g dZddlZddlmZddlmZmZmZddlZddl Zddlm Z ddl m Z m Z mZddlmZdd lmZdd lmZdd lmZmZdd lmZmZmZmZmZmZmZm Z m!Z!dd l"m#Z#ddl$m%Z%er ddl&m'Z'm(Z(ndZ(dZ'ej)e*Z+dZ,dZ-gdZ.dZ/dZ0eGddeZ1eGddeZ2eGddeZ3Gdde j4Z5Gdd e j4Z6Gd!d"e j4Z7dId%ej8d&e9d'e:d(ej8fd)Z;Gd*d+e j4Z<Gd,d-e j4Z=Gd.d/e j4Z>Gd0d1e j4Z?Gd2d3e j4Z@Gd4d5e j4ZAGd6d7e j4ZBGd8d9e j4ZCGd:d;e j4ZDGd<d=eZEd>ZFd?ZGed@eFGdAdBeEZHedCeFGdDdEeEZIedFeFGdGdHeEe#ZJdS)Jz9PyTorch Dilated Neighborhood Attention Transformer model.N) dataclass)OptionalTupleUnion)nn)BCEWithLogitsLossCrossEntropyLossMSELoss)ACT2FN)BackboneOutput)PreTrainedModel) find_pruneable_heads_and_indicesprune_linear_layer) ModelOutputOptionalDependencyNotAvailableadd_code_sample_docstringsadd_start_docstrings%add_start_docstrings_to_model_forwardis_natten_availableloggingreplace_return_docstringsrequires_backends) BackboneMixin) DinatConfig) natten2dav natten2dqkrpbctNrargskwargss d/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/dinat/modeling_dinat.pyrr1,...ctr r!r"s r%rr4r&r'rzshi-labs/dinat-mini-in1k-224)rr)iztabby, tabby catceZdZUdZdZejed<dZe e ejdfed<dZ e e ejdfed<dZ e e ejdfed<dS)DinatEncoderOutputa Dinat encoder's outputs, with potential hidden states and attentions. Args: last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`): Sequence of hidden-states at the output of the last layer of the model. hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each stage) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `torch.FloatTensor` (one for each stage) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. reshaped_hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each stage) of shape `(batch_size, hidden_size, height, width)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs reshaped to include the spatial dimensions. Nlast_hidden_state. hidden_states attentionsreshaped_hidden_states) __name__ __module__ __qualname____doc__r,torch FloatTensor__annotations__r-rrr.r/r'r%r+r+Is2,0u(///=AM8E%"3S"89:AAA:>Ju0#567>>>FJHU5+