.h1 2ddlmZddlZddlmZddlmZddlmZddl m Z m Z m Z m Z mZmZddlmZmZdd lmZmZdd lmZdd lmZdd Zdd ZddZddZddZddZddZ ddZ! d dZ"dgddgdgdddggddfdZ#eeeeeee e!eee e!d Z$d!dZ%y)")partialN)attempt_download_asset) TORCH_1_13) MaskDecoder)FpnNeckHiera ImageEncoderImageEncoderViT MemoryEncoder PromptEncoder)MemoryAttentionMemoryAttentionLayer) SAM2ModelSAMModel)TinyViT)TwoWayTransformerc&tdddgd|S)z_Build and return a Segment Anything Model (SAM) h-size model with specified encoder parameters. encoder_embed_dim encoder_depthencoder_num_headsencoder_global_attn_indexes checkpoint _build_samr"s Z/var/www/html/ai-service/venv/lib/python3.12/site-packages/ultralytics/models/sam/build.pybuild_sam_vit_hr' $3  c&tdddgd|S)z_Build and return a Segment Anything Model (SAM) l-size model with specified encoder parameters.r) rrr#r%s r&build_sam_vit_lr0#r(r)c&tdddgd|S)z_Build and return a Segment Anything Model (SAM) b-size model with specified encoder parameters. )r-r.rr#r%s r&build_sam_vit_br6.s $1  r)c0tgdgdgddd|S)z_Build and return a Mobile Segment Anything Model (Mobile-SAM) for efficient image segmentation.)@i@)r4r4r4)r4r- NT)rrr r! mobile_samr"r#r%s r&build_mobile_samr?9s! -"'$(  r)c 6tdgddgdgdgd|S)zjBuild and return a Segment Anything Model 2 (SAM2) tiny-size model with specified architecture parameters.`)rr4rr4r)r-r r5r<rr2irArencoder_stagesr encoder_global_att_blocksencoder_window_specencoder_backbone_channel_listr" _build_sam2r%s r& build_sam2_trNEs$ #"+)&9 r)c 6tdgddgdgdgd|S)zeBuild and return a small-size Segment Anything Model 2 (SAM2) with specified architecture parameters.rA)rr4r.r4r)rr= rCrErGrLr%s r& build_sam2_srQRs$ $"-)&9 r)c <tdgddgdgdddggd|S) zjBuild and return a Segment Anything Model 2 (SAM2) base-size model with specified architecture parameters.p)r4rrTr4)r3rrCrD)iirS)rrHr rIrJencoder_window_spatial_sizerKr"rLr%s r& build_sam2_brX_s+ $".)%'H&:  r)c 6tdgddgdgdgd|S)zeBuild and return a large-size Segment Anything Model 2 (SAM2) with specified architecture parameters.r4r;$r<r4)r!+r5r<rr5ii@i rZrGrLr%s r& build_sam2_lrams$ $".)&; r)cLd}d}d}||z} |rtddd|||gddddd ddd n9t|||d ttjj d ||dd|d| } t | t|| | f||fdtdtd|dd|ddgdgd} |ct|}t|d5} trtj| d ntj| } ddd| j | j| S#1swY,xYw)aT Build a Segment Anything Model (SAM) with specified encoder parameters. Args: encoder_embed_dim (int | list[int]): Embedding dimension for the encoder. encoder_depth (int | list[int]): Depth of the encoder. encoder_num_heads (int | list[int]): Number of attention heads in the encoder. encoder_global_attn_indexes (list[int] | None): Indexes for global attention in the encoder. checkpoint (str | None, optional): Path to the model checkpoint file. mobile_sam (bool, optional): Whether to build a Mobile-SAM model. Returns: (SAMModel): A Segment Anything Model instance with the specified architecture. Examples: >>> sam = _build_sam(768, 12, 12, [2, 5, 8, 11]) >>> sam = _build_sam([64, 128, 160, 320], [2, 2, 6, 2], [2, 4, 5, 10], None, mobile_sam=True) r+rrTi)rrrDrg@gFg?)img_sizein_chans num_classes embed_dimsdepths num_heads window_sizes mlp_ratio drop_ratedrop_path_rateuse_checkpointmbconv_expand_ratiolocal_conv_sizelayer_lr_decayr<gư>)epsTrD) depth embed_dimrdrk norm_layerri patch_sizeqkv_bias use_rel_posglobal_attn_indexes window_size out_chans)rtimage_embedding_sizeinput_image_size mask_in_chansr4ir5)rs embedding_dimmlp_dimri)num_multimask_outputs transformertransformer_dimiou_head_depthiou_head_hidden_dim)g33333^@gR]@gRY@)g(\2M@g(\L@gL@) image_encoderprompt_encoder mask_decoder pixel_mean pixel_stdNrb weights_only)rr rtorchnn LayerNormrr rrropenrloadload_state_dicteval)rrr r!r"r>prompt_embed_dim image_sizevit_patch_sizer|rsamf state_dicts r&r$r$zso4JN%7$ ! ( '& # "'uxx11t<'% ;&  %B #$&"68L!M(*5  !"#).  - #  -)+ C.+J7 *d # \q>HAE:ejjYZmJ \ J'HHJ J  \ \s <3DD#rr[r4rr`rr_c tt||||||td|ddgdd}tdd d t } t d } |duxrd|v} t d8id|d| d| dddddddddd dd dd dd dd d d d!d d"d d#d d$d d%d d&d d'd d(d)d*dd+d d,d-d.| d/| d0| d1td d2d34} |ft|}t|d55} trtj| d-6ntj| d7}ddd| j| j| S#1swY,xYw)9ae Build and return a Segment Anything Model 2 (SAM2) with specified architecture parameters. Args: encoder_embed_dim (int, optional): Embedding dimension for the encoder. encoder_stages (list[int], optional): Number of blocks in each stage of the encoder. encoder_num_heads (int, optional): Number of attention heads in the encoder. encoder_global_att_blocks (list[int], optional): Indices of global attention blocks in the encoder. encoder_backbone_channel_list (list[int], optional): Channel dimensions for each level of the encoder backbone. encoder_window_spatial_size (list[int], optional): Spatial size of the window for position embeddings. encoder_window_spec (list[int], optional): Window specifications for each stage of the encoder. checkpoint (str | None, optional): Path to the checkpoint file for loading pre-trained weights. Returns: (SAM2Model): A configured and initialized SAM2 model. Examples: >>> sam2_model = _build_sam2(encoder_embed_dim=96, encoder_stages=[1, 2, 7, 2]) >>> sam2_model.eval() )rtristagesglobal_att_blocks!window_pos_embed_bkg_spatial_size window_specrcr4rTnearest)d_modelbackbone_channel_listfpn_top_down_levelsfpn_interp_modelr)trunkneckscalpTr<)rpos_enc_at_input num_layerslayerr8)out_dimNzsam2.1rmemory_attentionmemory_encoder num_maskmemrrr+sigmoid_scale_for_mem_encg4@sigmoid_bias_for_mem_encg$$use_mask_input_as_output_without_samdirectly_add_no_mem_embeduse_high_res_features_in_sammultimask_output_in_samiou_prediction_use_sigmoiduse_obj_ptrs_in_encoderadd_tpos_enc_to_obj_ptrs"only_obj_ptrs_in_the_past_for_evalpred_obj_scorespred_obj_scores_mlpfixed_no_obj_ptrmultimask_output_for_trackinguse_multimask_token_for_obj_ptrmultimask_min_pt_numrmultimask_max_pt_numuse_mlp_for_obj_ptr_projcompile_image_encoderFno_obj_embed_spatialproj_tpos_enc_in_obj_ptrsuse_signed_tpos_enc_to_obj_ptrssam_mask_decoder_extra_argsg?g\(\?)dynamic_multimask_via_stability!dynamic_multimask_stability_delta"dynamic_multimask_stability_threshrrmodel)r r rrrr rdictrrrrrrr)rrHr rIrKrWrJr"rrr is_sam2_1sam2rrs r&rMrMs <!''!7.I+  "?!"A&  M"'sTVW_s_uv"2.N$&A8z+AI ! #! )! &!  !   !  #' ! "'! .2! #'! &*! !%! $(! !%! "&! ,0!  !! "!#! $%! &'+'! ()-)! *+! ,-! ."&/! 0$1! 2'3! 4#,5! 6)27! 8%),0.2/3% 9! DF+J7 *d # gq?I%**QU;uzzZ[}^efJ g Z(IIK K  g gs 6D==E) zsam_h.ptzsam_l.ptsam_b.ptz mobile_sam.ptz sam2_t.ptz sam2_s.ptz sam2_b.ptz sam2_l.ptz sam2.1_t.ptz sam2.1_s.ptz sam2.1_b.ptz sam2.1_l.ptcd}t|}tjD])}|j|stj |}+|s"t |dtj||S)a Build and return a Segment Anything Model (SAM) based on the provided checkpoint. Args: ckpt (str | Path, optional): Path to the checkpoint file or name of a pre-defined SAM model. Returns: (SAMModel | SAM2Model): A configured and initialized SAM or SAM2 model instance. Raises: FileNotFoundError: If the provided checkpoint is not a supported SAM model. Examples: >>> sam_model = build_sam("sam_b.pt") >>> sam_model = build_sam("path/to/custom_checkpoint.pt") Notes: Supported pre-defined models include: - SAM: 'sam_h.pt', 'sam_l.pt', 'sam_b.pt', 'mobile_sam.pt' - SAM2: 'sam2_t.pt', 'sam2_s.pt', 'sam2_b.pt', 'sam2_l.pt' Nz7 is not a supported SAM model. Available models are: )str sam_model_mapkeysendswithgetFileNotFoundError)ckpt model_builderks r& build_samrHsx,M t9D    !1 == )--a0M1 4&(`anasasau`v wxx  r))N)NF)r)& functoolsrrultralytics.utils.downloadsrultralytics.utils.torch_utilsrmodules.decodersrmodules.encodersrr r r r r modules.memory_attentionrr modules.samrrmodules.tiny_encoderrmodules.transformerrr'r0r6r?rNrQrXrar$rMrrrr)r&rs >4)iiK,)2     $ \@ -"7!"A%\@ %  r)