Convenience function for accessing box coordinates. Returns: a tensor with shape [N, 4] representing box coordinates.

Accesses a box collection and associated fields. This function returns specified field with object; if no field is specified, it returns the

Add field to box list. This method can be used to add related box data such as weights/labels, etc. Args: field: a string key to a

Name scope. Must be defined by implementations. Returns: a string representing the name scope of the anchor generation operation.

Encode a box list relative to an anchor collection. Args: boxes: BoxList holding N boxes to be encoded anchors: BoxList of N anchors

Constructs the graph, creates a test session and returns the results. The graph is executed either on TPU or CPU based on the `tpu_test` flag.

Input preprocessing. To be overridden by implementations. This function is responsible for any scaling/shifting of input values that is

Convenience function for accesssing box coordinates. Returns: a numpy array of shape [N, 4] representing box corners

Add data to a specified field. Args: field: a string parameter used to speficy a related field to be accessed. field_data: a numpy ar

Accesses data associated with the specified field in the box collection. Args: field: a string parameter used to speficy a related field to

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

Generates a collection of bounding boxes to be used as anchors. TODO(rathodv): remove **params from argument list and make stride and offse

Extracts first stage RPN features. This function is responsible for extracting feature maps from preprocessed images. These features are use

Decode boxes that are encoded relative to an anchor collection. Args: rel_codes: a tensor representing N relative-encoded boxes ancho

Writes a config object to disk.

Decodes serialized tensorflow example and returns a tensor dictionary. Args: tf_example_string_tensor: a string tensor holding a serialized

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

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

Helper function to assert if a proto field equals some value. Args: proto_field: The protobuf field to compare. expectation: The expe

Returns a tensor stored in preprocess_vars_cache or using generator_func. If the tensor was previously generated and appears in the PreprocessorCac

Adds a value to the dictionary. Args: function_id: identifier for the preprocessing function used. key: identifier for the variable s

Helper function to assert if a proto field equals some value. Args: proto_field: The protobuf field to compare. expectation: The expe

Provide groundtruth tensors. Args: groundtruth_boxes_list: a list of 2-D tf.float32 tensors of shape [num_boxes, 4] containing coor

Predict prediction tensors from inputs tensor. Outputs of this function can be passed to loss or postprocess functions. Args: preproce

Assign classification and regression targets to each anchor. For a given set of anchors and groundtruth detections, match anchors to groundtr

Access list of groundtruth tensors. Args: field: a string key, options are fields.BoxListFields.{boxes,classes,masks,keypoints}

Returns number of boxes held in collection. Returns: a tensor representing the number of boxes held in the collection.

Helper function to assert if a proto field equals some value. Args: proto_field: The protobuf field to compare. expectation: The expe

Computes matches among row and column indices and returns the result. Computes matches among the row and column indices based on the similarity

Return number of boxes held in collections.

Converts prediction tensors to final detections. This function converts raw predictions tensors to final detection results by slicing off the

Compute scalar loss tensors with respect to provided groundtruth. Calling this function requires that groundtruth tensors have been provided

Returns configurations for model.

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

Helper to check if two dicts with floatst or integers are close.

Return all non-box fields.

Convenience function for accessing masks. Returns: a numpy array of shape [N, height, width] representing masks

Compute evaluation result. Args: relationships: A dictionary of numerical label-text label mapping; if specified, returns per-relat

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

Computes the center coordinates, height and width of the boxes. Args: scope: name scope of the function. Returns: a list of 4 1-

Adds detections for a single image to be used for evaluation. If a detection has already been added for this image id, a warning is logged, a

Adds groundtruth for a single image to be used for evaluation. If the image has already been added, a warning is logged, and groundtruth is i

Extracts second stage box classifier features. Args: proposal_feature_maps: A 4-D float tensor with shape [batch_size * self.max_nu

Gather boxes from BoxList according to indices and return new BoxList. By default, `gather` returns boxes corresponding to the input index list, as

Returns column indices that are matched. Returns: column_indices: int32 tensor of shape [K] with column indices.

Returns number of boxes held in collection. This number is inferred at graph construction time rather than run-time. Returns: Number o

Returns column indices that are unmatched. Returns: column_indices: int32 tensor of shape [K] with column indices.

Adds detections for a single image to be used for evaluation. If a detection has already been added for this image id, a warning is logged, a

Adds groundtruth for a single image to be used for evaluation. If the image has already been added, a warning is logged, and groundtruth is i

Clears the state to prepare for a fresh evaluation.

Dequeues a batch of tensor_dict from the BatchQueue. TODO: use allow_smaller_final_batch to allow running over the whole eval set Returns:

Gathers elements from `input_tensor` based on match results. For columns that are matched to a row, gathered_tensor[col] is set to input_tens

Faster R-CNN with NAS preprocessing. Maps pixel values to the range [-1, 1]. Args: resized_inputs: A [batch, height_in, width_in, chan

Returns subsample of entries in indicator. Args: indicator: boolean tensor of shape [N] whose True entries can be sampled. batch_size

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

Constructs the graph, executes it on CPU and returns the result. Args: graph_fn: a callable that constructs the tensorflow graph to test. T

Extract features from preprocessed inputs. Args: preprocessed_inputs: a [batch, height, width, channels] float tensor representing

Gather boxes from BoxList according to indices and return new BoxList. By default, gather returns boxes corresponding to the input index list, as

Subsample indicator vector. Given a boolean indicator vector with M elements set to `True`, the function assigns all but `num_samples` of the

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