Mask binary cross-entropy loss for the masks head. target_masks: [batch, num_rois, height, width]. A float32 tensor of values 0 or 1. Use

* normalize the angle */

Computes IoU overlaps between two sets of boxes. boxes1, boxes2: [N, (y1, x1, y2, x2)].

Parses an image info Numpy array to its components. See compose_image_meta() for more details.

Parses a tensor that contains image attributes to its components. See compose_image_meta() for more details. meta: [batch, meta length] where

Refine classified proposals and filter overlaps and return final detections. Inputs: rois: [N, (y1, x1, y2, x2)] in normalized coordi

how many rows does the block at block-row r has?

Return the RPN bounding box loss graph. config: the model config object. target_bbox: [batch, max positive anchors, (dy, dx, log(dh), log(dw)

RPN anchor classifier loss. rpn_match: [batch, anchors, 1]. Anchor match type. 1=positive, -1=negative, 0=neutral anchor. rpn_

Builds the computation graph of Region Proposal Network. feature_map: backbone features [batch, height, width, depth] anchors_per_location: n

* @brief setApprox set approx to _approx * @param _approx */

* @brief setArea set area to _area * @param _area */

* @brief setAspectRatio set aspect_ratio to _aspect_ratio * @param _aspect_ratio */

* @brief setBoundingBox set boundingBox to _boundingBox * @param _boundingBox */

* @brief setCentroid set the centroid to _centroid * @param _centroid */

* @brief setConvexArea set convex_area to _convex_area * @param _convex_area */

* @brief setConvexHull set convex_hull to _convex_hull * @param _convex_hull */

* @brief setConvexImage set convexImage to _convexImage * @param _convexImage */

* @brief setEccentricity set the eccentricity to _eccentricity * @param _eccentricity */

* @brief setEllipse set the ellipse to _ellipse * @param _ellipse */

* @brief setExtrema set extrame to _extrema * @param _extrema */

* @brief setFilledArea set filledArea to _filledArea * @param _filledArea */

* @brief setFilledImage set filledImage to _filledImage * @param _filledImage */

* @brief setMinorAxis set minoraxis_length to minor_axis * @param minor_axis */

* @brief setMaxLoc set maxloc to _maxLoc * @param _maxloc */

* @brief setMaxVal set maxval to _maxval * @param _maxval */

* @brief setMeanVal set meanval to _meanval * @param _meanval */

* @brief setMinLoc set minloc to _minloc * @param _minloc */

* @brief setMinVal set minval to _minval * @param _minval */

* @brief setMinorAxis set minoraxis_length to minor_axis * @param minor_axis */

* @brief setMoments set moments to _moments * @param _moments */

* @brief setOrientation set orientation to _orientation * @param _orientation */

* @brief setPerimeter set perimeter to _perimeter * @param _perimeter */

* @brief setPixelList set pixelList to _pixelList * @param _pixelList */

* @brief setSolidity set solidity to _solidity * @param _solidity */

Sets model layers as trainable if their names match the given regular expression.

Implements Smooth-L1 loss. y_true and y_pred are typicallly: [N, 4], but could be any shape.

* Inverts the a block pattern of A in spinv * @returns false if not defined. */

if external stop flag is given, return its state. False otherwise

Reformats the detections of one image from the format of the neural network output to a format suitable for use in the rest of the app

the user data associated with this vertex

* @brief Approx * @return the approximate hull of the contour */

* @brief AspectRatio * @return the aspect ratio of the hull */

* @brief Centroid * @return the centroid of the hull */