^jv& ddlmZddlmZddlmZddlmZmZedeGd d eZ edeGd d eZ edeGd deZ edeGddeZ gdZ y))strict)PreTrainedConfig)auto_docstring)CONFIG_MAPPING AutoConfigzyonigozlan/EdgeTAM-hf) checkpointceZdZUdZdZdZdeiZdZe e zdze d<dZ e edze d<dZe dze d<dZee d <d Zee d <d Zee d <d Zee d<dZe edze d<dZee d<dZee d<dZee d<dZee d<fdZxZS)EdgeTamVisionConfiga backbone_channel_list (`List[int]`, *optional*, defaults to `[384, 192, 96, 48]`): The list of channel dimensions for the backbone. backbone_feature_sizes (`List[List[int]]`, *optional*, defaults to `[[256, 256], [128, 128], [64, 64]]`): The spatial sizes of the feature maps from the backbone. fpn_hidden_size (`int`, *optional*, defaults to 256): The hidden dimension of the FPN. fpn_kernel_size (`int`, *optional*, defaults to 1): The kernel size for the convolutions in the neck. fpn_stride (`int`, *optional*, defaults to 1): The stride for the convolutions in the neck. fpn_padding (`int`, *optional*, defaults to 0): The padding for the convolutions in the neck. fpn_top_down_levels (`List[int]`, *optional*, defaults to `[2, 3]`): The levels for the top-down FPN connections. num_feature_levels (`int`, *optional*, defaults to 3): The number of feature levels from the FPN to use. vision_configedgetam_vision_modelbackbone_configNbackbone_channel_listbackbone_feature_sizesfpn_hidden_sizefpn_kernel_size fpn_strider fpn_paddingfpn_top_down_levelsrnum_feature_levelsgelu hidden_actư>layer_norm_eps{Gz?initializer_rangec 0|jgdn |j|_|j ddgddgddggn |j|_|jddgn |j|_t|jt rT|jj dd|jd<t|jddi|j|_n.|j"tjd dd gd d  |_t|,di|y)N)i`0r@rr model_type timm_wrapperztimm/repvit_m1.dist_in1kT)rrrr)in_chans features_only out_indices) model_args) rrr isinstancerdictgetrr from_pretrainedsuper __post_init__selfkwargs __class__s |/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/edgetam/configuration_edgetam.pyr2z!EdgeTamVisionConfig.__post_init__Ds"&"<"<"D $JdJd "372M2M2Uc3Z#sb"X .[_[v[v #.2-E-E-MAq6SWSkSk d**D 1151E1E1I1I,Xf1gD  .#1$2F2F|2T#U#mX\XlXl#mD  ! ! )#-#=#=*()DQ]^$D  '')__name__ __module__ __qualname____doc__base_config_keyr&r sub_configsrr.r__annotations__rlistintrrrrrrrrstrrfloatrr2 __classcell__r6s@r7r r s&&O'J:K7;OT,,t3:.249t+2*.D4K.OSOSJK,0cT)0J NE #u#((r8r ceZdZUdZdZdZeed<dZee eze eefzed<dZ ee eze eefzed<dZ eed <d Z eed <d Zeed <dZeed<dZeed<y)EdgeTamPromptEncoderConfigaY 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. scale (`float`, *optional*, defaults to 1): The scale factor for the prompt encoder. prompt_encoder_configr hidden_sizei image_size patch_sizemask_input_channelsnum_point_embeddingsrrrrrscaleN)r9r:r;r<r=rIrAr?rJr@tuplerLrMrOrrBrrCrPr,r8r7rGrGXs.OK48Jd3i%S/1846Jd3i%S/16!! !#!J NE E3Nr8rGceZdZUdZdZdZeed<dZe ed<dZ eed<d Z eed <d Z eed <d Z eed <dZeed<dZeed<dZeed<dZeed<dZeed<dZeed<y)EdgeTamMaskDecoderConfiga mlp_dim (`int`, *optional*, defaults to 2048): The dimension of the MLP in the two-way transformer. attention_downsample_rate (`int`, *optional*, defaults to 2): The downsample rate for the attention layers. num_multimask_outputs (`int`, *optional*, defaults to 3): The number of multimask outputs. iou_head_depth (`int`, *optional*, defaults to 3): The depth of the IoU head. iou_head_hidden_dim (`int`, *optional*, defaults to 256): The hidden dimension of the IoU head. dynamic_multimask_via_stability (`bool`, *optional*, defaults to `True`): Whether to use dynamic multimask via stability. dynamic_multimask_stability_delta (`float`, *optional*, defaults to 0.05): The stability delta for the dynamic multimask. dynamic_multimask_stability_thresh (`float`, *optional*, defaults to 0.98): The stability threshold for the dynamic multimask. mask_decoder_configrrIrrimlp_dimrnum_hidden_layersnum_attention_headsattention_downsample_raternum_multimask_outputsiou_head_depthiou_head_hidden_dimTdynamic_multimask_via_stabilityg?!dynamic_multimask_stability_deltag\(\?"dynamic_multimask_stability_threshN)r9r:r;r<r=rIrAr?rrBrUrVrXrYrZr[r\r]boolr^rCr_r,r8r7rSrSps&,OKJGSs  %&s&!"3"NC"",0#T0/3%u304&4r8rSceZdZUdZdZeeedZdZ e e zdze d<dZ e e zdze d<dZe e zdze d<dZee d <fd ZxZS) EdgeTamConfiga prompt_encoder_config (Union[`dict`, `EdgeTamPromptEncoderConfig`], *optional*): Dictionary of configuration options used to initialize [`EdgeTamPromptEncoderConfig`]. mask_decoder_config (Union[`dict`, `EdgeTamMaskDecoderConfig`], *optional*): Dictionary of configuration options used to initialize [`EdgeTamMaskDecoderConfig`]. Example: ```python >>> from transformers import ( ... EdgeTamVisionConfig, ... EdgeTamPromptEncoderConfig, ... EdgeTamMaskDecoderConfig, ... EdgeTamModel, ... ) >>> # Initializing a EdgeTamConfig with `"facebook/edgetam.1_hiera_tiny"` style configuration >>> configuration = EdgeTamConfig() >>> # Initializing a EdgeTamModel (with random weights) from the `"facebook/edgetam.1_hiera_tiny"` style configuration >>> model = EdgeTamModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a EdgeTamConfig from a EdgeTamVisionConfig, EdgeTamPromptEncoderConfig, and EdgeTamMaskDecoderConfig >>> # Initializing EDGETAM vision encoder, memory attention, and memory encoder configurations >>> vision_config = EdgeTamVisionConfig() >>> prompt_encoder_config = EdgeTamPromptEncoderConfig() >>> mask_decoder_config = EdgeTamMaskDecoderConfig() >>> config = EdgeTamConfig(vision_config, prompt_encoder_config, mask_decoder_config) ``` edgetam)r rHrTNr rHrTrrc |t|jtrT|jjdd|jd<t |jddi|j|_n|jt d|_t|j trt di|j |_n|j t |_t|jtrtdi|j|_n|jt|_t|(di|y)Nr&rr,) r-r r.r/rrHrGrTrSr1r2r3s r7r2zEdgeTamConfig.__post_init__s d(($ //3/A/A/E/ElTj/kD  | ,!/0B0B<0P!Q!gTXTfTf!gD     '!/0F!G!ID  d00$ 7)C)adF`F`)aD &  ' ' /)C)ED & d.. 5'?'[$BZBZ'[D $  % % -'?'AD $ ''r8)r9r:r;r<r&r rGrSr>r r.rr?rHrTrrCr2rDrEs@r7rbrbsx!FJ#!;7K 59M4**T18<@4"22T9@:> 0047>#u#((r8rb)rbr rGrSN)huggingface_hub.dataclassesrconfiguration_utilsrutilsrautorr r rGrSrb__all__r,r8r7rjs(/3#-238(*8(48(v23!14,23!5/!54!5H23A($A(4A(H mr8