^jkZddlZddlmZddlmZddlZddlmZddlmcm Z ddlm Z ddl m ZddlmZddlmZdd lmZmZdd lmZdd lmZdd lmZmZdd lmZddlm Z ddl!m"Z"m#Z#m$Z$m%Z%ddl&m'Z'm(Z(ddl)m*Z*m+Z+ddl,m-Z-e#deGddeZ.e#deGddeZ/e#deGddeZ0edGdd ejbZ2Gd!d"ejbZ3Gd#d$ejbZ4Gd%d&ejbZ5 dd'e d(e d)e d*e d+e6e7d,e f d-Z8Gd.d/ejbZ9Gd0d1ejbZ:Gd2d3ejbZ;Gd4d5ejbZ<Gd6d7ejbZ=Gd8d9ejbZ> dd:ejbd;ejde?dzd?e?d@ee"fdAZ@GdBdCejbZAGdDdEejbZBdFdGdHdejfdIe7dJe7dKe7dLe?dMeDdNejdzdOejd,ejfdPZGGdQdRejbZHGdSdTejbZIGdUdVejbZJGdWdXejbZKGdYdZejbZLGd[d\ejbZMe#Gd]d^eZNGd_d`ejbZOdaZPGdbdceNZQGdddeeNZRGdfdgeNZSddhejdiejdjeTd,ejfdkZUGdldmeNZVddnZWdoe7dpejdqe7d,ejfdrZXdsejdqe?d,ejfdtZYGdudveNZZ ddwZ[e#dxGdydzeNZ\e#d{eGd|d}eZ]e#d~GddeNZ^gdZ_y)N)Callable) dataclass)Tensor)initialization)ACT2CLS) load_backbone)center_to_corners_formatcorners_to_center_format)use_kernel_forward_from_hub) ModelOutput)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)#compile_compatible_method_lru_cache)TransformersKwargsauto_docstringtorch_compilable_check torch_int)can_return_tuplemerge_with_config_defaults)OutputRecordercapture_outputs) Deimv2Configa& Base class for outputs of the Deimv2Decoder. This class adds two attributes to BaseModelOutputWithCrossAttentions, namely: - a stacked tensor of intermediate decoder hidden states (i.e. the output of each decoder layer) - a stacked tensor of intermediate reference points. ) custom_introceZdZUdZdZej dzed<dZej dzed<dZ ej dzed<dZ ej dzed<dZ ej dzed<dZ ej dzed<dZ eej dzed <dZeej dzed <dZeej dzed <y) Deimv2DecoderOutputa! intermediate_hidden_states (`torch.FloatTensor` of shape `(batch_size, config.decoder_layers, num_queries, hidden_size)`): Stacked intermediate hidden states (output of each layer of the decoder). intermediate_logits (`torch.FloatTensor` of shape `(batch_size, config.decoder_layers, sequence_length, config.num_labels)`): Stacked intermediate logits (logits of each layer of the decoder). intermediate_reference_points (`torch.FloatTensor` of shape `(batch_size, config.decoder_layers, sequence_length, hidden_size)`): Stacked intermediate reference points (reference points of each layer of the decoder). intermediate_predicted_corners (`torch.FloatTensor` of shape `(batch_size, config.decoder_layers, num_queries, 4)`): Stacked intermediate predicted corners (predicted corners of each layer of the decoder). initial_reference_points (`torch.FloatTensor` of shape `(batch_size, config.decoder_layers, num_queries, 4)`): Stacked initial reference points (initial reference points of each layer of the decoder). cross_attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` and `config.add_cross_attention=True` is passed or when `config.output_attentions=True`): Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads. Nlast_hidden_stateintermediate_hidden_statesintermediate_logitsintermediate_reference_pointsintermediate_predicted_cornersinitial_reference_points hidden_states attentionscross_attentions)__name__ __module__ __qualname____doc__rtorch FloatTensor__annotations__r r!r"r#r$r%tupler&r'u/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/deimv2/modeling_deimv2.pyrr-s"37u((4/6;? 1 1D 8?48**T18>B!5#4#4t#;B?C"E$5$5$<C9=e//$6=59M5**+d2926Je''(4/68<eE--.5