Tensorflow Example int64 parser.

Tensorflow Example bounding box parser.

Internal implementation of Pascal object detection metrics.

Performs metric computation for the VRD task. This class is internal.

An ItemHandler that tries two ItemHandlers in order.

Fake feature extracture to use in tests.

Tensorflow Example float parser.

An ItemHandler that returns a parsed Tensor, the result of a lookup.

Class to store results from the matcher. This class is used to store the results from the matcher. It provides convenient methods to query the ma

Sets up a simple 2x2 anchor grid on the unit square.

Test BoxCoder that encodes/decodes using the multiply-by-two function.

Generate a grid of anchors for multiple CNN layers.

Main class to perform labels hierachical expansion.

Tensorflow Example string parser.

Target assigner to compute classification and regression targets.

A dummy class that does not push any scope.

Abstract base class for anchor generators.

Matcher based on highest value. This class computes matches from a similarity matrix. Each column is matched to a single row. To support objec

Subsamples minibatches to a desired balance of positives and negatives.

BatchQueue class. This class creates a batch queue to asynchronously enqueue tensors_dict. It also adds a FIFO prefetcher so that the batches are

Bootstrapped sigmoid cross entropy classification loss function. This loss uses a convex combination of training labels and the current model's p

Abstract base class for box coder.

Box collection. BoxList represents a list of bounding boxes as numpy array, where each bounding box is represented as a row of 4 numbers, [y_mi

Box collection.

Naming conventions for BoxLists. Attributes: boxes: bounding box coordinates. classes: classes per bounding box. scores: scores per bou

Tests for common bounding box operations.

Tests for BoxList class.

Convenience wrapper for BoxList with masks. BoxMaskList extends the np_box_list.BoxList to contain masks as well. In particular, its constructor

BoxPredictor.

Wrapper for the pycocotools COCOeval class. To evaluate, create two objects (groundtruth_dict and detections_list) using the conventions listed a

Wrapper for the pycocotools COCO class.

Class to evaluate COCO detection metrics.

Class to evaluate COCO detection metrics.

Convolutional Box Predictor. Optionally add an intermediate 1x1 convolutional layer after features and predict in parallel branches box_encodings

Interface for data decoders.

Interface for object detection evalution classes. Example usage of the Evaluator: ------------------------------ evaluator = DetectionEvaluator

Abstract base class for detection models.

Naming conventions for storing the output of the detector. Attributes: source_id: source of the original image. key: unique key correspondi

Embedded-friendly SSD Feature Extractor using MobilenetV1 features. This feature extractor is similar to SSD MobileNetV1 feature extractor, and i

A simple (and poor) DetectionModel for use in test.

Faster R-CNN Feature Extractor definition.

Faster R-CNN with Inception Resnet v2 feature extractor implementation.

Faster R-CNN Inception V2 feature extractor implementation.

Faster R-CNN Meta-architecture definition.

Base class to test Faster R-CNN and R-FCN meta architectures.

Faster R-CNN Mobilenet V1 feature extractor implementation.

Faster R-CNN with NASNet-A feature extractor implementation.

Faster R-CNN with PNASNet feature extractor implementation.

Faster R-CNN Resnet 101 feature extractor implementation.