AI Center: Failed to create training Pipeline

[Ashutosh.Gupta]

Hi Everyone,

I am new to Ai Center and trying to create a training pipeline with animal pictures as a training dataset.
Please help me with the below error.
Let me know if any further details are needed.

Regards,
Ashutosh Gupta

2023-07-04 06:34:21,045 - uipath_core.trainer_run:main:74 - INFO:  Starting training job...
2023-07-04 06:34:21,677 - matplotlib:_get_config_or_cache_dir:526 - WARNING:  Matplotlib created a temporary config/cache directory at /tmp/matplotlib-a1ccq7hk because the default path (/home/aicenter/.config/matplotlib) is not a writable directory; it is highly recommended to set the MPLCONFIGDIR environment variable to a writable directory, in particular to speed up the import of Matplotlib and to better support multiprocessing.
2023-07-04 06:34:21,944 - matplotlib.font_manager:_load_fontmanager:1544 - INFO:  generated new fontManager
2023-07-04 06:34:28,797 - uipath_core.storage.azure_storage_client:download:118 - INFO:  Dataset from bucket folder training-bd9f84d1-10e9-41ad-9a59-da3bc22a99f0/7a4929b3-fbcd-4ef1-ba02-3e5155e5d01b/789caa0a-ce8d-4214-9989-86127f0241fb with size 300 downloaded successfully
2023-07-04 06:34:28,798 - uipath_core.training_plugin:train_model:130 - INFO:  Start model training...
2023-07-04 06:34:28,798 - uipath_core.training_plugin:initialize_model:124 - INFO:  Start model initialization...
2023-07-04 06:34:28,836 - uipath_core.training_plugin:initialize_model:127 - INFO:  Model initialized successfully
2023-07-04 06:34:28,836 - uipath_core.training_plugin:model_run:179 - ERROR:  Training failed for pipeline type: TRAIN_ONLY, error: [Errno 2] No such file or directory: '/microservice/dataset/images'
2023-07-04 06:34:29,145 - uipath_core.trainer_run:main:91 - ERROR:  Training Job failed, error: [Errno 2] No such file or directory: '/microservice/dataset/images'
Traceback (most recent call last):
  File "/home/aicenter/.local/lib/python3.8/site-packages/uipath_core/trainer_run.py", line 86, 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 171, in model_run
    self.run_train_only()
  File "/home/aicenter/.local/lib/python3.8/site-packages/uipath_core/training_plugin.py", line 255, in run_train_only
    self.train_model(self.local_dataset_directory)
  File "/home/aicenter/.local/lib/python3.8/site-packages/uipath_core/training_plugin.py", line 132, in train_model
    response = self.model.train(directory)
  File "/microservice/train.py", line 37, in train
    self.process_data()
  File "/microservice/train.py", line 61, in process_data
    self.df_train, self.df_test = preprocess.preprocess_data(self.opt)
  File "<frozen aicenter.image_classifier.preprocess>", line 11, in preprocess_data
  File "<frozen aicenter.image_classifier.preprocess>", line 31, in create_df_from_single_folder
FileNotFoundError: [Errno 2] No such file or directory: '/microservice/dataset/images'
2023-07-04 06:34:29,145 - uipath_core.trainer_run:main:98 - INFO:  Job run stopped.

[vrdabberu (Varunraj Dabberu)]

Hi @Ashutosh.Gupta

In training sections all the fields should be mapped and if you are not mapping any filed then make sure you have disabled that particular filed and then you try creating and running the pipeline.

Hope it helps !!

[Ashutosh.Gupta]

Hi,

Here is the screenshot for the pipeline settings. Let me know if I have missed anything.

Regards,
Ashutosh Gupta

[vrdabberu (Varunraj Dabberu)]

Hi @Ashutosh.Gupta

Check whether you have disabled the unnecessary fields in Data Labelling section.

Please send me the screenshot of training page (Data Labelling) and also change the pipeline type from train run to full pipe line run.

Regards

[Ashutosh.Gupta]

Hi @vrdabberu ,

Below are the screenshots for the same.

Regards,
Ashutosh Gupta

[vrdabberu (Varunraj Dabberu)]

Hi @Ashutosh.Gupta

Once you click on Data labelling you will get a data labelling session and in that session click on the animal_training or animal_evaluation as per required and u will be redirected to a document manager page and in that particular page you can see all fields in the right side and please check the unmapped field and beside the unmapped field there will be a pencil symbol click on that and you can see the hidden option in that and mark that unmapped filed as hidden and do the same process for all unmapped fields and then export the files and try to create a new pipeline and then you run the pipeline.

Regards.

[vrdabberu (Varunraj Dabberu)]

refer the below images.