(l) for l in lengths])
ValueError: Found input variables with inconsistent numbers of samples: [2364, 6000]

Application exited with code 1 (Error)

Job failed (see above)

Any ideas on how I might be able to fix this issue? Thanks!

Ok, I ran the MFCC then the NN Classifer and it seems to be working. What is the retrain model section for? Can it not be used if you add more data to the data set?

Hey @tatecarson - yeah retrain should just retrain the model with new data, leaving all previous parameters in place. We did a release today that changes the way we handle these input blocks so we’re looking at any regressions that might have occurred there and caused your issue. But good that you managed to work around it.