About Visual Prompt Encoder.

[fuweifu-vtoo]

Dear author, I have another question for you：

In Visual Prompt Encoder, is it stacking three layers of deformable cross-attention layer, then connecting one self attention and one FFN?

Or stacking three blocks of (Deformable cross attention + self attention + FFN)

[Mountchicken]

three blocks of (Deformable cross attention + self attention + FFN)

[pisiguiii]

Hi @Mountchicken

Previously you referred to code from Grounding DINO:
#85 (comment)
, the DeformableTransformerDecoderLayer class.
I would like to clarify, when you mention "Deformable cross attention" do you mean DeformableTransformerDecoderLayer or the only self.cross_attn module from this class?

If I understood correctly, then
DeformableTransformerDecoderLayer == (Deformable cross attention + self attention + FFN)
Am I right in my conclusions?

[Mountchicken]

The visual prompt encoder consists of serval DeformableTransformerDecoderLayer