* @brief Moments return moments; * @param _moments * @return moments */

where does the col at block-col r starts?

* return the workspace for a vertex in an edge */

* @brief BoundingBox * @return the boundingBox */

* @brief FilledImage * @return the image where region is white and others are black */

mode: Either "training" or "inference" config: A Sub-class of the Config class model_dir: Directory to save training logs and

* tests whether there is a NaN in the array */

conv_block is the block that has a conv layer at shortcut # Arguments input_tensor: input tensor kernel_size: defualt 3, the kerne

returns the level of the edge

Load a subset of the COCO dataset. dataset_dir: The root directory of the COCO dataset. subset: What to load (train, val, minival, val

* @brief Area * @return return area */

Runs the detection pipeline. images: List of images, potentially of different sizes. Returns a list of dicts, one dict per image. Th

Display Configuration values.

* override in your class if it's possible to initialize the vertices in certain combinations. * The return value may correspond to the cost f

Modified version of the correspoding Keras function with the addition of multi-GPU support and the ability to exclude some layers from

the optimizer (graph) on which the solver works

Prepares the Dataset class for use. TODO: class map is not supported yet. When done, it should handle mapping classes from diff

* calculate the robust information matrix by updating the information matrix of the error */

rows of the matrix

set the row of this vertex in the Hessian

true => this node should be marginalized out during the optimization

Train the model. train_dataset, val_dataset: Training and validation Dataset objects. learning_rate: The learning rate to train with

* @brief ConvexHull * @return return the convex hull */