Skip to content

Commit 3327f63

Browse files
Merge pull request #800 from MohamedNourArm:toupstream/pcqat_example_notebook
PiperOrigin-RevId: 394394607
2 parents 27b267a + 7ceff63 commit 3327f63

File tree

3 files changed

+708
-6
lines changed

3 files changed

+708
-6
lines changed

tensorflow_model_optimization/g3doc/_book.yaml

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -59,6 +59,8 @@ upper_tabs:
5959
path: /model_optimization/guide/combine/cqat_example
6060
- title: Sparsity preserving quantization
6161
path: /model_optimization/guide/combine/pqat_example
62+
- title: Sparsity and cluster preserving quantization
63+
path: /model_optimization/guide/combine/pcqat_example
6264
- title: Sparsity preserving clustering
6365
path: /model_optimization/guide/combine/sparse_clustering_example
6466

tensorflow_model_optimization/g3doc/guide/combine/collaborative_optimization.md

Lines changed: 12 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -30,12 +30,12 @@ clustering doesn't preserve the sparsity introduced by the pruning API. To solve
3030
this problem, we introduce the following experimental collaborative optimization
3131
techniques:
3232

33-
* [Sparsity preserving clustering](https://github.com/tensorflow/model-optimization/pull/520)
34-
* [Sparsity preserving quantization aware training](https://github.com/tensorflow/model-optimization/pull/568)
33+
* [Sparsity preserving clustering](https://www.tensorflow.org/model_optimization/guide/combine/sparse_clustering_example)
34+
* [Sparsity preserving quantization aware training](https://www.tensorflow.org/model_optimization/guide/combine/pqat_example)
3535
(PQAT)
36-
* [Cluster preserving quantization aware training](https://github.com/tensorflow/model-optimization/pull/617)
36+
* [Cluster preserving quantization aware training](https://www.tensorflow.org/model_optimization/guide/combine/cqat_example)
3737
(CQAT)
38-
* Sparsity and cluster preserving quantization aware training (PCQAT) - WIP
38+
* [Sparsity and cluster preserving quantization aware training](https://www.tensorflow.org/model_optimization/guide/combine/pcqat_example)
3939

4040
These provide several deployment paths that could be used to compress a machine
4141
learning model and to take advantage of hardware acceleration at inference time.
@@ -108,5 +108,11 @@ with PQAT and CQAT collaborative optimization paths.
108108

109109
## Examples
110110

111-
End-to-end example of the different deployment paths will be added in the
112-
future.
111+
For end-to-end examples of the collaborative optimization techniques described
112+
here, please refer to the
113+
[CQAT](https://www.tensorflow.org/model_optimization/guide/combine/cqat_example),
114+
[PQAT](https://www.tensorflow.org/model_optimization/guide/combine/pqat_example),
115+
[sparsity-preserving clustering](https://www.tensorflow.org/model_optimization/guide/combine/sparse_clustering_example),
116+
and
117+
[PCQAT](https://www.tensorflow.org/model_optimization/guide/combine/pcqat_example)
118+
example notebooks.

0 commit comments

Comments
 (0)