Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

chore: update upn_decoder.py #7

Open
wants to merge 1 commit into
base: v1.0
Choose a base branch
from
Open

chore: update upn_decoder.py #7

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions chatrex/upn/models/decoder/upn_decoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
class DeformableTransformerDecoderLayer(nn.Module):
"""Deformable Transformer Decoder Layer. This is a modified version in Grounding DINO.
After the query is attented to the image feature, it is further attented to the text feature.
The excute order is: self_attn -> cross_attn to text -> cross_attn to image -> ffn
The execute order is: self_attn -> cross_attn to text -> cross_attn to image -> ffn
Args:
d_model (int): The dimension of keys/values/queries in :class:`MultiheadAttention`.
d_ffn (int): The dimension of the feedforward network model.
Expand Down Expand Up @@ -145,7 +145,7 @@ def forward(
@DECODERS.register_module()
class UPNDecoder(nn.Module):
"""Decoder used in UPN. Each layer is a DeformableTransformerDecoderLayer. The query
will be abled to attend the image feature and text feature. The excute order is:
will be abled to attend the image feature and text feature. The execute order is:
self_attn -> cross_attn to image -> ffn

Args:
Expand Down