Batch data into lists of length *n*. The last batch may be shorter. NOTE based on more-itertools impl, to be replaced by python 3.12 itertools.bat

Build zero-shot classifier weights by iterating over class names in batches Args: model: CLIP model instance tokenizer: CLIP toke

Center crops and/or pads the given image. If the image is torch Tensor, it is expected to have [..., H, W] shape, where ... means an arbitrary

Shortcut to reader's `fetch_file()`.

Shortcut to reader's `fetch_file()`.

grid_size: int of the grid height and width return: pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/

Get parameters

Choose strategy for dropping (masking) tokens to achieve target context length

Return function over iterator that groups key, value pairs into samples. :param keys: function that splits the key into key and extension (base_p

enumerate available model architectures based on config files

Returns the names of available CLIP models

return all models having the specified pretrain tag

return all pretrain tags for the specified model architecture

Load weights from .npz checkpoints for official Google big_vision image-text models Currently the SigLIP source models are supported and a Custo

Load a CLIP model Parameters ---------- name : str A model name listed by `clip.available_models()`, or the path to a model check

Profile the full model using torch.utils.flop_counter

Profile the image encoder using torch.utils.flop_counter

Profile the text encoder using torch.utils.flop_counter