Add a list of new tokens to the tokenizer class. If the new tokens are not in the vocabulary, they are added to it with indices start

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

Prepares a sequence of input id, or a pair of sequences of inputs ids so that it can be used by the model. It adds special tokens, tr

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

Generates all tokens in the Trie starting from a given node. Args: node (dict): The node in the Trie from which tokens n

Build :obj:`ConcatDataset by.

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

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.

Retrieves the node corresponding to the given token in the Trie. Args: token (str): The token for which the correspondin

https://github.com/pytorch/pytorch/blob/db2a237763eb8693a20788be94f8c192e762baa8/torch/nn/functional.py#L4726

Initialize ``auxiliary_head``

Initialize ``decode_head``

Check and initialize input transforms. The in_channels, in_index and input_transform must match. Specifically, when input_transform i

Make stem layer for ResNet.

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

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

Positioning embeding method. Resize the pos_embed, if the input image size doesn't match the training size. Args:

Creates a non-causal 4D mask of shape `(batch_size, 1, query_length, key_value_length)` from a 2D mask of shape `(batch_size, key_value_lengt

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.

Converts a string into a sequence of tokens (string), using the tokenizer. Split in words for word-based vocabulary or sub-words for

Placeholder for augmentation test.

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

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

Brightness distortion.

Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens

Build pixel sampler for segmentation map.

CAM feature classification.

Returns canonicalized `text` (puncuation removed). Args: text (`str`): String to be canonicalized. ke

Copy/paste/tweak model's weights to our SigLIP structure.

Convert applicable model parameters to low-precision (bf16 or fp16)

Calculate dice loss, which is proposed in `V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation <https://arxiv

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