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
Describe the bug
During training from the GUI it gives me an error, the log says folder of a class is empty, but I checked and it has audio segments.
To Reproduce
Steps to reproduce the behavior:
For the GUI:
Go to Train
Click on Select training data, select folder
Classifier output: tflite
Epochs, batch size and learning rate, default
Upsampling mode: SMOTE
Upsampling ratio: 0.25
Use mixup
Crop mde: segments
Model save: replace
See error:
`Log:
[2025-01-29 14:13:34]
Traceback (most recent call last):
File "birdnet_analyzer\utils.py", line 411, in upsample_core
File "numpy\random\mtrand.pyx", line 951, in numpy.random.mtrand.RandomState.choice
ValueError: 'a' cannot be empty unless no samples are taken
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "birdnet_analyzer\train.py", line 393, in trainModel
File "birdnet_analyzer\model.py", line 244, in trainLinearClassifier
File "birdnet_analyzer\utils.py", line 504, in upsampling
File "birdnet_analyzer\utils.py", line 413, in upsample_core
birdnet_analyzer.utils.EmptyClassException: Class with label Lanius is empty. Please remove it from the training data.`
Expected behavior
A clear and concise description of what you expected to happen.
Screenshots
Lanius Folder:
Desktop (please complete the following information):
OS: Win11
Version 1.5.1
The text was updated successfully, but these errors were encountered:
Describe the bug
During training from the GUI it gives me an error, the log says folder of a class is empty, but I checked and it has audio segments.
To Reproduce
Steps to reproduce the behavior:
For the GUI:
`Log:
[2025-01-29 14:13:34]
Traceback (most recent call last):
File "birdnet_analyzer\utils.py", line 411, in upsample_core
File "numpy\random\mtrand.pyx", line 951, in numpy.random.mtrand.RandomState.choice
ValueError: 'a' cannot be empty unless no samples are taken
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "birdnet_analyzer\train.py", line 393, in trainModel
File "birdnet_analyzer\model.py", line 244, in trainLinearClassifier
File "birdnet_analyzer\utils.py", line 504, in upsampling
File "birdnet_analyzer\utils.py", line 413, in upsample_core
birdnet_analyzer.utils.EmptyClassException: Class with label Lanius is empty. Please remove it from the training data.`
Expected behavior
A clear and concise description of what you expected to happen.
Screenshots
Lanius Folder:
Desktop (please complete the following information):
The text was updated successfully, but these errors were encountered: