g bdZddlZddlmZddlmZmZmZmZm Z ddl Z ddl Z ddl m Z ddl mZmZmZddlmZdd lmZmZmZmZmZdd lmZdd lmZmZmZmZm Z m!Z!dd l"m#Z#d dl$m%Z%ej&e'Z(dZ)dZ*gdZ+dZ,dZ-eGddeZ.eGddeZ/eGddeZ0eGddeZ1Gdde j2Z3Gdde j2Z4Gd d!e j2Z5dRd$e j6d%e7d&e8d'e j6fd(Z9Gd)d*e j2Z:Gd+d,e j2Z;Gd-d.e j2Z<Gd/d0e j2Z=d1e j6d2ee>d3ee>d'e j6fd4Z?Gd5d6e j2Z@d1e j6d7ee>e>fd8ee>e>fd9eee>d'e j6f d:ZAGd;dZDGd?d@e j2ZEedAeCdBGdCdDeBZFGdEdFe j2ZGGdGdHe j2ZHedIeCGdJdKeBZIedLeCGdMdNeBZJedOeCGdPdQeBe#ZKdS)SzPyTorch Hiera model.N) dataclass)DictListOptionalTupleUnion)nn)BCEWithLogitsLossCrossEntropyLossMSELoss)ACT2FN)BackboneOutputBaseModelOutputBaseModelOutputWithPoolingImageClassifierOutput ModelOutput)PreTrainedModel)add_code_sample_docstringsadd_start_docstrings%add_start_docstrings_to_model_forwardloggingreplace_return_docstrings torch_int) BackboneMixin) HieraConfigrzfacebook/hiera-tiny-224-hf)r1izfacebook/hiera-tiny-224-in1k-hfztabby, tabby catceZdZUdZdZejed<dZe e ejdfed<dZ e e ejdfed<dZ e e ejdfed<dS)HieraEncoderOutputa Hiera 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)`. Thesre are the unrolled hidden states of the model. 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, height, width, hidden_size)`. These are the reshaped and re-rolled hidden states of the model. 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$d/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/hiera/modeling_hiera.pyr r =s2,0u(///=AM8E%"3S"89:AAA:>Ju0#567>>>FJHU5+