tjv&ddlmZddlmZddlmZddlmZmZedeGd d eZ edeGd d eZ edeGd deZ edeGddeZ gdZ dS))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 |jgdn|j|_|j ddgddgddggn|j|_|jddgn|j|_t|jt rK|jdd|jd<t|jddi|j|_n(|j!tj d dd gd d  |_tj di|dS)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 o/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/edgetam/configuration_edgetam.pyr2z!EdgeTamVisionConfig.__post_init__Ds3"&"<"D    $Jd "372M2Uc3Z#sb"X . .[_[v #.2-E-MAq66SWSk d*D 1 1 151E1I1I,Xf1g1gD  .#1$2F|2T#U#m#mX\Xl#m#mD  ! )#-#=*()DQ]Q]Q]^^$$$D  ''''''')__name__ __module__ __qualname____doc__base_config_keyr&r sub_configsrr.r__annotations__rlistintrrrrrrrrstrrfloatrr2 __classcell__r6s@r7r r sD&&O'J:K7;OT,,t3:::.249t+222*.D4K...OSOSJK,0cT)000J NE   #u###(((((((((r8r ceZdZUdZdZdZeed<dZee eze eefzed<dZ ee eze eefzed<dZ eed <d Z eed <d Zeed <dZeed<dZeed<dS)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/188846Jd3i%S/1666!!!! !#!!!J NE   E3NNNNNr8rGceZdZUdZdZdZeed<dZe ed<dZ eed<d Z eed <d Z eed <d Z eed <dZeed<dZeed<dZeed<dZeed<dZeed<dZeed<dS)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#T000/3%u33304&44444r8rSceZdZUdZdZeeedZdZ 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 pt|jtrK|jdd|jd<t |jddi|j|_n |jt d|_t|jtrt di|j|_n|jt |_t|jtrtdi|j|_n|jt|_tj di|dS)Nr&rr,) r-r r.r/rrHrGrTrSr1r2r3s r7r2zEdgeTamConfig.__post_init__s6 d($ / / J/3/A/E/ElTj/k/kD | ,!/0B<0P!Q!g!gTXTf!g!gD     '!/0F!G!I!ID  d0$ 7 7 F)C)a)adF`)a)aD & &  ' /)C)E)ED & d. 5 5 B'?'['[$BZ'['[D $ $  % -'?'A'AD $'''''''r8)r9r:r;r<r&r rGrSr>r r.rr?rHrTrrCr2rDrEs@r7rbrbs!!FJ#!;7K 59M4**T1888<@4"22T9@@@:> 0047>>>#u###(((((((((r8rb)rbr rGrSN)huggingface_hub.dataclassesrconfiguration_utilsrutilsrautorr r rGrSrb__all__r,r8r7rjs(/.....333333######--------23338(8(8(8(8(*8(8(438(v2333!143,2333!5!5!5!5!5/!5!543!5H2333A(A(A(A(A($A(A(43A(H m l lr8