Convert the model into training mode while keep layers freezed.

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that

Args: cfg (CfgNode):

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

Args: cfg (CfgNode): model (DiffusionInst): a DiffusionInst to apply TTA on. tta_mapper (

Args: cfg (CfgNode): instance_mode (ColorMode): parallel (bool): whether to run the model in different pr

Execute inference on a list of inputs, using batch size = self.batch_size, instead of the length of the list. Inputs & outpu

Args: input (dict): one dataset dict with "image" field being a CHW tensor Returns: dict: one output dict

Computes the precision@k for the specified values of k

Run all_gather on arbitrary picklable data (not necessarily tensors) Args: data: any picklable object Returns: list[data]

Apply ema stored in `model` to model and returns a function to restore the weights are applied

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

simOTA for detr

:features: (torch.Size([2, 256, 208, 208]),xxx,) :param bboxes: (N, nr_boxes, 4) :param pro_features: (N, nr_boxes, d_model)

pro_features: (1, N * nr_boxes, self.d_model) roi_features: (49, N * nr_boxes, self.d_model)

Forward function. Args: x: input features with shape of (num_windows*B, N, C) mask: (0/-inf) mask with shape of (num_

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

Forward function.

Forward function.

Args: batched_inputs: a list, batched outputs of :class:`DatasetMapper` . Each item in the list contains the inpu

Equivalent to nn.functional.interpolate, but with support for empty batch sizes. This will eventually be supported natively by PyTorch, and t

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

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

Compute the bounding boxes around the provided masks The masks should be in format [N, H, W] where N is the number of masks, (H, W) are the spati

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

:param gt_boxes: (cx, cy, w, h), normalized :param num_proposals:

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!