Creates the matcher Params: cost_class: This is the relative weight of the classification error in the matching cost

Initializes the model. Parameters: backbone: torch module of the backbone to be used. See backbone.py transformer: to

Parameters: is_thing_map: This is a whose keys are the class ids, and the values a boolean indicating whether

Initializes the model. Parameters: backbone: torch module of the backbone to be used. See backbone.py transformer: to

Create the criterion. Parameters: num_classes: number of object categories, omitting the special no-object category m

Performs the matching Params: outputs: This is a dict that contains at least these entries: "pred_logits": Tens

 The forward expects a NestedTensor samples and patches Tensor. samples consists of: - samples.tensor: batched images, of s

This function computes the panoptic prediction from the model's predictions. Parameters: outputs: This is a dict coming directly

 The forward expects a NestedTensor, which consists of: - samples.tensor: batched images, of shape [batch_size x 3 x H x W]

This performs the loss computation. Parameters: outputs: dict of tensors, see the output specification of the model for the form

Perform the computation Parameters: outputs: raw outputs of the model target_sizes: tensor of dimension [batch_size x

supports both NestedTensor and torch.Tensor

supports both NestedTensor and torch.Tensor

Compute the losses related to the bounding boxes, the L1 regression loss and the GIoU loss targets dicts must contain the key "boxes" conta

Compute the cardinality error, ie the absolute error in the number of predicted non-empty boxes This is not really a loss, it is intended for

Compute the mse loss between normalized features.

Classification loss (NLL) targets dicts must contain the key "labels" containing a tensor of dim [nb_target_boxes]

Compute the losses related to the masks: the focal loss and the dice loss. targets dicts must contain the key "masks" containing a tensor o

Function to plot specific fields from training log(s). Plots both training and test results. :: Inputs - logs = list containing Path objects

Args: input_dict (dict): all the values will be reduced average (bool): whether to do average or sum Reduce the values in the

Warning: does not synchronize the deque!