Wrap a single line of text into multiple lines such that each line's width (measured at the given scale) does not exceed max_width.

Extract features from the image. Args: image: A batch of images as a tensor of shape (B, C, H, W) or a list of P

Extract features from the image. Args: image: A batch of images as a tensor of shape (B, C, H, W) or a list of P

Clip the gradient norm of an iterable of parameters. The norm is computed over all gradients together, as if they were concatenated i

Extract features from the image. Args: image: A batch of images as a tensor of shape (B, C, H, W) or a list of P

Extract features from the image. Args: image: A batch of images as a tensor of shape (B, C, H, W) or a list of P

Args: cross_attn_block: The underlying cross-attention module channels: Model channels (output dimension)