Do not add eos again if user already added it.

Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.

Freeze stages param and norm stats.

Checks whether `char` is a control character.

Checks whether `char` is a punctuation character.

Checks whether `char` is a whitespace character.

Make causal mask used for bi-directional self-attention.

Update the size of the full vocabulary with the added tokens. Counts the `keys` and not the `values` because otherwise if there is a

Calculate accuracy according to the prediction and target. Args: pred (torch.Tensor): The model prediction, shape (N, num_class, ...)

Builder for attention.

Builder for feed-forward network (FFN).

Builder of box sampler.

Builder for transformer layer.

Returns list of utf-8 byte and a corresponding list of unicode strings. The reversible bpe codes work on unicode strings. This means you

Returns list of utf-8 byte and a corresponding list of unicode strings. The reversible bpe codes work on unicode strings. This means you

Collect the information of the running environments.

Contrast distortion.

This method forwards all its arguments to SiglipTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this me

Extract features from images.

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

Placeholder of forward function.

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

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

Args: imgs (List[Tensor]): the outer list indicates test-time augmentations and inner Tensor should have a shape

this will perform the index select, cat the tensors, and provide the attn_bias from cache

Randomly get a crop bounding box.

Calculate the padding size of input. Args: input_shape (:obj:`torch.Size`): arrange as (H, W). Returns: Tupl

Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).

Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).

Get ``num_points`` most uncertain points with random points during train. Sample points in [0, 1] x [0, 1] coordinate space based on their

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

return all pretrain tags for the specified model architecture

Make divisible function. This function rounds the channel number to the nearest value that can be divisible by the divisor. It is taken from

Test model with multiple gpus. This method tests model with multiple gpus and collects the results under two different modes: gpu and cpu mod

nn.Module: normalization layer after the first convolution layer

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

Randomly sample an img_scale when ``ratio_range`` is specified. A ratio will be randomly sampled from the range specified by ``ratio_

Resize pos_embed weights. Resize pos_embed using bicubic interpolate method. Args: pos_embed (torch.Tensor): Position emb

Draw `result` over `img`. Args: img (str or Tensor): The image to be displayed. result (Tensor): The semantic segment

Test with single GPU. Args: model (nn.Module): Model to be tested. data_loader (utils.data.Dataloader): Pytorch data loader.

Returns the tokenized representation of given input string(s) Parameters ---------- texts : Union[str, List[str]] An input s

Calculate evaluation metrics Args: total_area_intersect (ndarray): The intersection of prediction and ground truth histogram o