Skip to content
This repository has been archived by the owner on Mar 21, 2024. It is now read-only.

Issue on running innerEye deep learning with a local dataset instead of Azure blob storage. #816

Closed
1 task done
Med-Rokaimi opened this issue Oct 25, 2022 · 1 comment

Comments

@Med-Rokaimi
Copy link

Med-Rokaimi commented Oct 25, 2022

Is there an existing issue for this?

  • I have searched the existing issues

Problem summary

I'm trying to implement the Sample classification task: Glaucoma Detection on OCT volumes following the steps in the following link:
https://innereye-deeplearning.readthedocs.io/md/sample_tasks.html
But I want to run the model on a local dataset instead of Azure blob dataset. I created the following file myglaucoma.py:

from InnerEye.ML.configs.classification.GlaucomaPublic import GlaucomaPublic
class MyGlaucomaModel(GlaucomaPublic):
def init(self) -> None:
super().init()
self.azure_dataset_id="glaucoma_detection".
Where the "glaucoma_detection" is the folder where the dataset is located. When I try to run it using the following command:

python InnerEye/ML/runner.py --model=MyGlaucomaModel

But I get the following error: Unable to make dataset 'glaucoma_detection available for a local run because no AzureML workspace has been provided. Provide a workspace, or set a folder for local execution.

Code for reproduction

class MyGlaucomaModel(GlaucomaPublic):
    def __init__(self) -> None:
        super().__init__()
        self.azure_dataset_id="glaucoma_detection".

Actual outcome

Traceback (most recent call last):
File "InnerEye/ML/runner.py", line 467, in
main()
File "InnerEye/ML/runner.py", line 461, in main
run(project_root=fixed_paths.repository_root_directory(),
File "InnerEye/ML/runner.py", line 457, in run
return runner.run()
File "InnerEye/ML/runner.py", line 219, in run
azure_run_info = self.submit_to_azureml_if_needed()
File "InnerEye/ML/runner.py", line 352, in submit_to_azureml_if_needed
azure_run_info = submit_to_azure_if_needed(
File "/home/ai/anaconda3/envs/InnerEye/lib/python3.8/site-packages/health_azure/himl.py", line 502, in submit_to_azure_if_needed
mounted_input_datasets, mount_contexts = setup_local_datasets(cleaned_input_datasets,
File "/home/ai/anaconda3/envs/InnerEye/lib/python3.8/site-packages/health_azure/datasets.py", line 342, in setup_local_datasets
target_path, mount_context = d.to_input_dataset_local(workspace)
File "/home/ai/anaconda3/envs/InnerEye/lib/python3.8/site-packages/health_azure/datasets.py", line 139, in to_input_dataset_local
raise ValueError(f"Unable to make dataset '{self.name} available for a local run because no AzureML "
ValueError: Unable to make dataset 'glaucoma_detection available for a local run because no AzureML workspace has been provided. Provide a workspace, or set a folder for local execution.

Error messages

Unable to make dataset 'glaucoma_detection available for a local run because no AzureML workspace has been provided. Provide a workspace, or set a folder for local execution.

Expected outcome

Train the model

System info

No response

AB#7859

@Med-Rokaimi
Copy link
Author

Solved
local_dataset=full_ml_test_data_path(),
self.azure_dataset_id="glaucoma_detection",

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
Status: Done
Development

No branches or pull requests

1 participant