Document Understanding AI Center Pipeline Getting Failed

Learning Initatives Automation Starter
1

After Dataset update, if i ran pipeline. It’s getting failed. I ran couple of datasets earlier. It was working fine. Now all my new dataset pipelines are getting failed. any guess on this ?

Pipeline
Pipeline2955×471 33.3 KB

Log :smiling_face_with_tear:

Traceback (most recent call last):
File “”, line 48, in preprocess_dataset
File “”, line 143, in init
File “”, line 31, in init
File “”, line 678, in preprocess_data
AssertionError: Training and / or validation set is empty, verify that training / validation split is correctly set
2022-06-23 03:39:28,594 - uipath_core.training_plugin:model_run:150 - ERROR: Training failed for pipeline type: TRAIN_ONLY, error: Dataset preprocess Failed
2022-06-23 03:39:28,606 - uipath_core.trainer_run:main:90 - ERROR: Training Job failed, error: Dataset preprocess Failed
Traceback (most recent call last):
File “”, line 48, in preprocess_dataset
File “”, line 143, in init
File “”, line 31, in init
File “”, line 678, in preprocess_data
AssertionError: Training and / or validation set is empty, verify that training / validation split is correctly set

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File “/model/bin/uipath_core/trainer_run.py”, line 85, in main
wrapper.run()
File “/workspace/model/microservice/training_wrapper.py”, line 64, in run
return self.training_plugin.model_run()
File “/model/bin/uipath_core/training_plugin.py”, line 151, in model_run
raise e
File “/model/bin/uipath_core/training_plugin.py”, line 143, in model_run
self.run_train_only()
File “/model/bin/uipath_core/training_plugin.py”, line 212, in run_train_only
self.train_model(self.local_dataset_directory)
File “/model/bin/uipath_core/training_plugin.py”, line 116, in train_model
self.model.train(directory)
File “/workspace/model/microservice/train.py”, line 36, in train
self.process_data()
File “/workspace/model/microservice/train.py”, line 69, in process_data
self.trainer.preprocess_dataset()
File “”, line 49, in preprocess_dataset
Exception: Dataset preprocess Failed
Traceback (most recent call last):
File “”, line 48, in preprocess_dataset
File “”, line 143, in init
File “”, line 31, in init
File “”, line 678, in preprocess_data
AssertionError: Training and / or validation set is empty, verify that training / validation split is correctly set

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File “/model/bin/bin/uipath-core-training”, line 8, in
sys.exit(main())
File “/model/bin/uipath_core/trainer_run.py”, line 91, in main
raise e
File “/model/bin/uipath_core/trainer_run.py”, line 85, in main
wrapper.run()
File “/workspace/model/microservice/training_wrapper.py”, line 64, in run
return self.training_plugin.model_run()
File “/model/bin/uipath_core/training_plugin.py”, line 151, in model_run
raise e
File “/model/bin/uipath_core/training_plugin.py”, line 143, in model_run
self.run_train_only()
File “/model/bin/uipath_core/training_plugin.py”, line 212, in run_train_only
self.train_model(self.local_dataset_directory)
File “/model/bin/uipath_core/training_plugin.py”, line 116, in train_model
self.model.train(directory)
File “/workspace/model/microservice/train.py”, line 36, in train
self.process_data()
File "/workspa… (truncated).

2

Hi @SrenivasanKanna

Have you tried with full pipeline run?

Are the data sets labelled specific as train or validate?

Thanks

3

Thank you for your response , Let me check

4

Where you able to fix it? I am facing the same issue? @SrenivasanKanna

5

Make Sure that, the pipeline will be run based on the Data set Import.

If you Choose as Evaluation set, The pipeline will get success only if you choose the Evaluation run.

The Suggested way is - to use Train run to improve your ML Skill and the evaluation run does not improve your ML Skill.

The Reason is - We need to Follow the Below Order:

  1. Create DataLabelling - Import your doc and Export it. That will be available in your DataSets
  2. Create ML Packages
  3. Run Pipeline - If your pipeline got Success.
  4. Create ML Skill - While Creatin ML Skill Choose the package minor Verison of your latest pipeline version