nvidia.dali.fn.box_encoder — NVIDIA DALI (original) (raw)

nvidia.dali.fn.box_encoder(__input_0, __input_1, /, *, anchors, bytes_per_sample_hint=[0], criteria=0.5, means=[0.0, 0.0, 0.0, 0.0], offset=False, preserve=False, scale=1.0, stds=[1.0, 1.0, 1.0, 1.0], device=None, name=None)#

Encodes the input bounding boxes and labels using a set of default boxes (anchors) passed as an argument.

This operator follows the algorithm described in “SSD: Single Shot MultiBox Detector” and implemented in mlperf/training. Inputs must be supplied as the following Tensors:

• BBoxes that contain bounding boxes that are represented as [l,t,r,b].
• Labels that contain the corresponding label for each bounding box.

The results are two tensors:

• EncodedBBoxes that contain M-encoded bounding boxes as [l,t,r,b], where M is number of anchors.
• EncodedLabels that contain the corresponding label for each encoded box.

Supported backends

• ‘cpu’
• ‘gpu’

Parameters:

• __input_0¶ (TensorList) – Input to the operator.
• __input_1¶ (TensorList) – Input to the operator.

Keyword Arguments:

• anchors¶ (float or list of float) – Anchors to be used for encoding, as the list of floats is in the ltrbformat.
• bytes_per_sample_hint¶ (int or list of int, optional, default = [0]) –
  Output size hint, in bytes per sample.
  If specified, the operator’s outputs residing in GPU or page-locked host memory will be preallocated to accommodate a batch of samples of this size.
• criteria¶ (float, optional, default = 0.5) –
  Threshold IoU for matching bounding boxes with anchors.
  The value needs to be between 0 and 1.
• means¶ (float or list of float, optional, default = [0.0, 0.0, 0.0, 0.0]) – [x y w h] mean values for normalization.
• offset¶ (bool, optional, default = False) – Returns normalized offsets ((encoded_bboxes*scale - anchors*scale) - mean) / stdsin EncodedBBoxes that use std and the mean and scale arguments.
• preserve¶ (bool, optional, default = False) – Prevents the operator from being removed from the graph even if its outputs are not used.
• scale¶ (float, optional, default = 1.0) – Rescales the box and anchor values before the offset is calculated (for example, to return to the absolute values).
• stds¶ (float or list of float, optional, default = [1.0, 1.0, 1.0, 1.0]) – [x y w h] standard deviations for offset normalization.