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.

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

Add support for Bayesian neural network quantization #23

Merged
merged 71 commits into from
Jun 27, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
71 commits
Select commit Hold shift + click to select a range
793da93
Update links in README.md
ranganathkrishnan Oct 5, 2021
b924510
update MOPED layer example utility function
ranganathkrishnan Oct 5, 2021
81648f9
fix minor typo.
ranganathkrishnan Oct 5, 2021
a506530
Update README.md
ranganathkrishnan Oct 5, 2021
ade5f9b
feat: add possibility to return no kl, save it as attribute
piEsposito Nov 26, 2021
037006d
feat: add possibility to return no kl on flipout layers, save it as a…
piEsposito Nov 26, 2021
f892b95
updates to support dnn to bnn imodel auto conversion
msubedar Dec 8, 2021
161bfdf
updates to support dnn to bnn imodel auto conversion
msubedar Dec 8, 2021
b2f81a3
Update README.md
ranganathkrishnan Dec 16, 2021
42724f5
Update README.md
ranganathkrishnan Dec 16, 2021
d8b9940
update the posterior variational param init value
ranganathkrishnan Dec 16, 2021
8d4e136
remove duplicate kl_loss definition in Conv1dReparameterization layer
ranganathkrishnan Dec 16, 2021
bc6681b
include kl_loss() function in Convolutional flipout layers,
ranganathkrishnan Dec 16, 2021
06922f8
Update release version with dnn_to_bnn() feature
ranganathkrishnan Dec 16, 2021
fa51c94
Update README.md
ranganathkrishnan Jan 13, 2022
c3ca3f8
Update requirements.txt
ranganathkrishnan Jan 17, 2022
de85018
Include training, testing and uncertainty quantification snippet in R…
ranganathkrishnan Jan 18, 2022
57ac5df
update version in setup.py
ranganathkrishnan Jan 18, 2022
e38d696
Update bayesian_torch.layers.md
ranganathkrishnan Jan 26, 2022
7d343e5
Update links in README.md
ranganathkrishnan Jan 26, 2022
83fe717
Update setup.py
ranganathkrishnan Jan 26, 2022
7c6df36
Update README.md
ranganathkrishnan Jan 27, 2022
3acddc9
include assets folder
ranganathkrishnan Jan 28, 2022
cbff73c
Update README.md
ranganathkrishnan Jan 28, 2022
a081d57
Update README.md
ranganathkrishnan Jan 28, 2022
f0207c0
Update README.md
ranganathkrishnan Jan 28, 2022
3793ce5
Update README.md
ranganathkrishnan Jan 28, 2022
b71fc17
Update setup.py
ranganathkrishnan Jan 28, 2022
5019bf9
release to PyPI, update install instruction through "pip" command
ranganathkrishnan Jan 31, 2022
7e8d246
Switched to permanent URL for the top image.
michaelbeale-IL Jan 31, 2022
bf8c3e3
changing to raw.githubusercontent.com Url for top image.
michaelbeale-IL Jan 31, 2022
3ca0190
Update README.md
michaelbeale-IL Jan 31, 2022
a8cb7eb
update links and release number for PyPI documentation
ranganathkrishnan Jan 31, 2022
a5750c7
Update README.md
ranganathkrishnan Feb 9, 2022
789657d
update download count badge
ranganathkrishnan Mar 3, 2022
5802ef9
implement quantized convolution variational layers
junliang-lin Nov 14, 2022
d910ae8
replace hardcoded variables with function parameters and add comments
junliang-lin Nov 30, 2022
878c3f2
implement quantized linear variational layer
junliang-lin Dec 5, 2022
9c1493a
update init file
junliang-lin Dec 5, 2022
7a89b6d
quantized linear variational layer
junliang-lin Dec 5, 2022
3ea51a5
quantized conv flipout layers
junliang-lin Dec 5, 2022
5b696ae
quantized linear flipout layer
junliang-lin Dec 5, 2022
33986eb
template for quantized transposed conv1d flipout layer
junliang-lin Dec 5, 2022
3e39d22
quantized flipout layers
junliang-lin Dec 7, 2022
61c3407
update init file
junliang-lin Dec 7, 2022
f647bcf
update name list
junliang-lin Dec 7, 2022
9524bc0
bnn to qbnn conversion
junliang-lin Dec 7, 2022
3930c61
Merge remote-tracking branch (#5)
junliang-lin Feb 6, 2023
f3f32e8
add kl flag for BNN to QBNN conversion
junliang-lin Feb 7, 2023
b0a99d2
resolve merge conflicts
junliang-lin Feb 10, 2023
44ab990
Merge branch 'main' into feature/kl_flag
junliang-lin Feb 10, 2023
5c691d6
quantized flipout models
junliang-lin Feb 13, 2023
51385b3
remove kl computations
junliang-lin Feb 13, 2023
525c462
quantization directory structure
junliang-lin Feb 14, 2023
3360bcf
example for prepare function
junliang-lin Feb 14, 2023
51bab43
quantization prepare function
junliang-lin Feb 20, 2023
df09408
import quantization module
junliang-lin Feb 20, 2023
b4ce3f5
finish quantization function
junliang-lin Feb 20, 2023
9b5a9dc
quantization module prototype
junliang-lin Mar 2, 2023
9b0118f
bnn to qbnn
junliang-lin Mar 3, 2023
b780aad
qbnn example
junliang-lin Mar 6, 2023
87488e2
qbnn performance test
junliang-lin Mar 6, 2023
1e8bd69
fix accuracy drop
junliang-lin Mar 7, 2023
b3d9980
support load and store quantized models
junliang-lin Mar 14, 2023
ccc52ee
calibration support for quantized flipout layers
junliang-lin Mar 14, 2023
17480e6
fix qconv2d flipout layers
junliang-lin Mar 19, 2023
18b296f
modify the bias to a torch.Parameter to allow for JIT tracing
junliang-lin Mar 29, 2023
69dc4db
pre-sampling for flipout layers
junliang-lin Mar 29, 2023
c3e47ed
fix input
junliang-lin Apr 19, 2023
86adb6d
fix batchnorm
junliang-lin Apr 19, 2023
d9a26a5
Merge branch 'main' into quantization
junliang-lin Apr 26, 2023
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
1 change: 1 addition & 0 deletions bayesian_torch/__init__.py
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
from bayesian_torch import quantization as quantization
Empty file added bayesian_torch/ao/__init__.py
Empty file.
Empty file.
Empty file.
Loading