iterator support

Performs a single optimization step. Arguments: closure (callable, optional): A closure that reevaluates the model

This method has no effects in this class, but raises an exception if the expected size does not match */

Args: - dataset_name: str Returns: - list of strings, representing class names

removes reparameterization and backward hook (does not remove forward hook)

Get the mapping stored in our `names.txt` file that maps a class name to a data loader class index. Args: - dataset_name Returns: - data

Performs a single optimization step. Arguments: closure (callable, optional): A closure that reevaluates the model

Resize an RGB image and label. Args: - img_rgb: Array of (M,N) Returns: - img_rgb_resized

* @brief Vocabulary::clear */

Will be used to obtain the unique: - filesystem parent (i.e. sequence ID), - image ID - segment ID to overwrite this mask/segment later, by m

Args: - None Returns: - u_names: universal class names

Applies reparametrization to module's `name` parameter and modifies instance attributes as appropriate. `hook_child` adds reparameter

* Returns whether the vocabulary is empty (i.e. it has not been trained) * @return true iff the vocabulary is empty */

Args: - dname: - split: e.g. 'train', 'val', 'trainval', etc. Returns: -

Returns the dim'th component of the idx'th point in the class:

Args: filepath (str): a string that contains the absolute path, including the file name, where the visualized ima

Given a grayscale image where intensities denote instance IDs (same intensity denotes belonging to same instance), convert this to an RGB image whe

Args: - dataset_name Returns: - classname_to_dataloaderid_map:

60x faster than the Matplotlib rasterizer... well done pillow! Args: - polygon: iterable e.g. [(x1,y1),(x2,y2),...] - img_h: integer represe

* Returns whether the node is a leaf node * @return true iff the node is a leaf */

Concatenate images along a horizontal axis and save them. Accept RGB images, and convert to BGR for OpenCV to save them. Args: - img_list: lis

Args: - label_mapping_dict: dictionary from int to int, from original class ID to a new class ID. This is NOT the id_to_class_name dictionary

Args: - Returns: -

cv2.RETR_CCOMP flag retrieves all the contours and arranges them to a 2-level hierarchy. External contours (boundary) of the object are placed in h

For datasets like ScanNet where image filename stem is not unique. Will not return the suffix, e.g. 'aiport_terminal/ADE_train_00000001_seg.pn

Args: boxes (Boxes, RotatedBoxes or ndarray): either a :class:`Boxes`, or an Nx4 numpy array of XYXY_ABS format f

* Empty constructors */