Adds a tf.summary.image for a CDF plot of the values. Normalizes `values` such that they sum to 1, plots the cumulative distribution function and

Adds a tf.summary.image for a CDF plot of the values. Normalizes `values` such that they sum to 1, plots the cumulative distribution function and

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

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

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_key: A unique string/integer identifier for the image. gro

Numpy function to plot CDF.

Numpy function to plot CDF.

Change coordinate frame of the boxlist to be relative to window's frame. Given a window of the form [ymin, xmin, ymax, xmax], changes bounding bo

Clears the state to prepare for a fresh evaluation.

Clip bounding boxes to a window. This op clips input bounding boxes (represented by bounding box corners) to a window, optionally filtering out b

Returns a list containing static and dynamic values for the dimensions. Returns a list of static and dynamic values for shape dimensions. This is

Compute Average Precision according to the definition in VOCdevkit. Precision is modified to ensure that it does not decrease as recall decrease.

Compute CorLoc according to the definition in the following paper. https://www.robots.ox.ac.uk/~vgg/rg/papers/deselaers-eccv10.pdf Returns nans

Compute precision and recall. Args: scores: A float numpy array representing detection score labels: A boolean numpy array representing tru

Cosine decay schedule with warm up period. Cosine annealing learning rate as described in: Loshchilov and Hutter, SGDR: Stochastic Gradient Des

Reads a label map and returns a category index. Args: label_map_path: Path to `StringIntLabelMap` proto text file. Returns: A category i

Creates a category index with a single `object` class.

Creates pyramid image. Useful for testing. For example, pyramid_image(5, 6, 1) looks like: # [[[ 5. 4. 3. 2. 1. 0.] # [ 6. 5. 4. 3.

Creates a pipeline_pb2.TrainEvalPipelineConfig from configs dictionary. This function nearly performs the inverse operation of get_configs_from_p

Creates random bounding boxes of specific maximum height and width. Args: num_boxes: number of boxes. max_height: maximum height of boxes.

Converts bounding boxes from dense to sparse form. Args: dense_locations: a [max_num_boxes, 4] tensor in which only the first k rows are

Draws bounding boxes on image (numpy array). Args: image: a numpy array object. boxes: a 2 dimensional numpy array of [N, 4]: (ymin, xmin,

Draws bounding boxes on image (numpy array). Args: image: a numpy array object. boxes: a 2 dimensional numpy array of [N, 4]: (ymin, xmin,

Draws bounding boxes on batch of image tensors. Args: images: A 4D uint8 image tensor of shape [N, H, W, C]. boxes: [N, max_detections, 4]

Draws bounding boxes on batch of image tensors. Args: images: A 4D uint8 image tensor of shape [N, H, W, C]. boxes: [N, max_detections, 4]

Draws boxes on image.

Draws boxes on image.

Encodes a numpy array into a PNG string. Args: image: a numpy array with shape [height, width, 3]. Returns: PNG encoded image string.

Encodes a numpy array into a PNG string. Args: image: a numpy array with shape [height, width, 3]. Returns: PNG encoded image string.

Compute evaluation result. Returns: A dictionary of metrics with the following fields - 1. summary_metrics: 'Precision/mAP@<

Compute evaluation result. Returns: A named tuple with the following fields - average_precision: float numpy array of average preci

Exponential decay schedule with burn-in period. In this schedule, learning rate is fixed at burnin_learning_rate for a fixed period, before trans

Filters out groundtruth with boxes corresponding to crowd. Args: tensor_dict: a dictionary of following groundtruth tensors - fields.Inpu

Filters out groundtruth with no bounding boxes. Args: tensor_dict: a dictionary of following groundtruth tensors - fields.InputDataFields

Freeze gradients whose variable names match a regular expression. Args: grads_and_vars: A list of gradient to variable pairs (tuples). rege

Returns batch size from the tensor shape. Args: tensor_shape: A rank 4 TensorShape. Returns: An integer representing the batch size of t

Reads training configuration from multiple config files. Args: model_config_path: Path to model_pb2.DetectionModel. train_config_path: Path

Reads configuration from a pipeline_pb2.TrainEvalPipelineConfig. Args: pipeline_config_path: Path to pipeline_pb2.TrainEvalPipelineConfig text

Returns depth from the tensor shape. Args: tensor_shape: A rank 4 TensorShape. Returns: An integer representing the depth of the tensor.

Returns height from the tensor shape. Args: tensor_shape: A rank 4 TensorShape. Returns: An integer representing the height of the tenso

Reads a label map and returns a dictionary of label names to id. Args: label_map_path: path to label_map. use_display_name: whether to use

Returns the number of classes for a detection model. Args: model_config: A model_pb2.DetectionModel. Returns: Number of classes. Rais

Returns the subset of variables available in the checkpoint. Inspects given checkpoint and returns the subset of variables that are available in

Returns width from the tensor shape. Args: tensor_shape: A rank 4 TensorShape. Returns: An integer representing the width of the tensor.

Creates dense vector with indices set to specific value and rest to zeros. This function exists because it is unclear if it is safe to use tf.s

Compute pairwise intersection areas between boxes. Args: boxlist1: BoxList holding N boxes boxlist2: BoxList holding M boxes Returns:

Computes pairwise intersection-over-area between box collections. Intersection-over-area (ioa) between two boxes box1 and box2 is defined as thei

Computes pairwise intersection-over-union between box collections. Args: boxes1: a numpy array with shape [N, 4] holding N boxes. boxes2: a

Computes pairwise intersection-over-union between box collections. Args: boxlist1: BoxList holding N boxes boxlist2: BoxList holding M boxe

Loads categories from a csv file. The CSV file should have one comma delimited numeric category id and string category name pair per line. For ex

Manually stepped learning rate schedule. This function provides fine grained control over learning rates. One must specify a sequence of learnin

Merges boxes with same coordinates and returns K-hot encoded classes. Args: boxes: A tf.float32 tensor with shape [N, 4] holding N boxes. c

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

Python function to merge numpy boxes.

Tiles the contents of x and y into a pair of grids. Multidimensional analog of numpy.meshgrid, giving the same behavior if x and y are vectors. G

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

Multiply gradients whose variable names match a regular expression. Args: grads_and_vars: A list of gradient to variable pairs (tuples). re

L2 normalizes the inputs across the specified dimension to a target norm. This op implements the L2 Normalization layer introduced in Liu, Wei, e

Converts a batch of boxes from normal to image coordinates. Args: normalized_boxes: a float32 tensor of shape [None, num_boxes, 4] in nor

Pad or clip the input tensor along the first dimension. Args: t: the input tensor, assuming the rank is at least 1. length: a tensor of sha

Returns the tensor zero padded to the specified multiple. Appends 0s to the end of the first and second dimension (height and width) of the tenso

Returns a zero padded one-hot tensor. This function converts a sparse representation of indices (e.g., [4]) to a zero padded one-hot representati

Position-sensitive crop and pool rectangular regions from a feature grid. The output crops are split into `spatial_bins_y` vertical bins and `spa

Prunes the boxes in boxlist1 that overlap less than thresh with boxlist2. For each box in boxlist1, we want its IOA to be more than minoverlap with

Prunes bounding boxes that fall outside a given window. This function prunes bounding boxes that even partially fall outside the given window. Se

Read list of training or validation examples. The file is assumed to contain a single example per line where the first token in the line is an id

Recursively parses XML contents to python dict. We assume that `object` tags are the only ones that can appear multiple times at the same level o

Transforms the box masks back to full image masks. Embeds masks in bounding boxes of larger masks whose shapes correspond to image shape. Args

Replaces nan label scores with 1.0. Args: label_scores: a tensor containing object annoation label scores. Returns: a tensor where NaN l

Retains only groundtruth with positive class ids. Args: tensor_dict: a dictionary of following groundtruth tensors - fields.InputDataFiel

Saves categories to a csv file. Args: categories: A list of dictionaries representing categories to save to file. Each category

Saves an image (represented as a numpy array) to PNG. Args: image: a numpy array with shape [height, width, 3]. output_path: path to which

Saves an image (represented as a numpy array) to PNG. Args: image: a numpy array with shape [height, width, 3]. output_path: path to which

Tests new learning rates for Adam Optimizer.