discopat.nn_models

class discopat.nn_models.FasterRCNNModel(net, label_map, model_parameters)[source]

Bases: NNModel

Parameters:

  • net (NeuralNet)

  • label_map (dict[str, int])

  • model_parameters (dict)

classmethod from_dict(model_as_dict)[source]
Parameters:

model_as_dict (dict)

Return type:

Self

make_box_from_tensors(box_xyxy, label, score)[source]
Parameters:

  • box_xyxy (Tensor)

  • label (Tensor)

  • score (Tensor)

Return type:

Box

post_process(raw_predictions)[source]

Adapt the internal detector’s predictions to discopat’s format.

Parameters:

raw_predictions (list[dict[Tensor]])

Return type:

list[Box]

pre_process(frame)[source]

Prepare the frame’s array to pass through the internal detector.

Can be a neural net, a convolutional sparse encoder…

Parameters:

frame (Frame)

Return type:

Tensor

property reversed_label_map
set_device(device)[source]
Parameters:

device (ComputingDevice)

Return type:

None

to_dict()[source]
Return type:

dict

static xyxy_to_xywh(xmin, ymin, xmax, ymax)[source]
Parameters:

  • xmin (float)

  • ymin (float)

  • xmax (float)

  • ymax (float)

Return type:

tuple[float, float, float, float]

Modules

detr

faster_rcnn

torch_box_ops

Utilities for bounding box manipulation and GIoU.