lucidrains/deformable-attention
Implementation of Deformable Attention in Pytorch from the paper "Vision Transformer with Deformable Attention"
PythonMIT
Issues
- 1
Padding function in Line 25 of deformable_attention_1d.py should pad for h not w.
#10 opened by CyberPegasus - 0
The means of vgrid?
#9 opened by BrunoQin - 0
1d deformable attention
#8 opened by zhengchunge - 2
Should be 'xy' instead of 'ij'?
#6 opened by kareido - 0
Controlling the number of keys per query
#5 opened by tdchua - 0
- 1
- 4
- 2
What the 'bug' means?
#1 opened by HAN-oQo