Hello,
I’m training an open-source object detection model from the AI Center. This model is designed to identify whether a part is missing from an object. I’ve marked my images—those with missing parts and those without—using Label Studio and saved them as .XML (Pascal VOC) files.
Here’s what my dataset looks like:
However, when I run the entire model training process, I encounter the following errors. I usually leave the Evaluation dataset blank, and I’m not sure if I should be adding something there:
ERROR:
UiPath_core.training_plugin:trigger_full_training_and_publish_model:580 - ERROR: Failed to trigger full training and publish data, error: ‘numpy.float64’ object has no attribute ‘index’
2024-08-19 10:20:56,048 - UiPath_core.training_plugin:model_run:179 - ERROR: Training failed for pipeline type: FULL_TRAINING, error: ‘numpy.float64’ object has no attribute ‘index’
2024-08-19 10:20:56,053 - UiPath_core.trainer_run:main:103 - ERROR: Training Job failed, error: ‘numpy.float64’ object has no attribute ‘index’
Traceback (most recent call last):
File “/home/aicenter/.local/lib/python3.8/site-packages/UiPath_core/trainer_run.py”, line 98, in main
wrapper.run()
File “/microservice/training_wrapper.py”, line 58, in run
return self.training_plugin.model_run()
File “/home/aicenter/.local/lib/python3.8/site-packages/UiPath_core/training_plugin.py”, line 195, in model_run
raise ex
File “/home/aicenter/.local/lib/python3.8/site-packages/UiPath_core/training_plugin.py”, line 167, in model_run
self.run_full_training()
File “/home/aicenter/.local/lib/python3.8/site-packages/UiPath_core/training_plugin.py”, line 215, in run_full_training
self.trigger_full_training_and_publish_model()
File “/home/aicenter/.local/lib/python3.8/site-packages/UiPath_core/training_plugin.py”, line 581, in trigger_full_training_and_publish_model
raise e
File “/home/aicenter/.local/lib/python3.8/site-packages/UiPath_core/training_plugin.py”, line 554, in trigger_full_training_and_publish_model
self.train_model(self.training_data_directory)
These errors appear during the pipeline run. I’m wondering if the dataset needs a specific folder structure or if I’m missing something else.
Can you help me fix this issue?