API Reference¶
nondefaced_detector.models
: Model functions¶
|
|
A layer block of one convolutional, one batch normalization, and one non-linear activation sequence. |
|
The TruncatedSubmodel trained in Step 1 of the model. |
|
The final block of the model |
|
3 identical submodel blocks are used to train on spatial information from all three axes (axial, coronal, sagittal) separately. |
|
The final block of the model that combines features and outputs a real-valued probability using the sigmoid function. |
nondefaced_detector.dataloaders
: Dataset functions¶
Returns tf.data.Dataset after preprocessing from tfrecords for training and validation |
nondefaced_detector.preprocess
: Preprocess input volumes¶
Script to preprocess volumes
Script to preprocess volumes |
|
Preprocess input volumes before prediction. |
|
Preprocess multiple input volumes before prediction in parallel. |
nondefaced_detector.preprocessing
: Helper functions for the preprocess module¶
|
Conform the input dataset to the canonical orientation. |
|
|
|
nondefaced_detector.training
: Training¶
Train a model. |
nondefaced_detector.prediction
: Making predictions¶
Methods to predict using trained models
Methods to predict using trained models |
|
Return predictions from a list of input volumes. |
|
Transpose dataset and get slices from the volume based on the plane. |
|
Return tf.keras.Model object from a filepath. |
nondefaced_detector.inference
: Inference¶
Standalone inference script for held-out test dataset.
Standalone inference script for held-out test dataset. |
|
Inference function to reproduce original model scores. |
nondefaced_detector.helpers
: Helper functions¶
save_path: path to write the volume to tensor_3d: 3D volume which needs to be saved affine: image orientation, translation |
|
load_path: volume path to load :returns: loaded 3D volume affine: affine data specific to the volume :rtype: volume |
|
nondefaced_detector.utils
: Utility functions¶
Utilities for Nondefaced-detector.
Utilities for Nondefaced-detector. |
|
Download a datalad dataset/repo. |