Core Module (radionets.core)#
Introduction#
radionets.core contains core modules, classes and functions
for the deep-learning framework.
Submodules#
Reference/API#
radionets.core Package#
Functions#
|
|
|
returns list of bundle paths located in a directory |
|
|
|
|
|
|
|
Load data set from a directory and return it as H5DataSet. |
|
Loads a previously saved model as pre-model. |
|
open radio galaxy bundles created in first analysis step |
|
|
|
open radio galaxy bundles created in first analysis step |
|
|
|
write fft_pairs created in second analysis step to h5 file |
|
|
|
Basic logging setup. |
Classes#
Callback for tracking and plotting average training and validation losses. |
|
|
Callback for logging training metrics and visualizations to Comet ML. |
|
Callback to move model to CUDA device before training. |
|
Callback that applies data augmentation using random rotations. |
|
|
|
Callback for gradient and prediction tracking. |
|
|
|
Normalization callback for input and target data. |
|
Callback for computing spatial gradients of model predictions. |
|
Callback for saving temporary model checkpoints during training. |
|
Callback for switching loss functions during training. |