configs/sam2_hiera_base_plus.yaml

# @package _global_

# Model
backbone:
  _target_: models.backbones.image_encoder.ImageEncoder
  scalp: 1
  trunk:
    _target_: models.backbones.hieradet.Hiera
    embed_dim: 112
    num_heads: 2
  neck:
    _target_: models.backbones.image_encoder.FpnNeck
    position_encoding:
      _target_: models.position_encoding.PositionEmbeddingSine
      num_pos_feats: 256
      normalize: true
      scale: null
      temperature: 10000
    d_model: 256
    backbone_channel_list: [896, 448, 224, 112]
    fpn_top_down_levels: [2, 3]  # output level 0 and 1 directly use the backbone features
    fpn_interp_model: nearest

  
#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