Returns inverse of rotation

* @brief Perimeter * @return return the perimeter */

Convert annotation which can be polygons, uncompressed RLE, or RLE to binary mask. :return: binary mask (numpy 2D array)

Convert annotation which can be polygons, uncompressed RLE to RLE. :return: binary mask (numpy 2D array)

Applies the given deltas to the given boxes. boxes: [N, 4] where each row is y1, x1, y2, x2 deltas: [N, 4] where each row is [dy, dx, log(dh),

Picks different number of values from each row in x depending on the values in counts.

Build Mask R-CNN architecture. input_shape: The shape of the input image. mode: Either "training" or "inference". The inputs a

Arrange resutls to match COCO specs in http://cocodataset.org/#format

Generate targets for training Stage 2 classifier and mask heads. This is not used in normal training. It's useful for debugging or to train th

Builds a Keras model of the Region Proposal Network. It wraps the RPN graph so it can be used multiple times with shared weights. anchors

Given the anchors and GT boxes, compute overlaps and identify positive anchors and deltas to refine them to match their corresponding GT boxes.

boxes: [N, 4] each row is y1, x1, y2, x2 window: [4] in the form y1, x1, y2, x2

window: (y1, x1, y2, x2). The window in the image we want to clip to. boxes: [N, (y1, x1, y2, x2)]

get the row of this vertex in the Hessian

Generates detection targets for one image. Subsamples proposals and generates target class IDs, bounding box deltas, and masks for each. Inpu

Runs official COCO evaluation. dataset: A Dataset object with valiadtion data eval_type: "bbox" or "segm" for bounding box or segmentation eva

Finds the last checkpoint file of the last trained model in the model directory. Returns: log_dir: The directory where eve

If a layer is encapsulated by another layer, this function digs through the encapsulation and returns the layer that holds the weights

scales: 1D array of anchor sizes in pixels. Example: [32, 64, 128] ratios: 1D array of anchor ratios of width/height. Example: [0.5, 1, 2]

Generates ROI proposals similar to what a region proposal network would generate. image_shape: [Height, Width, Depth] count: Number of RO

* Returns the branching factor of the tree (k) * @return k */

* Returns the depth levels of the tree (L) * @return L */

* Returns the scoring method * @return scoring method */

* Returns the weighting method * @return weighting method */

Downloads ImageNet trained weights from Keras. Returns path to weights file.

Map an internal class ID to the corresponding class ID in the source dataset.

* return the current time in seconds since 1. Jan 1970 */

Load and return ground truth data for an image (image, mask, bounding boxes). augment: If true, apply random image augmentation. Currently, only

Load instance masks for the given image. Different datasets use different ways to store masks. Override this method to load instance

Implementatin of Log2. TF doesn't have a native implemenation.

Takes a source class ID and returns the int class ID assigned to it. For example: dataset.map_source_class_id("coco.12") -> 23

Loss for Mask R-CNN bounding box refinement. target_bbox: [batch, num_rois, (dy, dx, log(dh), log(dw))] target_class_ids: [batch, num_rois].

Loss for the classifier head of Mask RCNN. target_class_ids: [batch, num_rois]. Integer class IDs. Uses zero padding to fill in the array