PredictionImageGradient

class radionets.core.callbacks.PredictionImageGradient(validation_data, model, amp_phase, arch_name)

Bases: Callback

Callback for computing spatial gradients of model predictions.

Parameters:

validation_datastr or Path

Path to validation dataset.

modelstr or Path

Path to pretrained model.

amp_phasebool

Whether to use amplitude-phase representation.

arch_namestr

Name of the architecture used for the model.

Attributes Summary

learn
name	Name of the Callback, camel-cased and with 'Callback' removed
order
run
run_train
run_valid

Methods Summary

__call__(event_name)	Call self.{event_name} if it's defined
save_output_pred()

Attributes Documentation

learn = None

name

Name of the Callback, camel-cased and with ‘Callback’ removed

order = 0

run = True

run_train = True

run_valid = True

Methods Documentation

__call__(event_name)

Call self.{event_name} if it’s defined

save_output_pred()