configs/sam2_hiera_s.yaml

# @package _global_

# Model
model:
  _target_: sam2.modeling.sam2_base.SAM2Base
  image_encoder:
    _target_: sam2.modeling.backbones.image_encoder.ImageEncoder
    scalp: 1
    trunk:
      _target_: sam2.modeling.backbones.hieradet.Hiera
      embed_dim: 96
      num_heads: 1
      stages: [1, 2, 11, 2]
      global_att_blocks: [7, 10, 13]
      window_pos_embed_bkg_spatial_size: [7, 7]
    neck:
      _target_: sam2.modeling.backbones.image_encoder.FpnNeck
      position_encoding:
        _target_: sam2.modeling.position_encoding.PositionEmbeddingSine
        num_pos_feats: 256
        normalize: true
        scale: null
        temperature: 10000
      d_model: 256
      backbone_channel_list: [768, 384, 192, 96]
      fpn_top_down_levels: [2, 3]  # output level 0 and 1 directly use the backbone features
      fpn_interp_model: nearest

  memory_attention:
    _target_: sam2.modeling.memory_attention.MemoryAttention
    d_model: 256
    pos_enc_at_input: true
    layer:
      _target_: sam2.modeling.memory_attention.MemoryAttentionLayer
      activation: relu
      dim_feedforward: 2048
      dropout: 0.1
      pos_enc_at_attn: false
      self_attention:
        _target_: sam2.modeling.sam.transformer.RoPEAttention
        rope_theta: 10000.0
        feat_sizes: [32, 32]
        embedding_dim: 256
        num_heads: 1
        downsample_rate: 1
        dropout: 0.1
      d_model: 256
      pos_enc_at_cross_attn_keys: true
      pos_enc_at_cross_attn_queries: false
      cross_attention:
        _target_: sam2.modeling.sam.transformer.RoPEAttention
        rope_theta: 10000.0
        feat_sizes: [32, 32]
        rope_k_repeat: True
        embedding_dim: 256
        num_heads: 1
        downsample_rate: 1
        dropout: 0.1
        kv_in_dim: 64
    num_layers: 4

  memory_encoder:
      _target_: sam2.modeling.memory_encoder.MemoryEncoder
      out_dim: 64
      position_encoding:
        _target_: sam2.modeling.position_encoding.PositionEmbeddingSine
        num_pos_feats: 64
        normalize: true
        scale: null
        temperature: 10000
      mask_downsampler:
        _target_: sam2.modeling.memory_encoder.MaskDownSampler
        kernel_size: 3
        stride: 2
        padding: 1
      fuser:
        _target_: sam2.modeling.memory_encoder.Fuser
        layer:
          _target_: sam2.modeling.memory_encoder.CXBlock
          dim: 256
          kernel_size: 7
          padding: 3
          layer_scale_init_value: 1e-6
          use_dwconv: True  # depth-wise convs
        num_layers: 2

  num_maskmem: 7
  image_size: 1024
  # apply scaled sigmoid on mask logits for memory encoder, and directly feed input mask as output mask
  sigmoid_scale_for_mem_enc: 20.0
  sigmoid_bias_for_mem_enc: -10.0
  use_mask_input_as_output_without_sam: true
  # Memory
  directly_add_no_mem_embed: true
  # use high-resolution feature map in the SAM mask decoder
  use_high_res_features_in_sam: true
  # output 3 masks on the first click on initial conditioning frames
  multimask_output_in_sam: true
  # SAM heads
  iou_prediction_use_sigmoid: True
  # cross-attend to object pointers from other frames (based on SAM output tokens) in the encoder
  use_obj_ptrs_in_encoder: true
  add_tpos_enc_to_obj_ptrs: false
  only_obj_ptrs_in_the_past_for_eval: true
  # object occlusion prediction
  pred_obj_scores: true
  pred_obj_scores_mlp: true
  fixed_no_obj_ptr: true
  # multimask tracking settings
  multimask_output_for_tracking: true
  use_multimask_token_for_obj_ptr: true
  multimask_min_pt_num: 0
  multimask_max_pt_num: 1
  use_mlp_for_obj_ptr_proj: true
  # Compilation flag
  compile_image_encoder: False