deepsulci.pattern_classification.capsul.resnet_labeling.PatternDeepLabeling

PatternDeepLabeling

Process to recognize a searched fold pattern using a 3D-ResNet-18.

Note

  • Type ‘PatternDeepLabeling.help()’ for a full description of this process parameters.

  • Type ‘<PatternDeepLabeling>.get_input_spec()’ for a full description of this process input trait types.

  • Type ‘<PatternDeepLabeling>.get_output_spec()’ for a full description of this process output trait types.

Inputs

[Mandatory]

graphs: a legal value ([‘List_File’] - mandatory)

graphs to classify

model_file: a string or os.PathLike object ([‘File’] - mandatory)

file (.mdsm) storing neural network parameters

param_file: a string or os.PathLike object ([‘File’] - mandatory)

file (.json) storing the hyperparameters (bounding_box, learning rate and momentum)

Outputs

result_file: a string or os.PathLike object ([‘File (filename: input)’] - mandatory)

file (.csv) with predicted class (y_pred) for each of the input graphs