Error when trying to train FOMO

I am getting the following error when I try to train a FOMO Model. Not all of the samples have been labelled yet… I am trying to build a model to see if it is good enough to label the rest. I also started this project as an image classification project, and then did a Version/Restore to create a new project so I could try Object Detection on the data set. Not sure if that added some confusing cruft to the data objects.

It is project ID: 133736

Creating job... OK (ID: 3822466)

Scheduling job in cluster...
Job started
Scheduling job in cluster...
Job started
Splitting data into training and validation sets...
Traceback (most recent call last):
  File "/home/", line 368, in <module>
  File "/home/", line 307, in main_function
    train_dataset, validation_dataset, samples_dataset, X_train, X_test, Y_train, Y_test, has_samples, X_samples, Y_samples =
  File "/app/./resources/libraries/ei_tensorflow/", line 164, in get_dataset_from_folder
    X_train, X_test, Y_train, Y_test, X_train_raw = split_and_shuffle_data(
  File "/app/./resources/libraries/ei_tensorflow/", line 50, in split_and_shuffle_data
    Y = ei_tensorflow.utils.load_y_structured(dir_path, 'y_train.npy', len(X))
  File "/app/./resources/libraries/ei_tensorflow/", line 7, in load_y_structured
    Y_structured_file = json.loads(
  File "/usr/lib/python3.8/", line 322, in decode
    (result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x93 in position 0: invalid start byte
Application exited with code 1

Quick try @lukedc Can you remove and re-add DSP block and regenerate features?

That solved it! It must have been using the old features and block.