Check whether the sha1 hash of the file content matches the expected hash. Parameters ---------- filename : str Path to the file.

Performs all_gather operation on the provided tensors. *** Warning ***: torch.distributed.all_gather has no gradient.

Compute the DICE loss, similar to generalized IOU for masks Args: inputs: A float tensor of arbitrary shape. The pred

Filter to keep only boxes and masks with score exceeding a given threshold. This op keeps the collection of boxes and masks whose corresponding sco

Filter to keep only boxes with score exceeding a given threshold. This op keeps the collection of boxes whose corresponding scores are greater th

Generalized IoU from https://giou.stanford.edu/ The boxes should be in [x0, y0, x1, y1] format Returns a [N, M] pairwise matrix, where

Get a yacs CfgNode object with default values for your project.

Compute pairwise intersection areas between boxes. Args: boxes1: a numpy array with shape [N, 4] holding N boxes boxes2: a numpy array with

Compute pairwise intersection areas between masks. Args: masks1: a numpy array with shape [N, height, width] holding N masks. Masks value

Loads label map proto. Args: path: path to StringIntLabelMap proto text file. Returns: a StringIntLabelMapProto

Read label map and class ids.

Loss used in RetinaNet for dense detection: https://arxiv.org/abs/1708.02002. Args: inputs: A float tensor of arbitrary shape.

Sort boxes and associated fields according to a scalar field. A common use case is reordering the boxes according to descending scores. Args:

Args: x: (B, D, H, W, C) window_size (tuple[int]): window size Returns: windows: (B*num_windows, window_size*window_s

Initializes the model. Parameters: backbone: torch module of the backbone to be used. See backbone.py transformer: to

Args: med_config (str): path for the mixture of encoder-decoder model's configuration file image_size (int): input im

Labels true/false positives of detections of an image across all classes. Args: detected_boxes: A float numpy array of shape [N, 4], repres

Labels boxes detected with the same class from the same image as tp/fp. Args: detected_boxes: A numpy array of shape [N, 4] representing de

Labels boxes detected with the same class from the same image as tp/fp. Args: detected_boxes: A numpy array of shape [N, 4] representing de

Returns numpy arrays belonging to class with index `class_index`. Args: detected_boxes: A numpy array containing detected boxes. dete

Returns numpy arrays belonging to class with index `class_index`. Args: detected_boxes: A numpy array containing detected boxes. dete

Computes overlaps and scores between detected and groudntruth boxes. Args: detected_boxes: A numpy array of shape [N, 4] representing detec

Computes overlaps and scores between detected and groudntruth boxes. Args: detected_boxes: A numpy array of shape [N, 4] representing detec

Check whether data fullfills the format of N*[ymin, xmin, ymax, xmin]. Args: data: a numpy array of shape [N, 4] representing box coordinat

Load weights from .npz checkpoints for official Google Brain Flax implementation

Removes entries with invalid boxes. A box is invalid if either its xmax is smaller than its xmin, or its ymax is smaller than its ymin.

Removes entries with invalid boxes. A box is invalid if either its xmax is smaller than its xmin, or its ymax is smaller than its ymin.

Removes entries with invalid boxes. A box is invalid if the box area is beyond the required box area. Args: detected_boxes: A float nu

Update grouth truth statitistics. 1. Difficult boxes are ignored when counting the number of ground truth instances as done in Pascal

Checks if a label map is valid. Args: label_map: StringIntLabelMap to validate. Raises: ValueError: if label map is invalid.

Computes the precision@k for the specified values of k

Computes the precision@k for the specified values of k

Performs all_gather operation on the provided tensors. Graph remains connected for backward grad computation.

Computes area of boxes. Args: boxlist: BoxList holding N boxes Returns: a numpy array with shape [N*1] representing box areas