Returns a random 0-D tensor between minval and maxval. Args: minval: minimum value of the random tensor. maxval: maximum value of the rando

Computes area of boxes. Args: boxlist: BoxList holding N boxes scope: name scope. Returns: a tensor with shape [N] representing box

This function creates an image that can be used to test vis functions. It makes an image composed of four colored rectangles. Returns:

Returns path to the local pipeline config file.

Returns a map of variables to load from a foreign checkpoint. See parent class for details. Args: fine_tune_checkpoint_type: whether t

Computes matrix of pairwise similarity between BoxLists. This op (to be overriden) computes a measure of pairwise similarity between the boxe

Builds a DetectionModel based on the model config. Args: model_config: A model.proto object containing the config for the desired D

Returns a dictionary of eval metric ops to use with `tf.EstimatorSpec`. Note that once value_op is called, the detections and groundtruth added v

Returns all non-box fields (i.e., everything not named 'boxes').

Determines whether the groundtruth includes the given field. Args: field: a string key, options are fields.BoxListFields.{boxes,cla

Parses tensorflow example and returns a tensor dictionary. Args: tf_example: a tf.Example object. Returns: A dictionary of the f

Feature-extractor specific preprocessing. SSD meta architecture uses a default clip_window of [0, 0, 1, 1] during post-processing. On calling

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

Copies the extra fields of boxlist_to_copy_from to boxlist_to_copy_to. Args: boxlist_to_copy_to: BoxList to which extra fields are copied.

Returns configurations for model.

Sets the static shape of the target. Args: target: the target tensor. Its first dimension will be overwritten. num_anchors: the numbe

Set the indicated fields of x to val. Args: x: tensor. indicator: boolean with same shape as x. val: scalar with value to set.

Converts a BoxList containing 'masks' into a BoxMaskList. Args: boxlist: An np_box_list.BoxList object. Returns: An np_box_mask_list.Box

Clears the state to prepare for a fresh evaluation.

Evaluates the detection boxes and returns a dictionary of coco metrics. Returns: A dictionary holding - 1. summary_metrics: 'D

Gather boxes from np_box_mask_list.BoxMaskList according to indices. By default, gather returns boxes corresponding to the input index list, as w

Returns column indices that match to some row. The indices returned by this op are always sorted in increasing order. Returns: column_

Predicts unpostprocessed tensors from input tensor. This function takes an input batch of images and runs it through the forward pass of the

scale box coordinates in x and y dimensions. Args: boxlist: BoxList holding N boxes y_scale: (float) scalar tensor x_scale: (float) sca

Overlay labeled boxes on an image with formatted scores and label names. This function groups boxes that correspond to the same location and crea

Overlay labeled boxes on an image with formatted scores and label names. This function groups boxes that correspond to the same location and crea

Computes detection metrics. Args: include_metrics_per_category: If True, will include metrics per category. all_metrics_per_category:

Load annotations dictionary into COCO datastructure. See http://mscoco.org/dataset/#format for a description of the annotations format. As a

SSD FPN feature extractor based on Resnet v1 architecture. Args: is_training: whether the network is in training mode. depth_multipli

Constructor. Args: architecture: Architecture name of the Resnet V1 model. resnet_model: Definition of the Resnet V1 model. is_

Asserts successful updating of all learning rate schemes.

Compute CorLoc score for object detection result. Args: detected_boxes: A float numpy array of shape [N, 4], representing N regio

Create optimizer learning rate based on config. Args: learning_rate_config: A LearningRate proto message. Returns: A learning rate. R

Loads COCO annotation json files and converts to tf.Record format. Args: annotations_file: JSON file containing bounding box annotations. i

Returns a boolean indicating whether the input is a tensor. Args: t: the input to be tested. Returns: a boolean that indicates whether t

Converts first stage prediction tensors from the RPN to proposals. This function decodes the raw RPN predictions, runs non-max suppression on

Create a function to scale logits then apply a Tensorflow function.

Sets the 0-th dimension of the input tensor. Args: t: the input tensor, assuming the rank is at least 1. d0: an integer indicating the 0-th

Adds groundtruth for a single image to be used for evaluation. Args: image_id: A unique string/integer identifier for the image. grou

Adds groundtruth for a single image to be used for evaluation. Args: image_id: A unique string/integer identifier for the image. grou

Computes area of boxes. Args: boxes: Numpy array with shape [N, 4] holding N boxes Returns: a numpy array with shape [N*1] representing

Computes area of masks. Args: masks: Numpy array with shape [N, height, width] holding N masks. Masks values are of type np.uint8 and val

Retrieves specified fields as a dictionary of tensors. Args: fields: (optional) list of fields to return in the dictionary. If None

Clears the state to prepare for a fresh evaluation.

Creates a model function for `Estimator`. Args: detection_model_fn: Function that returns a `DetectionModel` instance. configs: Dictionary

Get corner coordinates of boxes. Returns: a list of 4 1-d numpy arrays [y_min, x_min, y_max, x_max]

Returns column indices that are ignored (neither Matched nor Unmatched). The indices returned by this op are always sorted in increasing order.

Retains groundtruth by valid indices. Args: tensor_dict: a dictionary of following groundtruth tensors - fields.InputDataFields.groundtru

Scales keypoint coordinates in x and y dimensions. Args: keypoints: a tensor of shape [num_instances, num_keypoints, 2] y_scale: (float) sc

Summarize the number of positives and negatives after mining.

Returns column indices that do not match any row. The indices returned by this op are always sorted in increasing order. Returns: colu

Converts a box in [ymin, xmin, ymax, xmax] format to COCO format. This is a utility function for converting from our internal [ymin, xmin, ymax,

Compresses mask using Run-length encoding provided by pycocotools. Args: masks: uint8 numpy array of shape [mask_height, mask_width] with value

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

Computes func(x, sel), with sel sampled from [0...num_cases-1]. If both preprocess_vars_cache AND key are the same between two calls, sel will be

Decodes a batch of box encodings with respect to the anchors. Args: box_encodings: A float32 tensor of shape [batch_size, num_ancho

Decodes box encodings with respect to the anchor boxes. Args: box_encodings: a 4-D tensor with shape [batch_size, num_anchors, num_

Slim arg scope for InceptionV2 batch norm.

Checks whether mask dtype is uint8 and the values are either 0 or 1.

Computes clip window for non max suppression based on image shapes. This function assumes that the clip window's left top corner is at (0, 0).

Crops to a set of proposals from the feature map for a batch of images. Helper function for self._postprocess_rpn. This function calls `tf.im

Copies the extra fields of boxlist_to_copy_from to boxlist_to_copy_to. Args: boxlist_to_copy_to: BoxList to which extra fields are copied.

Constructs a new feature extractor. Args: depth_multiplier: float depth multiplier for feature extractor pad_to_multiple: the nearest

Constructs a new feature extractor. Args: depth_multiplier: float depth multiplier for feature extractor pad_to_multiple: the nearest

Constructs a new feature extractor. Args: depth_multiplier: float depth multiplier for feature extractor pad_to_multiple: the nearest