profile
viewpoint
If you are wondering where the data of this site comes from, please visit https://api.github.com/users/dabrahams/events. GitMemory does not store any data, but only uses NGINX to cache data for a period of time. The idea behind GitMemory is simply to give users a better reading experience.
Dave Abrahams dabrahams Google Mountain View, CA http://daveabrahams.com Swift and C+ language/library designer, professor of blowing-your-mind.

apple/swift 56373

The Swift Programming Language

apple/llvm-project 395

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. This fork is used to manage Apple’s stable releases of Clang as well as support the Swift project.

dabrahams/DivideAndConquer 14

Demonstrates a fix for the mutating divide-and-conquer COW problem

dabrahams/dwamacs 10

My personal emacs configuration stuff

dabrahams/bbproto 9

Buildbot Configuration Prototype

dabrahams/fglrx-support 4

Various files needed to get the ATI Proprietary Linux driver to work

dabrahams/dotemacs 3

An emacs configuration that is not encumbered by GPLv3

dabrahams/elisp 3

Now-retired personal Emacs configuration files and packages

dabrahams/0compile 1

Porting 0compile to windows

push eventtensorflow/model-optimization

Ethan Kim

commit sha 0d35b800d1a051afaab404d6d535a74b7714ff41

Remove @staticmethod PiperOrigin-RevId: 380484127

view details

push time in 8 hours

push eventtensorflow/model-optimization

Elena Zhelezina

commit sha 19b532235b806685749292a684ae7ccc9d2af66f

Fixed clustering for Conv3D. Change-Id: Ic1ee16760d9643b8142e5644d6cb68a6890bc621

view details

Elena Zhelezina

commit sha 647d6436b494b7d4723a3213aefaa15920a00c42

Merge branch 'upstream/master' into conv3d_bug_clustering Change-Id: Ic20345f29b6548e7eabf34fe5488654284987a83

view details

Peng Sun

commit sha 6917424dbdb00e376c0798080f1a2e15390e1243

Added fix bug for clustering with Conv1D Change-Id: Icd0acb2c5a671d4cafc3222fcc4d8098716b3f73

view details

Elena Zhelezina

commit sha 8ff951c5c18f90194d006033aae240e622a21b31

Merge branch 'master' into conv3d_bug_clustering

view details

Elena Zhelezina

commit sha 0779443ccbf739d8d710cee6746c228775eaabcf

Resolved small issues after updating with master. Change-Id: If55e372e7f13fc032f4b85d7e449ed0ecaf6a873

view details

Elena Zhelezina

commit sha 42f45580429242813c100e9f50c5a110103cd54f

Small fix after updating with master. Change-Id: Ib4331480e2d29a24973a15fb5d2cbcf05e051b91

view details

Elena Zhelezina

commit sha 41be2658955b4153ea4ca4145f731c8ff21e4cb9

Addressing comments: 1. Nits: Docstring corrections 2. Simplify clunky code in get_pulling_indices Change-Id: I3c6818099fab1c9b844620cd1dfad6e97efeb0fd

view details

Elena Zhelezina

commit sha d2a916d5a23c2d2949d3cac74adb8734fde11ebc

Removed clustering registry completely. Change-Id: I367607cb123404f72da7b4a592a70d154d14ed13

view details

Elena Zhelezina

commit sha 3cc9cf7369b82cf789aaac9d587e1c26e7755cb9

Merge branch 'master' into conv3d_bug_clustering

view details

Elena Zhelezina

commit sha fa56571985eeec6d7a712a87b40fece71fbdd8b7

Merge branch 'master' into conv3d_bug_clustering

view details

Elena Zhelezina

commit sha f0f5342f6e61bfc0dc9b4bd07695c611b3f00caa

Small correction after merging with master. Change-Id: Ied79f7dfe484770d41dc9b08ae3b5acdbd970e54

view details

Elena Zhelezina

commit sha 6b284bb068cbc0ef7265f248e4b65a93fb04ad31

Merge branch 'master' into conv3d_bug_clustering

view details

A. Unique TensorFlower

commit sha 3e7f162cff17e0990562ed5900039978507065ea

Merge pull request #609 from wwwind:conv3d_bug_clustering PiperOrigin-RevId: 380746962

view details

Ethan Kim

commit sha 27080bbe2320acbab688a66e29ec3724b775a9d5

Remove @staticmethod PiperOrigin-RevId: 380484127

view details

push time in 8 hours

push eventtensorflow/model-optimization

Elena Zhelezina

commit sha 19b532235b806685749292a684ae7ccc9d2af66f

Fixed clustering for Conv3D. Change-Id: Ic1ee16760d9643b8142e5644d6cb68a6890bc621

view details

Elena Zhelezina

commit sha 647d6436b494b7d4723a3213aefaa15920a00c42

Merge branch 'upstream/master' into conv3d_bug_clustering Change-Id: Ic20345f29b6548e7eabf34fe5488654284987a83

view details

Peng Sun

commit sha 6917424dbdb00e376c0798080f1a2e15390e1243

Added fix bug for clustering with Conv1D Change-Id: Icd0acb2c5a671d4cafc3222fcc4d8098716b3f73

view details

Elena Zhelezina

commit sha 8ff951c5c18f90194d006033aae240e622a21b31

Merge branch 'master' into conv3d_bug_clustering

view details

Elena Zhelezina

commit sha 0779443ccbf739d8d710cee6746c228775eaabcf

Resolved small issues after updating with master. Change-Id: If55e372e7f13fc032f4b85d7e449ed0ecaf6a873

view details

Elena Zhelezina

commit sha 42f45580429242813c100e9f50c5a110103cd54f

Small fix after updating with master. Change-Id: Ib4331480e2d29a24973a15fb5d2cbcf05e051b91

view details

Elena Zhelezina

commit sha 41be2658955b4153ea4ca4145f731c8ff21e4cb9

Addressing comments: 1. Nits: Docstring corrections 2. Simplify clunky code in get_pulling_indices Change-Id: I3c6818099fab1c9b844620cd1dfad6e97efeb0fd

view details

Elena Zhelezina

commit sha d2a916d5a23c2d2949d3cac74adb8734fde11ebc

Removed clustering registry completely. Change-Id: I367607cb123404f72da7b4a592a70d154d14ed13

view details

Elena Zhelezina

commit sha 3cc9cf7369b82cf789aaac9d587e1c26e7755cb9

Merge branch 'master' into conv3d_bug_clustering

view details

Elena Zhelezina

commit sha fa56571985eeec6d7a712a87b40fece71fbdd8b7

Merge branch 'master' into conv3d_bug_clustering

view details

Elena Zhelezina

commit sha f0f5342f6e61bfc0dc9b4bd07695c611b3f00caa

Small correction after merging with master. Change-Id: Ied79f7dfe484770d41dc9b08ae3b5acdbd970e54

view details

Elena Zhelezina

commit sha 6b284bb068cbc0ef7265f248e4b65a93fb04ad31

Merge branch 'master' into conv3d_bug_clustering

view details

A. Unique TensorFlower

commit sha 3e7f162cff17e0990562ed5900039978507065ea

Merge pull request #609 from wwwind:conv3d_bug_clustering PiperOrigin-RevId: 380746962

view details

push time in 9 hours

PR merged tensorflow/model-optimization

[Clustering] Fixing the bug in clustering for Conv1D/Conv3D api-review cla: yes ready to pull technique:clustering

There is a bug in clustering for Conv1D/Conv3D. We used the layout for Conv2D and this is wrong, because tensors for Conv1D/ Conv3D have different ranks. Tests for both cases are added.

+119 -319

13 comments

7 changed files

wwwind

pr closed time in 9 hours

push eventtensorflow/model-optimization

Ethan Kim

commit sha 6700c5f6a1b1d8f793b9aae2c766bed3fd55056d

Remove @staticmethod PiperOrigin-RevId: 380484127

view details

push time in 9 hours

push eventtensorflow/model-optimization

Ethan Kim

commit sha c0f1a94ffb0e2f4e7dcdfe207f6de0a6d9a7a7b7

Remove @staticmethod PiperOrigin-RevId: 380484127

view details

push time in 10 hours

PR opened tensorflow/model-optimization

[Pruning] Draft implementation of structured pruning 2x4.

This is the draft of the implementation of structured pruning 2x4: for block of 4 elements we zero 2 elements with the smallest absolute magnitude. The testing on different networks is in progress.

API change: there is additional parameter: sparsity_2x4. When it is set to True, then the layer is pruned using this type of sparsity. pruning_params.update({"sparsity_2x4": True})

There are several assumptions done in this implementation:

  • we apply this type of pruning only to Conv2D and Dense layers;
  • in case of Conv2D, pruning is done in channels dimension, in case of Dense layer - width dimension;
  • if the weight dimension is not divisible by 4, then we don't do any pruning;

Added a simple example of CNN on mnist: mnist_e2e_sparsity2x4.py Added a small tool that checks weights in .tflite file: check_sparsity_2x4.py

+592 -8

0 comment

9 changed files

pr created time in a day

PR closed tensorflow/model-optimization

remove tensorflow uninstall and tf-nightly cla: yes technique:qat

Google Colab no longer requires the TF nightly build, which is causing errors. Using the installed TF is sufficient

+0 -2

6 comments

1 changed file

jar

pr closed time in a day

pull request commenttensorflow/model-optimization

remove tensorflow uninstall and tf-nightly

CLAs look good, thanks!

ℹ️ Googlers: Go here for more info.

<!-- ok -->

jar

comment created time in a day

pull request commenttensorflow/model-optimization

remove tensorflow uninstall and tf-nightly

CLAs look good, thanks!

ℹ️ Googlers: Go here for more info.

<!-- ok -->

jar

comment created time in a day

pull request commenttensorflow/model-optimization

remove tensorflow uninstall and tf-nightly

@googlebot I signed it!

jar

comment created time in a day

pull request commenttensorflow/model-optimization

remove tensorflow uninstall and tf-nightly

Thanks for your pull request. It looks like this may be your first contribution to a Google open source project (if not, look below for help). Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

:memo: Please visit https://cla.developers.google.com/ to sign.

Once you've signed (or fixed any issues), please reply here with @googlebot I signed it! and we'll verify it.


What to do if you already signed the CLA

Individual signers
Corporate signers

ℹ️ Googlers: Go here for more info.

<!-- need_sender_cla -->

jar

comment created time in a day

pull request commenttensorflow/model-optimization

remove tensorflow uninstall and tf-nightly

Thanks for your pull request. It looks like this may be your first contribution to a Google open source project (if not, look below for help). Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

:memo: Please visit https://cla.developers.google.com/ to sign.

Once you've signed (or fixed any issues), please reply here with @googlebot I signed it! and we'll verify it.


What to do if you already signed the CLA

Individual signers
Corporate signers

ℹ️ Googlers: Go here for more info.

<!-- need_sender_cla -->

jar

comment created time in a day

pull request commenttensorflow/model-optimization

remove tensorflow uninstall and tf-nightly

Check out this pull request on  <a href="https://app.reviewnb.com/tensorflow/model-optimization/pull/742"><img align="absmiddle" alt="ReviewNB" height="28" class="BotMessageButtonImage" src="https://raw.githubusercontent.com/ReviewNB/support/master/images/button_reviewnb.png"/></a>

See visual diffs & provide feedback on Jupyter Notebooks.


<i>Powered by <a href='https://www.reviewnb.com/?utm_source=gh'>ReviewNB</a></i>

jar

comment created time in a day

PR opened tensorflow/model-optimization

remove tensorflow uninstall and tf-nightly

Google Colab no longer requires the TF nightly build, which is causing errors. Using the installed TF is sufficient

+0 -2

0 comment

1 changed file

pr created time in a day

PR opened tensorflow/model-optimization

Add support for Pruning callback function in Model garden trainer

Add support for Pruning callback function in Model garden trainer

+21 -0

0 comment

1 changed file

pr created time in a day

create barnchtensorflow/model-optimization

branch : test_380577575

created branch time in a day

push eventtensorflow/model-optimization

Ethan Kim

commit sha 6f6142bb2cdd8b3fdad004d54dc74fd2bd5a42b6

Remove @staticmethod PiperOrigin-RevId: 380484127

view details

push time in a day

PR opened tensorflow/model-optimization

Remove @staticmethod

Remove @staticmethod

+3 -7

0 comment

1 changed file

pr created time in a day

create barnchtensorflow/model-optimization

branch : test_380484127

created branch time in a day

delete branch tensorflow/model-optimization

delete branch : test_379651386

delete time in 2 days

PR merged tensorflow/model-optimization

Update release notes for 0.6.0. cla: yes

Update release notes for 0.6.0.

+17 -3

0 comment

2 changed files

copybara-service[bot]

pr closed time in 2 days

push eventtensorflow/model-optimization

David Rim

commit sha bd7396d04e0b1da82cac0b9004ded060f5185f71

Update release notes for 0.6.0. PiperOrigin-RevId: 380482539

view details

push time in 2 days

push eventtensorflow/model-optimization

David Rim

commit sha bd7396d04e0b1da82cac0b9004ded060f5185f71

Update release notes for 0.6.0. PiperOrigin-RevId: 380482539

view details

push time in 2 days

push eventtensorflow/model-optimization

David Rim

commit sha dc5852728e9b84df324db8710208c009ab03f63f

Update release notes for 0.6.0. PiperOrigin-RevId: 379651386

view details

push time in 2 days

starteddabrahams/initsplit

started time in 4 days

created tagtensorflow/model-optimization

tagv0.6.0

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

created time in 4 days

PR opened tensorflow/model-optimization

Update release notes

Update release notes

+17 -3

0 comment

2 changed files

pr created time in 4 days

create barnchtensorflow/model-optimization

branch : test_379651386

created branch time in 4 days

PR opened tensorflow/model-optimization

Move collaborative optimizations out of the experimental API package

Move collaborative optimizations out of the experimental API package

Clustering and sparsity preserving quantization schemes are now available in tfmot.sparsity.keras.quantization.collaborative_optimizations

+2 -20

0 comment

6 changed files

pr created time in 5 days