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

Jump to bottom

CCT and CVT #39

Merged
merged 18 commits into from
Dec 3, 2021
Merged

CCT and CVT #39

merged 18 commits into from
Dec 3, 2021

Conversation

abhi-glitchhg
Copy link
Member

will fix #4

@abhi-glitchhg
[WIP]
bfab0d3 
*added embedding, (in paper they refer this as tokenizer)
*added encoder and classification model
*added tests
@abhi-glitchhg
[WIP]
646e0d8 
*added test for classification model
@abhi-glitchhg
[WIP]
3183ea9 
*added test for classification model
@abhi-glitchhg abhi-glitchhg marked this pull request as draft November 27, 2021 11:13
@codecov-commenter
Copy link

codecov-commenter commented Nov 27, 2021 •
edited
Loading

Codecov Report

Merging #39 (62063a6) into main (24def8c) will decrease coverage by 0.19%.
The diff coverage is 98.55%.

@@             Coverage Diff             @@
##              main      #39      +/-   ##
===========================================
- Coverage   100.00%   99.80%   -0.20%     
===========================================
  Files           45       48       +3     
  Lines          895     1031     +136     
===========================================
+ Hits           895     1029     +134     
- Misses           0        2       +2
Impacted Files Coverage Δ
vformer/encoder/pyramid.py 100.00% <ø> (ø)
vformer/models/dense/PVT/segmentation.py 100.00% <ø> (ø)
vformer/models/classification/cvt.py 96.66% <96.66%> (ø)
vformer/encoder/embedding/__init__.py 100.00% <100.00%> (ø)
vformer/encoder/embedding/cvt.py 100.00% <100.00%> (ø)
vformer/encoder/vanilla.py 100.00% <100.00%> (ø)
vformer/models/classification/__init__.py 100.00% <100.00%> (ø)
vformer/models/classification/cct.py 100.00% <100.00%> (ø)

abhi-glitchhg and others added 8 commits November 27, 2021 16:50
@abhi-glitchhg
[WIP]
7b10192 
pre-commit resolved
@abhi-glitchhg
[WIP]
307d58b 
pre-commit resolved
@abhi-glitchhg
[WIP]
1265475 
*added CCT
@abhi-glitchhg
[WIP]
46e747f 
*precommit issue resolved
@abhi-glitchhg
[WIP]
c9b99b9 
*fixed a bug in cvt encoder
@abhi-glitchhg
Merge branch 'SforAiDl:main' into CCT_CVT
57acef2
@abhi-glitchhg
[WIP]
158b133 
*Added Docstring
@abhi-glitchhg
[WIP]
99c19b2 
*coverage
@abhi-glitchhg abhi-glitchhg marked this pull request as ready for review December 2, 2021 11:04
@abhi-glitchhg
[WIP]
f074bde 
*changed readme file-
Added citations for crossvit and compact transformer
Added references for crossvit and compact transformer
@abhi-glitchhg
Modified test_models.py, now
7739c23 
Coverage = 100%
@abhi-glitchhg
Pre-commit resolved
a9657a9
NeelayS
NeelayS requested changes Dec 3, 2021
View reviewed changes
Copy link
Member

@NeelayS NeelayS left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@abhi-glitchhg I've added a few comments, please check.

README.md Show resolved Hide resolved
tests/test_models.py Show resolved Hide resolved
tests/test_models.py Show resolved Hide resolved
vformer/encoder/cvt.py Outdated Show resolved Hide resolved
vformer/encoder/cvt.py Outdated Show resolved Hide resolved
vformer/encoder/embedding/cvt.py Show resolved Hide resolved
vformer/encoder/embedding/cvt.py Outdated Show resolved Hide resolved
vformer/models/classification/cct.py Show resolved Hide resolved
vformer/models/classification/cvt.py Show resolved Hide resolved
@NeelayS NeelayS merged commit 76d688c into SforAiDl:main Dec 3, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@NeelayS NeelayS NeelayS requested changes

Assignees
No one assigned
Labels
Paper implementation
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

[Paper] Escaping the Big Data Paradigm with Compact Transformers
3 participants
@abhi-glitchhg @codecov-commenter @NeelayS