search

SforAiDl / vformer

A modular PyTorch library for vision transformer models
https://vformer.readthedocs.io/
MIT License
162 stars 22 forks source link

Add Convolutional Vision Transformers (CvT) #64

Closed alvanli closed 2 years ago

alvanli commented 2 years ago

Added model for CVT, not to be confused with CVT (Compact Vision Transformer) and ConViT

codecov-commenter commented 2 years ago

Codecov Report

Merging #64 (c182af2) into main (e1f4950) will not change coverage. The diff coverage is 100.00%.

@@            Coverage Diff             @@
##              main       #64    +/-   ##
==========================================
  Coverage   100.00%   100.00%            
==========================================
  Files           52        56     +4     
  Lines         1440      1617   +177     
==========================================
+ Hits          1440      1617   +177
Impacted Files Coverage Δ
vformer/attention/__init__.py 100.00% <100.00%> (ø)
vformer/attention/convvt.py 100.00% <100.00%> (ø)
vformer/encoder/__init__.py 100.00% <100.00%> (ø)
vformer/encoder/convvt.py 100.00% <100.00%> (ø)
vformer/encoder/embedding/__init__.py 100.00% <100.00%> (ø)
vformer/encoder/embedding/convvt.py 100.00% <100.00%> (ø)
vformer/models/classification/__init__.py 100.00% <100.00%> (ø)
vformer/models/classification/convvt.py 100.00% <100.00%> (ø)
NeelayS commented 2 years ago

Hi @alvanli, thank you for this PR! Could you please check whether it would be possible to add further tests to get the code coverage up to 100%? Thanks!

NeelayS commented 2 years ago

Thanks for that. I'll review this PR asap (most likely tomorrow).

NeelayS commented 2 years ago

Thanks for the changes @alvanli. LGTM!