Update Configs/sam2_hiera_large.yaml

Configs/sam2_hiera_large.yaml

@@ -24,7 +24,7 @@ model:
         temperature: 10000
       d_model: 256
       backbone_channel_list: [1152, 576, 288, 144]
-      fpn_top_down_levels: [2, 3]  # output level 0 and 1 directly use the backbone features
+      fpn_top_down_levels: [2, 3]
       fpn_interp_model: nearest
 
   memory_attention:
@@ -82,36 +82,24 @@ model:
         kernel_size: 7
         padding: 3
         layer_scale_init_value: 1e-6
-        use_dwconv: true  # depth-wise convs
+        use_dwconv: true
       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
-  # SAM decoder
   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
-  no_obj_embed_spatial: 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: true
-  proj_tpos_enc_in_obj_ptrs: true
-  use_signed_tpos_enc_to_obj_ptrs: 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