`i @dZddlZddlZddlZddlmZddlmZm Z ddl Z ddl m Z ddl m Z ddlmZdd lmZdd lmZdd lmZmZmZdd lmZmZmZmZdd lmZddlm Z ej!e"Z#eedGddeZ$eedGddeZ%eedGddeZ&eedGddeZ'dZ(dZ)Gdd e j*Z+Gd!d"e j*Z,Gd#d$e j*Z-dLd'e j.d(e/d)e0d*e j.fd+Z1Gd,d-e j*Z2Gd.d/e j*Z3Gd0d1e j*Z4Gd2d3e j*Z5Gd4d5e j*Z6Gd6d7e j*Z7Gd8d9e j*Z8Gd:d;eZ9Gd<d=e j*Z:eGd>d?eZ;eGd@dAe;Z<edBGdCdDe;Z=edEGdFdGe;Z>edHGdIdJe;eZ?gdKZ@dS)MzPyTorch Swin Transformer model.N) dataclass)OptionalUnion)nn)ACT2FN)GradientCheckpointingLayer)BackboneOutput)PreTrainedModel) find_pruneable_heads_and_indicesmeshgridprune_linear_layer) ModelOutputauto_docstringlogging torch_int) BackboneMixin) SwinConfigzN Swin encoder's outputs, with potential hidden states and attentions. ) custom_introceZdZUdZdZeejed<dZ ee ejdfed<dZ ee ejdfed<dZ ee ejdfed<dS)SwinEncoderOutputa 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__rrtorch FloatTensor__annotations__rtuplerrz/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/swin/modeling_swin.pyrr*s6:x 12999=AM8E%"3S"89:AAA:>Ju0#567>>>FJHU5+