Group keys based on common prefixes. A prefix is the string up to the final "." in each key. Args: keys (list[str]): list of par

Format a group of parameter name suffixes into a loggable string. Args: group (list[str]): list of parameter name suffixes. Ret

A context which ignores CUDA OOM exception from pytorch.

function used for multiscale test, will be refactor in the future. The same input with `forward` function.

Load a json file with COCO's instances annotation format. Currently supports instance detection, instance segmentation, and p

Load a checkpoint file. Can be overwritten by subclasses to support different formats. Args: f (str): a locally m

Load weights from a checkpoint. Args: checkpoint (Any): checkpoint contains the weights.

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

Returns: Tensor: A Tensors of predicted class-specific or class-agnostic boxes for all images in a batch. Element

Print evaluation results in the form of a string table. Args: pq_res (dict): a dictionary containing the evaluation results. Re

Calculate random scaling factor. Args: upper_bound (float): range of the random scale. Returns: rand

Open a context where one head in `model.roi_heads` is temporarily turned off. Args: attr (str): the attribute in `model.r

Computes the precision@k for the specified values of k

Match names between the two state-dict, and update the values of model_state_dict in-place with copies of the matched tensor in ckpt_state_di

Calculate the Intersection of Unions (IoUs) between bounding boxes. IoU is calculated as a ratio of area of the intersection and area of the u

Create evaluator(s) for a given dataset. This uses the special metadata "evaluator_type" associated with each builtin dataset. For your o

Build a LR scheduler from config.

Create a MobileNetV2 instance from config. Returns: MobileNetV2: a :class:`MobileNetV2` instance.

Create a ShuffleNetV2 instance from config. Returns: ShuffleNetV2: a :class:`ShuffleNetV2` instance.

Returns: iterable It now calls :func:`cvpods.data.build_train_loader`. Overwrite it if you'd like a different da

wrapper of caching file logic for s3/http/https protocols in megfile

We estimate uncerainty as L1 distance between 0.0 and the logit prediction in 'logits' for the foreground class in `classes`. Args:

match the detection results with the groundtruth in the whole database

Convert a dataset in cvpods's standard format into COCO json format COCO data format description can be found here: http://cocodataset.or

create a table with given header. Args: header_dict (dict): headers (list): min_cols (int): Returns: st

Download a file from a given URL to a directory. If file exists, will not overwrite the existing file. Args: url (str):

Draw annotations/segmentaions in cvpods Dataset format. Args: dic (dict): annotation/segmentation data of one image, in

Draw instance-level prediction results on an image. Args: predictions (Instances): the output of an instance detection/s

Args: segment: numpy array of shape Nx2, containing all the points in the polygon. color: color of the polygon. Refer

Draw semantic segmentation predictions/labels. Args: sem_seg (Tensor or ndarray): the segmentation of shape (H, W).

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

Single-image inference. Return bounding-box detection results by thresholding on scores and applying non-maximum suppression (NMS). Args

Filter out images with too few number of keypoints. Args: dataset_dicts (list[dict]): annotations in cvpods Dataset format. Ret

filter all zeros data.

For each feature map, select the `pre_nms_topk` highest scoring proposals, apply NMS, clip proposals, and remove small boxes. Return the `pos

Args: input: NCHW images rois: Bx6 boxes. First column is the index into N. The other 5 columns are (

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

Use the given boxes in `instances` to produce other (non-box) per-ROI outputs. This is useful for downstream tasks where a box is kn

This method return a handle that counts the number of activation from the output shape for the specified operation. Args: op_nam

Given a model, the inputs and the handles for each operation, return the results for the model analysis. Args: model (nn.Module)

Get a logging-friendly message to report parameter names (keys) that are in the model but not found in a checkpoint. Args: keys

Find `num_points` most uncertain points from `uncertainty_map` grid. Args: uncertainty_map (Tensor): A tensor of shape (N, 1, H, W)

Sample points in [0, 1] x [0, 1] coordinate space based on their uncertainty. The unceratinties are calculated for each point using 'unce

Get a logging-friendly message to report parameter names (keys) that are in the checkpoint but not found in the model. Args: key

Returns: dict[name -> HistoryBuffer]: the HistoryBuffer for all scalars

Args: score_thresh (float): same as fast_rcnn_inference. nms_thresh (float): same as fast_rcnn_inference.

Arguments: box_cls, box_delta, box_center: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]):

Arguments: box_cls, box_delta, box_center: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]):

Args: conf_pred, loc_pred: Same as the output of :meth:`SSDHead.forward` shape = [N, Hi x Wi x D, 4] and [N, Hi x

Arguments: box_cls, box_delta: Same as the output of :meth:`RetinaNetHead.forward` anchors (list[list[Boxes]]): a lis

Args: box_size (height, width): Size of the reference box. boundary_threshold (int): Boxes that extend beyond the ref

Dump an "Instances" object to a COCO-format json that's used for evaluation. Args: instances (Instances): img_id (int): the i

The inverse is to rotate it back with expand, and crop to get the original shape.

Checks if the resource at the given URI is a directory. Args: path (str): A URI supported by this PathHandler R

Similar to :meth:`latest`, but the returned values are either the un-smoothed original latest value, or a median of the given