deepdisc.inference.match_objects

Functions

get_matched_object_inds(dataset_dict, outputs[, IOUthresh])

Returns indices for matched pairs of ground truth and detected objects in an image

get_object_coords(dataset_dict, outputs)

Returns indices for matched pairs of ground truth and detected objects in an image

get_matched_object_classes(dataset_dicts, imreader, ...)

Returns object classes for matched pairs of ground truth and detected objects in an image

get_matched_object_classes_new(dataset_dicts, predictor)

Returns object classes for matched pairs of ground truth and detected objects test images

run_batched_match_class(dataloader, predictor)

Test function not yet implemented for batch prediction

run_batched_get_object_coords(dataloader, predictor[, ...])

Returns object classes for matched pairs of ground truth and detected objects test images

Module Contents

get_matched_object_inds(dataset_dict, outputs, IOUthresh=0.5)[source]

Returns indices for matched pairs of ground truth and detected objects in an image

Parameters:

  • dataset_dict (dictionary) – The dictionary metadata for a single image

  • IOUthresh (float) – The IOU threshold used to match detections and ground truth

Returns:

  • matched_gts (list(int)) – The indices of matched objects in the ground truth list

  • matched_dts (list(int)) – The indices of matched objects in the detections list

  • outputs (list(Intances)) – The list of detected object Instances

get_object_coords(dataset_dict, outputs)[source]

Returns indices for matched pairs of ground truth and detected objects in an image

Parameters:

dataset_dict (dictionary) – The dictionary metadata containing the wcs for a single image

Returns:

  • matched_gts (list(int)) – The indices of matched objects in the ground truth list

  • matched_dts (list(int)) – The indices of matched objects in the detections list

  • outputs (list(Intances)) – The list of detected object Instances

get_matched_object_classes(dataset_dicts, imreader, key_mapper, predictor)[source]

Returns object classes for matched pairs of ground truth and detected objects in an image

Parameters:

  • dataset_dicts (list[dict]) – The dictionary metadata for a test images

  • imreader (ImageReader object) – An object derived from ImageReader base class to read the images.

  • key_mapper (function) – The key_mapper should take a dataset_dict as input and return the key used by imreader

  • predictor (AstroPredictor) – The predictor object used to make predictions on the test set

Returns:

  • true_classes (list(int)) – The classes of matched objects in the ground truth list

  • pred_classes (list(int)) – The classes of matched objects in the detections list

get_matched_object_classes_new(dataset_dicts, predictor)[source]

Returns object classes for matched pairs of ground truth and detected objects test images assuming the dataset_dicts have the image HxWxC in the ‘image_shaped’ field

Parameters:

  • dataset_dicts (list[dict]) – The dictionary metadata for a test images

  • predictor (AstroPredictor) – The predictor object used to make predictions on the test set

Returns:

  • true_classes (list(int)) – The classes of matched objects in the ground truth list

  • pred_classes (list(int)) – The classes of matched objects in the detections list

run_batched_match_class(dataloader, predictor)[source]

Test function not yet implemented for batch prediction

run_batched_get_object_coords(dataloader, predictor, oclass=True, gmm=False)[source]

Returns object classes for matched pairs of ground truth and detected objects test images assuming the dataset_dicts have the image HxWxC in the ‘image_shaped’ field

Parameters:

  • dataloader (Dataloader) – Dataloader that reads in images and formats input for the model

  • predictor (AstroPredictor) – The predictor object used to make predictions on the test set

Returns:

  • zpreds (list(float)) – The predicted reshifts of detected objects

  • all_ras (list(float)) – The RAs of detected objects

  • all_decs (list(float)) – The DECs of detected objects

  • oclasses (list(int)) – The predicted classes of detected objects

  • scores (list(float)) – The confidence scores of detected objects