diff --git a/segment_anything_fast/modeling/image_encoder.py b/segment_anything_fast/modeling/image_encoder.py index 540cd78..369c6de 100644 --- a/segment_anything_fast/modeling/image_encoder.py +++ b/segment_anything_fast/modeling/image_encoder.py @@ -346,7 +346,6 @@ def add_decomposed_rel_pos( Calculate decomposed Relative Positional Embeddings from :paper:`mvitv2`. https://github.com/facebookresearch/mvit/blob/19786631e330df9f3622e5402b4a419a263a2c80/mvit/models/attention.py # noqa B950 Args: - attn (Tensor): attention map. q (Tensor): query q in the attention layer with shape (B, q_h * q_w, C). rel_pos_h (Tensor): relative position embeddings (Lh, C) for height axis. rel_pos_w (Tensor): relative position embeddings (Lw, C) for width axis.