+ jRt^RIHt^RIHt^RIHt]!RR7]!RR]444t]!RR7]!RR ]444t]!RR7]!R R ]444t ]!RR7]!R R ]444t .ROt R#)zSAM model configuration)strict)PreTrainedConfig)auto_docstringzfacebook/sam-vit-huge) checkpointcbaa]tRt^toRtRtRtRt^t^t ^t Rt Rt V3Rlt V3RltR tVtV;t#) SamPromptEncoderConfigz mask_input_channels (`int`, *optional*, defaults to 16): The number of channels to be fed to the `MaskDecoder` module. num_point_embeddings (`int`, *optional*, defaults to 4): The number of point embeddings to be used. prompt_encoder_configgeluư>c l<VPVP,Vn\SV`!R/VBR#N) image_size patch_sizeimage_embedding_sizesuper __post_init__selfkwargs __class__s&,j/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/sam/configuration_sam.pyr$SamPromptEncoderConfig.__post_init__*s($(OOt$F! ''c<V^8dQh/S[;R&S[S[S[,,S[S[S[3,,;R&S[S[S[,,S[S[S[3,,;R&S[;R&S[;R&S[;R&S[;R&#) hidden_sizerrmask_input_channelsnum_point_embeddings hidden_actlayer_norm_eps)intlisttuplestrfloat)format __classdict__s"r __annotate__#SamPromptEncoderConfig.__annotate__sd3i%S/18d3i%S/16! !!"#$ %r)r)__name__ __module__ __qualname____firstlineno____doc__base_config_keyrrrrr r!r"r__annotate_func____static_attributes____classdictcell__ __classcell__rr)s@@rrrsB.OK48J46J! !J N()rrc\a]tRt^/toRtRtRtRtRt^t ^t ^t ^t ^t RtRtV3RltRtVtR #) SamMaskDecoderConfiga mlp_dim (`int`, *optional*, defaults to 2048): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. attention_downsample_rate (`int`, *optional*, defaults to 2): The downsampling rate of the attention layer. num_multimask_outputs (`int`, *optional*, defaults to 3): The number of outputs from the `SamMaskDecoder` module. In the Segment Anything paper, this is set to 3. iou_head_depth (`int`, *optional*, defaults to 3): The number of layers in the IoU head module. iou_head_hidden_dim (`int`, *optional*, defaults to 256): The dimensionality of the hidden states in the IoU head module. mask_decoder_configr reluir c<V^8dQh/S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[;R &S[;R &#) rrr!mlp_dimnum_hidden_layersnum_attention_headsattention_downsample_ratenum_multimask_outputsiou_head_depthiou_head_hidden_dimr")r#r&r')r(r)s"rr*!SamMaskDecoderConfig.__annotate__/s$%&'()*+, -. #&/0"1234"56 7rrN)r,r-r.r/r0r1rr!r<r=r>r?r@rArBr"r2r3r4)r)s@rr8r8/sO ,OKJG %&!"N" N7rr8caa]tRt^MtoRtRtRtRtRt^ t ^ t ^t Rt ^t RtRtR tR tR tR tR tR t^tRt^tR tV3RltV3RltRtVtV;t#)SamVisionConfiga output_channels (`int`, *optional*, defaults to 256): Dimensionality of the output channels in the Patch Encoder. use_rel_pos (`bool`, *optional*, defaults to `True`): Whether to use relative position embedding. window_size (`int`, *optional*, defaults to 14): Window size for relative position. global_attn_indexes (`list[int]`, *optional*, defaults to `[2, 5, 8, 11]`): The indexes of the global attention layers. num_pos_feats (`int`, *optional*, defaults to 128): The dimensionality of the position embedding. mlp_dim (`int`, *optional*): The dimensionality of the MLP layer in the Transformer encoder. If `None`, defaults to `mlp_ratio * hidden_size`. Example: ```python >>> from transformers import ( ... SamVisionConfig, ... SamVisionModel, ... ) >>> # Initializing a SamVisionConfig with `"facebook/sam-vit-huge"` style configuration >>> configuration = SamVisionConfig() >>> # Initializing a SamVisionModel (with random weights) from the `"facebook/sam-vit-huge"` style configuration >>> model = SamVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` vision_configsam_vision_modelir r r r gg|=Tg@Nc <VPf'\VPVP,4M VPVnVP^,Vn\ SV`!R/VBR#r)r<r#r mlp_ratioscalerrrs&,rrSamVisionConfig.__post_init__sRAEAUs4++dnn<=[_[g[g %%*  ''rc<V^8dQh/S[;R&S[;R&S[;R&S[;R&S[;R&S[S[S[,,S[S[S[3,,;R&S[S[S[,,S[S[S[3,,;R&S[;R&S[;R &S[S[,;R &S[;R &S[;R &S[;R &S[;R&S[;R&S[;R&S[S[,S[S[R3,,;R&S[;R&S[R,;R&#)rroutput_channelsr=r> num_channelsrrr!r"attention_dropoutinitializer_rangeqkv_biasrI use_abs_pos use_rel_pos window_size.global_attn_indexes num_pos_featsNr<)r#r$r%r&r'bool)r(r)s"rr*SamVisionConfig.__annotate__MseNOPQRST!UVWXd3i%S/18YZd3i%S/16[\]^!_`s{(ab$cdefghijklmncU38_4Dopqr4Zsr)r<rJ)r )r,r-r.r/r0r1 model_typerrMr=r>rNrrr!r"rOrPrQrIrRrSrTrUrVr<rr2r3r4r5r6s@@rrErEMs B&O#JKO!L48J46JJ!N%($HIKKK7DMG(wrrEcjaa]tRt^toRtRtR]R]R]/t Rt Rt Rt Rt RtV3R ltV3R ltR tVtV;t#) SamConfiga prompt_encoder_config (Union[`dict`, `SamPromptEncoderConfig`], *optional*): Dictionary of configuration options used to initialize [`SamPromptEncoderConfig`]. mask_decoder_config (Union[`dict`, `SamMaskDecoderConfig`], *optional*): Dictionary of configuration options used to initialize [`SamMaskDecoderConfig`]. Example: ```python >>> from transformers import ( ... SamVisionConfig, ... SamPromptEncoderConfig, ... SamMaskDecoderConfig, ... SamModel, ... ) >>> # Initializing a SamConfig with `"facebook/sam-vit-huge"` style configuration >>> configuration = SamConfig() >>> # Initializing a SamModel (with random weights) from the `"facebook/sam-vit-huge"` style configuration >>> model = SamModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a SamConfig from a SamVisionConfig, SamPromptEncoderConfig, and SamMaskDecoderConfig >>> # Initializing SAM vision, SAM Q-Former and language model configurations >>> vision_config = SamVisionConfig() >>> prompt_encoder_config = SamPromptEncoderConfig() >>> mask_decoder_config = SamMaskDecoderConfig() >>> config = SamConfig(vision_config, prompt_encoder_config, mask_decoder_config) ```samrr9rFNg{Gz?Tc 8<\VP\4'd\R/VPBVnMVPf\4Vn\VP\4'd\ R/VPBVnMVPf\ 4Vn\VP \4'd\R/VP BVnMVP f\4Vn\SV`$!R/VBR#r) isinstancerFdictrErrr9r8rrrs&,rrSamConfig.__post_init__s d(($ / /!0!F43E3E!FD     '!0!2D  d00$ 7 7)?)]$B\B\)]D &  ' ' /)?)AD & d.. 5 5';'Wd>V>V'WD $  % % -';'=D $ ''rc<V^8dQh/S[S[,R,;R&S[S[,R,;R&S[S[,R,;R&S[;R&S[;R&#)rNrFrr9rPtie_word_embeddings)rbrr'rW)r(r)s"rr*SamConfig.__annotate__sqZ**T18[\ "22T9@]^ 0047>_`#ab$cr)r9rrF)r,r-r.r/r0r\rr8rE sub_configsrFrr9rPrerr2r3r4r5r6s@@rr^r^sV! FJ!73K 59M<@:># $(grr^N)r^r8rrE) r0huggingface_hub.dataclassesrconfiguration_utilsrutilsrrr8rEr^__all__rrrrls.3#23(-(4(.23!+!4!823<(&<(4<(~23A( A(4A(H ]r