diff options
author | Nathan Bailey <nathan.bailey@arm.com> | 2024-05-15 08:12:30 +0100 |
---|---|---|
committer | Nathan Bailey <nathan.bailey@arm.com> | 2024-05-21 16:51:15 +0100 |
commit | 856111bcaef76c60303bdf2ae7cbf718d93d1df4 (patch) | |
tree | d955901817194e48e478f751140bd3c1741d1834 /README.md | |
parent | 0d3cc76284f9311c99169b568570d767f5b0aeb6 (diff) | |
download | mlia-856111bcaef76c60303bdf2ae7cbf718d93d1df4.tar.gz |
feat: Implement the conv2D rewrites for int8 and fp32 models
Enable clustering and fully connected rewrites for conv2D layers.
Resolves: MLIA-1159 and MLIA-1160
Signed-off-by: Nathan Bailey <nathan.bailey@arm.com>
Change-Id: I640b8a7e79e455b12fb68d02ac1c33213b8de9c6
Diffstat (limited to 'README.md')
-rw-r--r-- | README.md | 8 |
1 files changed, 8 insertions, 0 deletions
@@ -181,6 +181,14 @@ documentation, e.g. in the candidates from the rewrite library, with or without training using a small portion of the training data, to achieve local performance gains. +The following rewrites are supported: + +* fully-connected - replaces a subgraph with a fully connected layer +* fully-connected-sparsity24 - replaces a subgraph with a pruned 2:4 sparse fully connected layer +* fully-connected-clustering - replaces a subgraph with a clustered fully connected layer +* conv2d-sparsity24 - replaces a subgraph with a pruned 2:4 sparse conv2d layer +* conv2d-clustering - replaces a subgraph with a clustered conv2d layer + **Note:** A ***Keras model*** (.h5 or SavedModel) is required as input to perform pruning and clustering. A ***TensorFlow Lite model*** is required as input to perform a rewrite. |