Compute intersection areas between corresponding boxes in two boxlists. Args: boxlist1: BoxList holding N boxes boxlist2: BoxList holding N

Returns row indices that match some column. The indices returned by this op are ordered so as to be in correspondence with the output of matc

Updates `configs` dictionary based on supplied parameters. This utility is for modifying specific fields in the object detection configs. Say tha

Multi-class version of non maximum suppression. This op greedily selects a subset of detection bounding boxes, pruning away boxes that have high

Defines the default arg scope for the NASNet-A Large for object detection. This provides a small edit to switch batch norm training on and off.

Non maximum suppression. This op greedily selects a subset of detection bounding boxes, pruning away boxes that have high IOU (intersection over

Non maximum suppression. This op greedily selects a subset of detection bounding boxes, pruning away boxes that have high IOU (intersection over

Non maximum suppression. This op greedily selects a subset of detection bounding boxes, pruning away boxes that have high IOU (intersection over

Returns the number of anchors per spatial location. Returns: a list of integers, one for each expected feature map to be passed to th

Pads the input tensor with 0s along the first dimension up to the length. Args: t: the input tensor, assuming the rank is at least 1. lengt

Parses input and returns a numpy array or a dictionary of numpy arrays. Args: input_data: an input data Returns: A numpy array o

Defines the default arg scope for the PNASNet Large for object detection. This provides a small edit to switch batch norm training on and off. A

Converts a dictionary with annotations for an image to tf.Example proto. Args: image_path: The complete path to image. annotations: A dicti

Randomly crops and pads the image. Given an input image and its bounding boxes, this op first randomly crops the image and then randomly pads the

Randomly crops an image to the specified aspect ratio. Randomly crops the a portion of the image such that the crop is of the specified aspect ra

Randomly jitter box. Args: box: bounding box [1, 1, 4]. ratio: max ratio between jittered box and original box, a number betwee

Randomly pads the image. This function randomly pads the image with zeros. The final size of the padded image will be between min_image_size and

Randomly zero pads an image to the specified aspect ratio. Pads the image so that the resulting image will have the specified aspect ratio withou

Reads a KITTI annotation file. Converts a KITTI annotation file into a dictionary containing all the relevant information. Args: filename:

Reads pre-computed object detections and groundtruth from tf_record. Args: input_config: input config proto of type object_detection.prot

Refines a pool of boxes using non max suppression and box voting. Args: pool_boxes: (BoxList) A collection of boxes to be refined. pool_boxes m

Replaces variable values in the checkpoint with their moving averages. If the current checkpoint has shadow variables maintaining moving averages o

Returns a map of variables to load from a foreign checkpoint. Args: first_stage_feature_extractor_scope: A scope name for the first stage

Scale box coordinates in x and y dimensions. Args: boxlist: BoxList holding N boxes y_scale: float x_scale: float Returns: boxli

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

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

Create a tiled set of anchors strided along a grid in image space. This op creates a set of anchor boxes by placing a "basis" collection of boxes

Transpose the coordinate representation in a boxlist. Args: scope: name scope of the function.

Returns column indices that are unmatched or ignored. The indices returned by this op are always sorted in increasing order. Returns:

Writes frozen graph to disk. Args: frozen_graph_path: Path to write inference graph. frozen_graph_def: tf.GraphDef holding frozen graph.

Writes the graph and the checkpoint into disk.

Write metrics to a summary directory. Args: metrics: A dictionary containing metric names and values. global_step: Global step at which the

Write metrics to the output directory. Args: metrics: A dictionary containing metric names and values. output_dir: Directory to write metri

Writes SavedModel to disk. If checkpoint_path is not None bakes the weights into the graph thereby eliminating the need of checkpoint files durin

Wrapper of json.dump that allows specifying the float precision used. Args: obj: The object to dump. fid: The file id to write to. floa

Wrapper of json.dumps that allows specifying the float precision used. Args: obj: The object to dump. float_digits: The number of digits of

Export detection annotations in numpy arrays to COCO API. This function converts a set of predicted detections represented as numpy arrays to dic

Export groundtruth detection annotations in numpy arrays to COCO API. This function converts a set of groundtruth detection annotations represented

Exports keypoints in numpy arrays to COCO API. This function converts a set of predicted keypoints represented as numpy arrays to dictionaries th

Export segmentation masks in numpy arrays to COCO API. This function converts a set of predicted instance masks represented as numpy arrays to di

Returns parameters for use with Dump and Dumps to output pretty json. Example usage: ```json_str = json_utils.Dumps(obj, **json_utils.PrettyPar

Call the loss function. Args: prediction_tensor: an N-d tensor of shape [batch, anchors, ...] representing predicted quantities.

Computes localization and classification losses after hard mining. Args: location_losses: a float tensor of shape [num_images, num_anchors]

Constructs a GridAnchorGenerator. Args: scales: a list of (float) scales, default=(0.5, 1.0, 2.0) aspect_ratios: a list of (float) as

Constructs a MultiscaleGridAnchorGenerator. To construct anchors, at multiple scale resolutions, one must provide a the minimum level and max

Constructs a MultipleGridAnchorGenerator. To construct anchors, at multiple grid resolutions, one must provide a list of feature_map_shape_li

Constructs box collection. Args: data: a numpy array of shape [N, 4] representing box coordinates Raises: ValueError: if bbox da

Constructor. Args: matching_iou_threshold: IOU threshold to use for matching groundtruth boxes to detection boxes.

Initialized PerImageVRDEvaluation by evaluation parameters. Args: matching_iou_threshold: A ratio of area intersection to union, which is

Initialized PerImageEvaluation by evaluation parameters. Args: num_groundtruth_classes: Number of ground truth object classes matchin

Constructs box collection. Args: box_data: a numpy array of shape [N, 4] representing box coordinates mask_data: a numpy array of sha

Constructor. Args: categories: A list of dicts, each of which has the following keys - 'id': (required) an integer id uniquely iden

Constructor. Args: categories: A list of dicts, each of which has the following keys - 'id': (required) an integer id uniquely iden

Constructor. Args: categories: A list of dicts, each of which has the following keys - 'id': (required) an integer id uniquely iden

Initializes the BackupHandler handler. If the first Handler's tensors_to_item returns a Tensor with no elements, the second Handler is used.

Constructor sets keys_to_features and items_to_handlers. Args: load_instance_masks: whether or not to load and handle instance masks.

COCOEvalWrapper constructor. Note that for the area-based metrics to be meaningful, detection and groundtruth boxes must be in image coordina

Constructor. Args: categories: A list of dicts, each of which has the following keys - 'id': (required) an integer id uniquely iden

Constructs a minibatch sampler.

Constructs box collection. Args: boxes: a tensor of shape [N, 4] representing box corners Raises: ValueError: if invalid dimensi

Constructor. Args: is_training: Indicates whether the BoxPredictor is in training mode. num_classes: number of classes. Note that nu

Constructor. Args: is_training: Indicates whether the BoxPredictor is in training mode. num_classes: number of classes. Note that nu

Constructor. Args: is_training: Indicates whether the BoxPredictor is in training mode. num_classes: number of classes. Note that nu

Constructor. Args: is_training: Indicates whether the BoxPredictor is in training mode. num_classes: number of classes. Note that nu

Constructs a Match object. Args: match_results: Integer tensor of shape [N] with (1) match_results[i]>=0, meaning that column i is

Constructs a Matcher. Args: use_matmul_gather: Force constructed match objects to use matrix multiplication based gather instead of

Constructor. Args: delta: delta for smooth L1 loss.

Constructor. Args: gamma: exponent of the modulating factor (1 - p_t) ^ gamma. alpha: optional alpha weighting factor to balance posi

Constructor. Args: logit_scale: When this value is high, the prediction is "diffused" and when this value is low, the pr

Constructor. Args: logit_scale: When this value is high, the target is "diffused" and when this value is low, the target

Constructor. Args: alpha: a float32 scalar tensor between 0 and 1 representing interpolation weight bootstrap_type: set to ei

Constructor. The hard example mining implemented by this class can replicate the behavior in the two aforementioned papers (Srivastava et al.