Call `fast_rcnn_inference_single_image` for all images. Args: boxes (list[Tensor]): A list of Tensors of predicted class-specific or

Flattens predictions in the batch (binary case) Remove labels equal to 'ignore'

Implement operator-level flops counting using jit. This is a wrapper of fvcore.nn.flop_count, that supports standard detection models in

Use the given boxes in `instances` to produce other (non-box) per-ROI outputs. Args: features: same as in `forward()`

Return dict from versioned blob to list of (i, j), where i is index of consumer op, j is the index of input of that op.

Args: image_size (tuple): height, width Returns: crop_size (tuple): height, width in absolute pixels

like `get_fields` in the Instances object, but return each field in tensor representations

Return dict from versioned blob to (i, j), where i is index of producer op, j is the index of output of that op.

Return the device type ("cpu" or "gpu"/"cuda") of each (versioned) blob

Arguments: pred_logits, pred_deltas, pred_masks: Same as the output of: meth:`TensorMaskHead.forward`

Run model on the data_loader and evaluate the metrics with evaluator. Also benchmark the inference speed of `model.forward` accurately. T

Prepare some proposals to be used to train the ROI heads. It performs box matching between `proposals` and `targets`, and assigns

Computes gradient of the Lovasz extension w.r.t sorted errors See Alg. 1 in paper

Create a list of blocks just like those in a ResNet stage. Args: block_class (type): a subclass of ResNetBlockBase num_block

Convert pred_mask_logits to estimated foreground probability masks while also extracting only the masks for the predicted classes in pred_ins

Compare the "keep" result of two nms call. They are allowed to be different in terms of edit distance due to floating point precision iss

Paste a set of masks that are of a fixed resolution (e.g., 28 x 28) into an image. The location, height, and width for pasting each mask is d

Get features from feature maps in `features_list` that correspond to specific point coordinates inside each bounding box from `boxes`.

Deprecated

Print main metrics in a format similar to Detectron, so that they are easy to copypaste into a spreadsheet. Args: results (Order

Add an `img_tensor` associated with `img_name`, to be shown on tensorboard. Args: img_name (str): The name of th

Read an image into the given format. Will apply rotation and flipping if the image has such exif information. Args: file_name (s

Args: box_scores (N, 5): boxes in corner-form and probabilities. (Note here 5 == 4 + 1, i.e., 4-dim horizontal bo

Rename the op_id-th operator in predict_net, change it's output_id-th input's name to the new_name. It also does automatic re-route and c

Return semantic segmentation predictions in the original resolution. The input images are often resized when entering semantic segmentor. Mo

Convert DensePose outputs to results format. Results are more compact, but cannot be resampled any more

Args: bottom_up (Backbone): module representing the bottom up subnetwork. Must be a subclass of :class:`Backbone`

NOTE: this interface is experimental. Args: num_classes (int): number of classes. Used to label background proposals.

Args: src_rect (x0, y0, x1, y1): src coordinates output_size (h, w): dst image size interp: PIL interpola

Naive tracking heuristics to assign same color to the same instance, will update the internal state of tracked instances. Re

Calculate proper im2col step size, which should be divisible by input_size and not larger than prefer_size. Meanwhile the step size s

Derive the desired score numbers from summarized COCOeval. Args: coco_eval (None or COCOEval): None represents no predic

Forward logic of the box prediction branch. If `self.train_on_pred_boxes is True`, the function puts predicted boxes in the `prop

Args: features, targets: the same as in Same as in :meth:`ROIHeads.forward`. proposals (list[Instance

Forward logic of the densepose prediction branch. Args: features (list[Tensor]): #level input features for densepose pre

Forward logic of the coarse mask head.

Forward logic of the mask point head.

Return a process group based on gloo backend, containing all the ranks The result is cached.

Load and return the configuration from the specified file (relative to the base configuration directory)

Return the learning rate warmup factor at a specific iteration. See :paper:`in1k1h` for more details. Args: method (str): warmup

A context which ignores CUDA OOM exception from pytorch.

Randomly modifies given color to produce a slightly different color than the color given. Args: color (tuple[double]): a

Computes utility values for linear interpolation at points v. The points are given as normalized offsets in the source interval (v0_src,

Returns: list[int]: size of the tensor, on each rank Tensor: padded tensor that has the max size

Uniform float random number between low and high.

Based on the matching between N proposals and M groundtruth, sample the proposals and set their classification labels. Args:

Randomly sample a subset of positive and negative examples, and overwrite the label vector to the ignore value (-1) for all elements

Open a context where some heads in `model.roi_heads` are temporarily turned off. Args: attr (list[str]): the attribute in

Add config for additional category-related dataset options - category whitelisting - category mapping

Call `add_ground_truth_to_proposals_single_image` for all images. Args: gt_boxes(list[Boxes]): list of N elements. Element i is a Bo