^j%/ddlmZddlmZddlmZmZejeZ edeGddeZ edeGd d eZ edeGd d eZ gd Z y))strict)PreTrainedConfig)auto_docstringloggingzCIDAS/clipseg-rd64) checkpointceZdZUdZdZdZdZeed<dZ eed<dZ eed <d Z eed <d Z eed <dZ eed<dZeed<dZedzed<dZeezdzed<dZeed<dZedzed<dZedzed<dZedzed<dZeeezdzed <d!Zy)"CLIPSegTextConfiga Example: ```python >>> from transformers import CLIPSegTextConfig, CLIPSegTextModel >>> # Initializing a CLIPSegTextConfig with CIDAS/clipseg-rd64 style configuration >>> configuration = CLIPSegTextConfig() >>> # Initializing a CLIPSegTextModel (with random weights) from the CIDAS/clipseg-rd64 style configuration >>> model = CLIPSegTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```clipseg_text_model text_configi vocab_size hidden_sizeintermediate_size num_hidden_layersnum_attention_headsMmax_position_embeddings quick_gelu hidden_acth㈵>Nlayer_norm_epsattention_dropout{Gz?initializer_range?initializer_factor pad_token_idi bos_token_idi eos_token_idc|j|jzdk7r&td|jd|jdyzOPart of `@strict`-powered validation. Validates the architecture of the config.rzThe hidden size (z6) is not a multiple of the number of attention heads (z).Nrr ValueErrorselfs |/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/clipseg/configuration_clipseg.pyvalidate_architecturez'CLIPSegTextConfig.validate_architectureES   d66 6! ;#D$4$4#5622327  <)__name__ __module__ __qualname____doc__ model_typebase_config_keyr int__annotations__rrrrrrstrrfloatrrr!r#r$r%listr-r/r,r r s &J#OJK!s!s  #%S%"J"#'NEDL',/sU{T)/#u#'* * !L#* $L#*$+0L#S /D(0r/r ceZdZUdZdZdZdZeed<dZ eed<dZ eed <dZ eed <d Z eed <d Z eeezeeefzdzed<dZeeezeeefzdzed<dZeed<dZeed<dZeezdzed<dZeed<dZeed<dZy)CLIPSegVisionConfiga Example: ```python >>> from transformers import CLIPSegVisionConfig, CLIPSegVisionModel >>> # Initializing a CLIPSegVisionConfig with CIDAS/clipseg-rd64 style configuration >>> configuration = CLIPSegVisionConfig() >>> # Initializing a CLIPSegVisionModel (with random weights) from the CIDAS/clipseg-rd64 style configuration >>> model = CLIPSegVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```clipseg_vision_model vision_configiri rrrrr num_channelsN image_size patch_sizerrrrrrrrr r!c|j|jzdk7r&td|jd|jdyr'r(r*s r,r-z)CLIPSegVisionConfig.validate_architectureqr.r/)r0r1r2r3r4r5rr6r7rrrr@rBr:tuplerDrr8rr9rrr!r-r;r/r,r=r=Ns (J%OK!s!s!!L#;>Jd3i%S/1D8>;=Jd3i%S/1D8="J" NE ,/sU{T)/#u# ##r/r=c4eZdZUdZdZeedZdZe ezdze d<dZ e ezdze d<dZ e dze d<d Zee zdze d <d Zedze d <d Zee ee dfze d<dZe e d<dZe e d<dZee ze d<dZee d<dZe e d<dZe e d<dZee d<fdZxZS) CLIPSegConfiga extract_layers (`list[int]`, *optional*, defaults to `[3, 6, 9]`): Layers to extract when forwarding the query image through the frozen visual backbone of CLIP. reduce_dim (`int`, *optional*, defaults to 64): Dimensionality to reduce the CLIP vision embedding. conditional_layer (`int`, *optional*, defaults to 0): The layer to use of the Transformer encoder whose activations will be combined with the condition embeddings using FiLM (Feature-wise Linear Modulation). If 0, the last layer is used. use_complex_transposed_convolution (`bool`, *optional*, defaults to `False`): Whether to use a more complex transposed convolution in the decoder, enabling more fine-grained segmentation.. Example: ```python >>> from transformers import CLIPSegConfig, CLIPSegModel >>> # Initializing a CLIPSegConfig with CIDAS/clipseg-rd64 style configuration >>> configuration = CLIPSegConfig() >>> # Initializing a CLIPSegModel (with random weights) from the CIDAS/clipseg-rd64 style configuration >>> model = CLIPSegModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a CLIPSegConfig from a CLIPSegTextConfig and a CLIPSegVisionConfig >>> # Initializing a CLIPSegText and CLIPSegVision configuration >>> config_text = CLIPSegTextConfig() >>> config_vision = CLIPSegVisionConfig() >>> config = CLIPSegConfig(text_config=config_text, vision_config=config_vision) ```clipseg)r r?Nr r?rprojection_dimg/L F@logit_scale_init_valuer r!)r .extract_layers@ reduce_dimdecoder_num_attention_headsrdecoder_attention_dropoutrdecoder_hidden_actrdecoder_intermediate_sizerconditional_layerF"use_complex_transposed_convolutionc |ji}tjdnAt|jtr|jj }n |j}|j i}tjdnAt|j tr|j j }n |j }|jdd}|jdd}|t di|j }|jD]B\}}||vs |||k7s|dk7s||vr d|d|d} nd |d } tj| D|j||tdi|j } d | vr3| d jDcic]\}}t||c}}| d <| jD]B\}}||vs |||k7s|dk7s||vr d|d |d} nd |d } tj| D|j| t di||_tdi||_t |4di|ycc}}w)NzR`text_config` is `None`. Initializing the `CLIPSegTextConfig` with default values.zV`vision_config` is `None`. initializing the `CLIPSegVisionConfig` with default values.text_config_dictvision_config_dicttransformers_version`zp` is found in both `text_config_dict` and `text_config` but with different values. The value `text_config_dict["z"]` will be used instead.zj`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["z"]` will be overridden.id2labelzv` is found in both `vision_config_dict` and `vision_config` but with different values. The value `vision_config_dict["zp`vision_config_dict` is provided which will be used to initialize `CLIPVisionConfig`. The value `vision_config["r;)r loggerinfo isinstancer to_dictr?r=popitemsupdater8super __post_init__) r+kwargsr r?rYrZ_text_config_dictkeyvaluemessage_vision_config_dict __class__s r,rfzCLIPSegConfig.__post_init__s    #K KKl m ((*; <**224K**K    %M KKp q **,? @ ..668M ..M "::&8$?#ZZ(rws(/3,   H %/0,(,1,^/0'*'1'T/0G($G(1G(T Hr/