L4A Crop Mask Error


I am trying to run the L4A Crop Mask for my test site but am getting the following error in the output:

Number of inputs 1
Computing class counts
Image 0 vector length 31

Processing input 0
Image 0 vector length 31
itk::ERROR: No training sample found inside image
Traceback (most recent call last):
File “/usr/lib/python2.7/site-packages/sen2agri_common.py”, line 589, in execute
pool.map(self.internal_train_stratum, self.strata)
File “/usr/lib64/python2.7/multiprocessing/pool.py”, line 250, in map
return self.map_async(func, iterable, chunksize).get()
File “/usr/lib64/python2.7/multiprocessing/pool.py”, line 554, in get
raise self._value
Exception: (‘Error running TrainImagesClassifier’, 1)

Does anyone know what the problem is?

Grateful for any help


Hi Graham,

I have the same problem when running the L4A Crop Mask manually. Did you manage to sort it out?


Hi Graham,

I managed to sort out issue in my case and hopefully the same was in your case too. I ran the L4A process without in situ data and the process ran correctly.

This suggested that there was something wrong in my in situ data. I changed my attributes table and ensured that the area of each feature is more than 20 sq m. Also please ensure that the column heading is correct as the parameters looks for column of certain name.

It work correctly after that.

Hope this helps.


1 Like