Evaluate the coco results using COCOEval API.

Evaluate the coco results using COCOEval API.

Args: iou_type (str): max_dets_per_image (None or int): limit on maximum detections per image in evaluating AP This l

Copied from detectron2/engine/launch.py

Do a forward pass with a selected pair of meshes Args: embedder (nn.Module): module that computes vertex embeddings for d

Args: fields (dict[name: type])

Dynamically creates a new type that inherits the type of a given instance and overrides the `step` method to add gradient clipping

Statically infer the status of each blob, the status can be such as device type (CPU/GPU), layout (NCHW/NHWC), data type (float32/int8),

Get the arguments to be passed to ``aug.get_transform`` from the input ``aug_input``.

Returns metadata for "separated" version of the panoptic segmentation dataset.

Return the index list of relevant operator to produce target blob from source blob, if there's no dependency, return empty list.

Create a list of dataset indices (with repeats) to use for one epoch. Args: generator (torch.Generator): pseudo random n

Return the base directory for evolution configurations

Return the base directory for HRNet configurations

Return the base directory for quick schedules configurations

Returns: list[Tensor]: #featuremap tensors, each is (#locations x #cell_anchors) x 4

Params in the same submodule are grouped together. Args: keys: names of all parameters original_names: mapping from paramete

Turn "common1", "common2", "common3" into "common{1,2,3}"

Group elements of an iterable by chunks of size `n`, e.g. grouper(range(9), 4) -> (0, 1, 2, 3), (4, 5, 6, 7), (8, None, None, None)

Returns: list[str]: list of device for each external output

Args: input (dict): one dataset dict with "image" field being a CHW tensor Returns: dict: one output dict

Initialize confidence estimation layers based on configuration options Args: cfg (CfgNode): configuration options

Initialize confidence estimation layers based on configuration options Args: cfg (CfgNode): configuration options

If input instances don't have ID, ID_period, lost_frame_count fields, this method is used to initialize these fields. Args:

Encode keypoint locations into a target heatmap for use in SoftmaxWithLoss across space. Maps keypoints from the half-open interval [x1, x2)

Load COCO annotations from a JSON file Args: json_file: str Path to the file to load annotations from Returns:

Load COCO annotations from a JSON file Args: json_file: str Path to the file to load annotations from Returns:

Log the classification metrics to EventStorage. Args: pred_logits: Rx(K+1) logits. The last column is for background class.

Perform recursive lookup for the given type to find registered converter. If a converter was found for some base class, it ge