tjk6ddlZddlmZddlmZddlZddlmZddlmcm 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 ej1Z2Gd!d"ej1Z3Gd#d$ej1Z4Gd%d&ej1Z5 dd(e d)e d*e d+e d,e6e7d-e f d.Z8Gd/d0ej1Z9Gd1d2ej1Z:Gd3d4ej1Z;Gd5d6ej1Z<Gd7d8ej1Z=Gd9d:ej1Z> ddej d(ej d?ej dzd@e?dzdAe?dBee"fdCZ@GdDdEej1ZAGdFdGej1ZBdHdIdJdejCfdKe7dLe7dMe7dNe?dOeDdPejEdzdQejFd-ej fdRZGGdSdTej1ZHGdUdVej1ZIGdWdXej1ZJGdYdZej1ZKGd[d\ej1ZLGd]d^ej1ZMe#Gd_d`eZNGdadbej1ZOdcZPGdddeeNZQGdfdgeNZRGdhdieNZSddkej dlej dmeTd-ej fdnZUGdodpeNZVddrZWdse7dtej due7d-ej fdvZXdwej due?d-ej fdxZYGdydzeNZZ dd~Z[e#dGddeNZ\e#deGddeZ]e#dGddeNZ^gdZ_dS)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_introcFeZdZUdZdZejdzed<dZejdzed<dZ ejdzed<dZ ejdzed<dZ ejdzed<dZ ejdzed<dZ eejdzed <dZeejdzed <dZeejdzed <dS) 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'h/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/deimv2/modeling_deimv2.pyrr-s "37u(4/666;? 1D 8???48*T1888>B!5#4t#;BBB?C"E$5$<CCC9=e/$6===59M5*+d299926Je'(4/6668<eE-.5<<<<