Compute mean,recall and decay from per-frame evaluation. Calculates precision/recall for boundaries between foreground_mask and gt_mask u

Compute region similarity as the Jaccard Index. Arguments: annotation (ndarray): binary annotation map. segmentation (ndarray

Compute mean,recall and decay from per-frame evaluation. Arguments: per_frame_values (ndarray): per-frame evaluation Returns:

The default image loader, reads the image from the given path. It first tries to use the jpeg4py_loader, but reverts to the opencv_loader if the f

:param tracks: list[STrack] :param detections: list[BaseTrack] :param metric: :return: cost_matrix np.ndarray

Evaluate CLEAR MOT results for each class.

Run per image evaluation on given images and store results in self.evalImgs_cpp, a datastructure that isn't readable from Python but

VOC average precision (AP) Evaluation. Iterate inference on the test dataset and the results are evaluated by COCO API. NOTE

COCO average precision (AP) Evaluation. Iterate inference on the test dataset and the results are evaluated by COCO API. NOT

COCO average precision (AP) Evaluation. Iterate inference on the test dataset and the results are evaluated by COCO API. NOT

COCO average precision (AP) Evaluation. Iterate inference on the test dataset and the results are evaluated by COCO API. NOT

output: (N, 5+class) shape

Forward function. Args: pred (torch.Tensor): The prediction. target (torch.Tensor): The learning target of the predic

masks: (bs, M, H//4, W//4)

mask_in: propagated masks mode should be "sot" or "mot"

:param feat: (H1W1+H2W2, bs, C) :param mask: (bs, H1W1+H2W2) :param pos_embed: (H1W1+H2W2, bs, C) :param return_inte

mask_in: propagated masks mode should be "sot" or "mot" return_det: whether to return detection results during training

bs: batch size, dh: destination h, dw: destination w

:param query (N, Length_{query}, C) :param reference_points (N, Length_{query}, n_levels, 2), range

Forward function. Args: x: input features with shape of (num_windows*B, N, C) mask: (0/-inf) mask with shape of (num

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

Forward function.

Forward function.

Args: inputs: input images. return_base_feat: whether to return the original backbone feature Returns:

gt_bitmasks_full: (bs, M, H, W), gt_classes: (bs, M)

Get a parameter value with the given name. If it does not exists, it return the default value given as a second argument or returns an error i

Object bounding boxes, grouped by object

Get a yacs CfgNode object with default values.