Change the device of the data inplace. Example: >>> self = SamplingResult.random() >>> print(f'self = {self.to(None)}

Load checkpoint from a file or URI. Args: model (Module): Module to load checkpoint. filename (str): Accept local filepath, URL,

Add prefix for dict. Args: inputs (dict): The input dict with str keys. prefix (str): The prefix to add. Returns: d

Load checkpoint from a file or URI. Args: model (Module): Module to load checkpoint. filename (str): Accept local filepath, URL,

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

Apply function to a list of arguments. Note: This function applies the ``func`` to multiple inputs and map the multiple outputs o

Build Match Cost.

Encode images with backbone and decode into a semantic segmentation map of the same size as input.

Encode images with backbone and decode into a semantic segmentation map of the same size as input.

Forward function for training. Args: img (Tensor): Input images. img_metas (list[dict]): List of image info dict wher

Forward function for training. Args: img (Tensor): Input images. img_metas (list[dict]): List of image info dict wher

Inference with slide/whole style. Args: img (Tensor): The input image of shape (N, 3, H, W). img_meta (dict): Image i

Inference with slide/whole style. Args: img (Tensor): The input image of shape (N, 3, H, W). img_meta (dict): Image i

Assign boxes to either a ground truth boxes or a negative boxes.

Build Assigner.

Extract features from images.

Extract features from images.

Forward function for `FFN`. The function would add x to the output tensor if residue is None.

Forward for head part which is called after every decoder layer. Args: decoder_out (Tensor): in shape (num_queries, batch_size, c

Test segment without test-time aumengtation. Only the output of last decoder layers was used. Args: inputs (list[Tensor]

Initialize the weights in backbone. Args: pretrained (str, optional): Path to pre-trained weights. Defaults to No

Initialize the weights in backbone. Args: pretrained (str, optional): Path to pre-trained weights. Defaults to No

Inverse function of sigmoid. Args: x (Tensor): The tensor to do the inverse. eps (float): EPS avoid numerical

Load state_dict to a module. This method is modified from :meth:`torch.nn.Module.load_state_dict`. Default value for ``strict`` is set to ``F

Load state_dict to a module. This method is modified from :meth:`torch.nn.Module.load_state_dict`. Default value for ``strict`` is set to ``F

Randomly sample an img_scale when ``multiscale_mode=='range'``. Args: img_scales (list[tuple]): Images scale range for sampling.

Obtain the mean of tensor on different GPUs.

Sample positive and negative bboxes. This is a simple implementation of bbox sampling given candidates, assigning results and ground

Generate grid Points of a single level. Note: This function is usually called by method ``self.grid_priors``. Args:

Run forward function and calculate loss for auxiliary head in training.

Run forward function and calculate loss for auxiliary head in training.

Args: cls_pred (Tensor): The prediction with shape (num_query, 1, *) or (num_query, *). gt_labels (Te

Run forward function and calculate loss for decode head in inference.

Run forward function and calculate loss for decode head in inference.

Run forward function and calculate loss for decode head in training.

Run forward function and calculate loss for decode head in training.

Expand onehot labels to match the size of prediction.

Return a process group based on gloo backend, containing all the ranks The result is cached.

Initialize ``auxiliary_head``

Initialize ``auxiliary_head``

Initialize ``decode_head``

Initialize ``decode_head``

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Pad images according to ``self.size``.

Pad masks according to ``results['pad_shape']``.

Randomly sample an img_scale according to ``ratio_range`` and ``multiscale_mode``. If ``ratio_range`` is specified, a ratio will be s

Resize images with ``results['scale']``.

Resize semantic segmentation map with ``results['scale']``.

Sample negative samples.

Sample positive samples.

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modul

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modul

Args: mask_preds (Tensor): Mask prediction in shape (N1, H, W). gt_masks (Tensor): Ground truth in shape (N2, H, W)