heat: batchsize x channels x h x w

heat: batchsize x channels x h x w

Apply the given mask to the image.

:param emb: [H, W] :param semantic_mask: [H, W] :return:

As some brick types are visually indistinguiable, map them to a uniform brick_type.

compute optical flow color map :param u: horizontal optical flow :param v: vertical optical flow :return:

Finds matches between prediction and ground truth instances. Returns: gt_match: 1-D array. For each GT box it has the index of the matched

Computes IoU overlaps between two sets of masks. masks1, masks2: [Height, Width, instances]

:param bid: :param rot: :param op_type: :param xs: list :param zs: list :param xz_type: 'pos' or 'top_center', showing whethe

Display current results on visdom; save current results to an HTML file. Parameters: visuals (OrderedDict) - - dictionary of imag

Display the given set of images, optionally with titles. images: list or array of image tensors in HWC format. titles: optional. A list of tit

boxes: [num_instance, (y1, x1, y2, x2, class_id)] in image coordinates. masks: [height, width, num_instances] class_ids: [num_instances]

Display values in a table format. table: an iterable of rows, and each row is an iterable of values.

Run per image evaluation on given images and store results (a list of dict) in self.evalImgs :return: None

Run forward pass; called by both functions <optimize_parameters> and <test>.

Initialize our parser with basic options(only once). Add additional model-specific and dataset-specific options. These options are def

:param bid: brick type. :param extra_point: If extra_point and extra_point_value are set, the corresponding position in the voxel will be

Check valid rotations by rotation occupancy grid

.. warning:: In distributed mode, calling the :meth:`set_epoch` method at the beginning of each epoch **before** creating the :c

Return the directory that stores images

return the occ that are applied with rotation transform

Initialize network weights. Parameters: net (network) -- network to be initialized init_type (str) -- the name of an initializa

Define the common options that are used in both training and test.

Load result file and return a result api object. Args: self (obj): coco object with ground truth annotations resFile (str): f

Load all the networks from the disk. Parameters: epoch (int) -- current epoch; used in the file name '%s_net_%s.pth' % (epoch, na

Generate color wheel according Middlebury color code :return: Color wheel

Args: fn: template: WARNINGS: 'Any' cannot be a list *list_of_nested_list: list_of_nested_list[0], list_of_n

:param mask_gt: [H, W] :param mask_pred: [H, W] :return: mask_pred with reordered indices to that match gt mask

Calculate losses, gradients, and update network weights; called in every training iteration

display the current losses on visdom display: dictionary of error labels and values Parameters: epoch (int) -- current