Adds the predicted boxes on top of the image Arguments: image (np.ndarray): an image as returned by OpenCV p

Adds detected class names and scores in the positions defined by the top-left corner of the predicted bounding box Arguments

Adds the instances contours for each predicted object. Each label has a different color. Arguments: image (np.nd

Returns BoxList from `boxes` and adds probability scores information as an extra field `boxes` has shape (#detections, 4 * #c

Given segmentation masks and the bounding boxes corresponding to the location of the masks in the image, this function crops and resizes

Reduce the loss dictionary from all processes so that process with rank 0 has the averaged results. Returns a dict with the same fields as

Only keep boxes with both sides >= min_size Arguments: boxlist (Boxlist) min_size (int)

Arguments: image (np.ndarray): an image as returned by OpenCV Returns: prediction (BoxList): the detected ob

This function gathers data from multiple processes, and returns them in a list, as they were obtained from each process. This function i

Select only predictions which have a `score` > self.confidence_threshold, and returns the predictions in descending order of score

Produce additional matches for predictions that have only low-quality matches. Specifically, for each ground-truth find the set of pr

Load custom environment setup from a Python source file and run the setup function.

Perform environment setup work. The default setup is a no-op, but this function allows the user to specify a Python source file that performs

This method performs the positive/negative sampling, and return the sampled proposals. Note: this function keeps a state.

Interface for Python

Arguments: boxlists (list[BoxList])

Args: match_quality_matrix (Tensor[float]): an MxN tensor, containing the pairwise quality between M ground-truth ele

Arguments: matched idxs: list of tensors containing -1, 0 or positive values. Each tensor corresponds to a specif

Computes the loss for Faster R-CNN. This requires that the subsample method has been called beforehand. Arguments:

Arguments: proposals (list[BoxList]) mask_logits (Tensor) targets (list[BoxList]) Return:

Arguments: anchors (list[BoxList]) objectness (list[Tensor]) box_regression (list[Tensor]) ta

Arguments: k_min (int) k_max (int) canonical_scale (int) canonical_level (int) ep

Arguments: output_size (list[tuple[int]] or list[int]): output size for the pooled region scales (list[float]): scale

Args: high_threshold (float): quality values greater than or equal to this value are candidate matches.

Arguments: batch_size_per_image (int): number of elements to be selected per image positive_fraction (float): percent

Arguments: weights (4-element tuple) bbox_xform_clip (float)

Arguments: in_channels_list (list[int]): number of channels for each feature map that will be fed out

Arguments: proposal_matcher (Matcher) fg_bg_sampler (BalancedPositiveNegativeSampler) box_coder (BoxCoder

Arguments: score_thresh (float) nms (float) detections_per_img (int) box_coder (BoxCoder)

Arguments: proposal_matcher (Matcher) discretization_size (int)

Arguments: num_classes (int): number of output classes input_size (int): number of channels of the input once it's fl

Arguments: proposal_matcher (Matcher) fg_bg_sampler (BalancedPositiveNegativeSampler) box_coder (BoxCoder

Arguments: pre_nms_top_n (int) post_nms_top_n (int) nms_thresh (float) min_size (int)