Zj$\SrSSKrSSKJr SSKJr SSKJr SSK J r SSK J r SS K Jr SS KJrJr SS KJr S S KJrJr S SKJrJrJr S SKJrJrJrJrJ r J!r!J"r"J#r# \"SS9\"SS\555r$\"SS9\"SS\555r%\"SS9\"SS\555r&\"SS9\"SS\555r'"SS\5r("SS\"5r)"SS\5r*"S S!\!5r+"S"S#\5r,\"S$S%\ 55r-\"S&S'9"S(S)\#55r."S*S+\5r//S,Qr0g)-zPyTorch SAM 2 model.N)strict)initialization)PreTrainedConfig)PreTrainedModel)Unpack)auto_docstring)TransformersKwargsmerge_with_config_defaults)capture_outputs)CONFIG_MAPPING AutoConfig) Sam2ConfigSam2MaskDecoderConfigSam2PromptEncoderConfig) Sam2AttentionSam2FeedForward Sam2LayerNorm Sam2ModelSam2PreTrainedModelSam2TwoWayAttentionBlockSam2VisionEncoderOutputSam2VisionModelzyonigozlan/EdgeTAM-hf) checkpointc^\rSrSr%SrSrSrS\0rSr \ \ -S-\ S'Sr \\S-\ S'Sr\S-\ S'S r\\ S 'S r\\ S 'S r\\ S 'Sr\\ S'Sr\\S-\ S'Sr\\ S'Sr\\ S'Sr\\ S'Sr\\ S'U4SjrSrU=r$)EdgeTamVisionConfig(a 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_actgư>layer_norm_epsg{Gz?initializer_rangec B>URc/SQO URUlURc SS/SS/SS//O URUlURcSS/O URUl[UR[ 5(aUURR SS5URS'[URS"S0URD6UlO-URc [R"S SS /S QS .S 9Ul[TU],"S0UD6 g)N)i`0r$@r r model_type timm_wrapperztimm/repvit_m1.dist_in1kT)rr&r r)in_chans features_only out_indices) model_args) r"r#r* isinstancer!dictgetrrfrom_pretrainedsuper __post_init__)selfkwargs __class__s |/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/edgetam/modular_edgetam.pyrB!EdgeTamVisionConfig.__post_init__Qs"&"<"<"D $JdJd "372M2M2Uc3Z#sb"X .[_[v[v #.2-E-E-MAq6SWSkSk d**D 1 1151E1E1I1I,Xf1gD  .#1$2F2F|2T#U#mX\XlXl#mD  ! ! )#-#=#=*()DQ]^$D  '')r"r!r#r*)__name__ __module__ __qualname____firstlineno____doc__base_config_keyr6r sub_configsr!r>r__annotations__r"listintr#r%r'r(r)r*r+r-strr.floatr/rB__static_attributes__ __classcell__)rEs@rFrr(s&&O'J:K7;OT,,t3:.249t+2*.D4K.OSOSJK,0cT)0J NE #u#((rHrc\rSrSrSrg)EdgeTamPromptEncoderConfiger<NrIrJrKrLrUr<rHrFrXrXe rHrXc\rSrSrSrg)EdgeTamMaskDecoderConfigkr<NrZr<rHrFr]r]kr[rHr]c\rSrSrSrSrg) EdgeTamConfigqa] 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) ``` r<N)rIrJrKrLrMrUr<rHrFr`r`qs !F rHr`c\rSrSrSrg)EdgeTamLayerNormr<NrZr<rHrFrcrcrHrcc\rSrSrSrg)EdgeTamVisionEncoderOutputr<NrZr<rHrFrgrgrerHrgc\rSrSrSrg)EdgeTamAttentionr<NrZr<rHrFrjrjrerHrjc\rSrSrSrg)EdgeTamTwoWayAttentionBlockr<NrZr<rHrFrmrmrerHrmc\rSrSrSrg)EdgeTamFeedForwardr<NrZr<rHrFrprprerHrpcF\rSrSrSr\R "5S5rSrg)EdgeTamPreTrainedModelNc.[R"X5 [U[5(a/URb![ R "UR5 gg[US5(a*[ R"URURS9 gg)Npositional_embedding)std) r _init_weightsr= EdgeTamModelno_memory_embeddinginitzeros_hasattrnormal_rvscale)rCmodules rFrx$EdgeTamPreTrainedModel._init_weightssk%%d3 fl + +))5 F6676 V3 4 4 LL44&,, G5rHr<) rIrJrKrL"_keys_to_ignore_on_load_unexpectedtorchno_gradrxrUr<rHrFrsrss")-& ]]_HHrHrszN The vision model from EdgeTAM without any head or projection on top. ) custom_introc |\rSrSr\rSr0rSr\ \ S S\ RS-S\ \S\\-4Sjj55rSrg) EdgeTamVisionModel pixel_valuesc[S5eNz2Can't get input embeddings from timm wrapper modelNotImplementedErrorrCs rFget_input_embeddings'EdgeTamVisionModel.get_input_embeddings!"VWWrHNrDreturnc XUc [S5eUR"U40UD6nURnUVs/sHoURSSSS5PM nnUR U5upgX`R *SSSS2nXpR *SSSS2n[ USUUURS9$s snf)Nz You have to specify pixel_valuesrr rr&)last_hidden_statefpn_hidden_statesfpn_position_encoding hidden_states) ValueErrorbackbonerpermuteneckr+rgr)rCrrDbackbone_outputintermediate_hidden_states hidden_staterrs rFforwardEdgeTamVisionModel.forwards  ?@ @-- ??%4%F%F"[u%v[u<&:&:1aA&F[u"%v3799=W3X0-/F/F.F.HI$B$O 57N7N6N6P QRVTVRV W)8</"7)77   &wsB'r<)N)rIrJrKrLr config_classmain_input_name_can_record_outputsrr r r FloatTensorrr tuplergrrUr<rHrFrrsp 'L$OX 26 ''$. +,  + +    rHrc"\rSrSr/SQrSrSrg)ry)z ^memory_.*z^mask_downsample.*zspatial_perceiver.*z^object_pointer_proj.*z0^temporal_positional_encoding_projection_layer.*no_memory_positional_encodingno_object_pointer%occlusion_spatial_embedding_parameterc[S5errrs rFr!EdgeTamModel.get_input_embeddingsrrHr<N)rIrJrKrLrrrUr<rHrFryrys *&XrHry)ryrrsr`rrXr])1rMrhuggingface_hub.dataclassesrrr{configuration_utilsrmodeling_utilsrprocessing_utilsrutilsr utils.genericr r utils.output_capturingr autorrsam2.configuration_sam2rrrsam2.modeling_sam2rrrrrrrrrrXr]r`rcrgrjrmrprsrry__all__r<rHrFrs~ .&3-&#K5-``   238(*8(48(v23 !8 4 23 4 4 23$ J$ 4$ N }  !8  }  ":    H0 H H # #  # L X9 X  rH