config.json

{
  "architectures": [
    "Sam2VideoModel"
  ],
  "enable_occlusion_spatial_embedding": true,
  "enable_temporal_pos_encoding_for_object_pointers": true,
  "image_size": 1024,
  "initializer_range": 0.02,
  "mask_decoder_config": {
    "attention_downsample_rate": 2,
    "dynamic_multimask_stability_delta": 0.05,
    "dynamic_multimask_stability_thresh": 0.98,
    "dynamic_multimask_via_stability": true,
    "hidden_act": "gelu",
    "hidden_size": 256,
    "iou_head_depth": 3,
    "iou_head_hidden_dim": 256,
    "mlp_dim": 2048,
    "model_type": "",
    "num_attention_heads": 8,
    "num_hidden_layers": 2,
    "num_multimask_outputs": 3
  },
  "mask_downsampler_embed_dim": 256,
  "mask_downsampler_hidden_act": "gelu",
  "mask_downsampler_kernel_size": 3,
  "mask_downsampler_padding": 1,
  "mask_downsampler_stride": 2,
  "mask_downsampler_total_stride": 16,
  "max_object_pointers_in_encoder": 16,
  "memory_attention_downsample_rate": 1,
  "memory_attention_dropout": 0.1,
  "memory_attention_feed_forward_hidden_act": "relu",
  "memory_attention_feed_forward_hidden_size": 2048,
  "memory_attention_hidden_size": 256,
  "memory_attention_num_attention_heads": 1,
  "memory_attention_num_layers": 4,
  "memory_attention_rope_dropout": 0.1,
  "memory_attention_rope_feat_sizes": [
    64,
    64
  ],
  "memory_attention_rope_theta": 10000,
  "memory_encoder_hidden_size": 256,
  "memory_encoder_output_channels": 64,
  "memory_fuser_embed_dim": 256,
  "memory_fuser_hidden_act": "gelu",
  "memory_fuser_intermediate_dim": 1024,
  "memory_fuser_kernel_size": 7,
  "memory_fuser_layer_scale_init_value": 1e-06,
  "memory_fuser_num_layers": 2,
  "memory_fuser_padding": 3,
  "model_type": "sam2_video",
  "multimask_max_pt_num": 1,
  "multimask_min_pt_num": 0,
  "multimask_output_for_tracking": true,
  "multimask_output_in_sam": true,
  "num_maskmem": 7,
  "prompt_encoder_config": {
    "hidden_act": "gelu",
    "hidden_size": 256,
    "image_size": 1024,
    "layer_norm_eps": 1e-06,
    "mask_input_channels": 16,
    "model_type": "",
    "num_point_embeddings": 4,
    "patch_size": 16,
    "scale": 1
  },
  "sigmoid_bias_for_mem_enc": -10.0,
  "sigmoid_scale_for_mem_enc": 20.0,
  "torch_dtype": "float32",
  "transformers_version": "4.56.0.dev0",
  "vision_config": {
    "backbone_channel_list": [
      768,
      384,
      192,
      96
    ],
    "backbone_config": {
      "_name_or_path": "",
      "add_cross_attention": false,
      "architectures": null,
      "bad_words_ids": null,
      "begin_suppress_tokens": null,
      "blocks_per_stage": [
        1,
        2,
        7,
        2
      ],
      "bos_token_id": null,
      "chunk_size_feed_forward": 0,
      "cross_attention_hidden_size": null,
      "decoder_start_token_id": null,
      "diversity_penalty": 0.0,
      "do_sample": false,
      "early_stopping": false,
      "embed_dim_per_stage": [
        96,
        192,
        384,
        768
      ],
      "encoder_no_repeat_ngram_size": 0,
      "eos_token_id": null,
      "exponential_decay_length_penalty": null,
      "finetuning_task": null,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "global_attention_blocks": [
        5,
        7,
        9
      ],
      "hidden_act": "gelu",
      "hidden_size": 96,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "image_size": [
        1024,
        1024
      ],
      "initializer_range": 0.02,
      "is_decoder": false,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "layer_norm_eps": 1e-06,
      "length_penalty": 1.0,
      "max_length": 20,
      "min_length": 0,
      "mlp_ratio": 4.0,
      "model_type": "sam2_hiera_det_model",
      "no_repeat_ngram_size": 0,
      "num_attention_heads": 1,
      "num_attention_heads_per_stage": [
        1,
        2,
        4,
        8
      ],
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_channels": 3,
      "num_query_pool_stages": 3,
      "num_return_sequences": 1,
      "output_attentions": false,
      "output_hidden_states": false,
      "output_scores": false,
      "pad_token_id": null,
      "patch_kernel_size": [
        7,
        7
      ],
      "patch_padding": [
        3,
        3
      ],
      "patch_stride": [
        4,
        4
      ],
      "prefix": null,
      "problem_type": null,
      "pruned_heads": {},
      "query_stride": [
        2,
        2
      ],
      "remove_invalid_values": false,
      "repetition_penalty": 1.0,
      "return_dict": true,
      "return_dict_in_generate": false,
      "sep_token_id": null,
      "suppress_tokens": null,
      "task_specific_params": null,
      "temperature": 1.0,
      "tf_legacy_loss": false,
      "tie_encoder_decoder": false,
      "tie_word_embeddings": true,
      "tokenizer_class": null,
      "top_k": 50,
      "top_p": 1.0,
      "torch_dtype": null,
      "torchscript": false,
      "typical_p": 1.0,
      "use_bfloat16": false,
      "window_positional_embedding_background_size": [
        7,
        7
      ],
      "window_size_per_stage": [
        8,
        4,
        14,
        7
      ]
    },
    "backbone_feature_sizes": [
      [
        256,
        256
      ],
      [
        128,
        128
      ],
      [
        64,
        64
      ]
    ],
    "fpn_hidden_size": 256,
    "fpn_kernel_size": 1,
    "fpn_padding": 0,
    "fpn_stride": 1,
    "fpn_top_down_levels": [
      2,
      3
    ],
    "hidden_act": "gelu",
    "initializer_range": 0.02,
    "layer_norm_eps": 1e-06,
    "model_type": "sam2_vision_model",
    "num_feature_levels": 3
  }
}