diff options
author | Nathan Bailey <nathan.bailey@arm.com> | 2024-05-23 11:19:15 +0100 |
---|---|---|
committer | Nathan Bailey <nathan.bailey@arm.com> | 2024-05-30 14:25:38 +0000 |
commit | b35649e8b4002e6f9d585694a76b0b6e65d128b6 (patch) | |
tree | 8aaf1139b074cedea7e1c56afaba4e9061e65c6c /README.md | |
parent | 1d3f15488ee10d83b764c76940524626421f3664 (diff) | |
download | mlia-b35649e8b4002e6f9d585694a76b0b6e65d128b6.tar.gz |
feat: Enable user parameters for activation functions in conv2d rewrites
Allow the user to specify an activation function for conv2d rewrites
Enable automatic detection of most common activation function in rewrite in the case that the user does not specify one
Resolves: MLIA-1163
Signed-off-by: Nathan Bailey <nathan.bailey@arm.com>
Change-Id: Icbf6f4c6f8eaba6d78b88bdf62448f1d30aed1ae
Diffstat (limited to 'README.md')
-rw-r--r-- | README.md | 20 |
1 files changed, 13 insertions, 7 deletions
@@ -229,19 +229,19 @@ There are a number of predefined profiles for rewrites shown below: | Name | Batch Size | LR | Show Progress | Steps | LR Schedule | Num Procs | Num Threads | Checkpoints | Num Clusters | Cluster Centroids Init | | :-------------------------------------: | :--------: | :--: | :-----------: | :---: | :---------: | :-------: | :---------: | :---------: | :----------: | :--------------------------------: | -| optimization-fully-connected-clustering | 32 | 1e-3 | True | 48000 | "cosine" | 1 | 0 | None | 32 | "CentroidInitialization.LINEAR" | +| optimization-fully-connected-clustering | 32 | 1e-3 | True | 48000 | "cosine" | 1 | 0 | None | 16 | "CentroidInitialization.LINEAR" | | Name | Batch Size | LR | Show Progress | Steps | LR Schedule | Num Procs | Num Threads | Checkpoints | Sparsity M | Sparsity N | | :-----------------------------------: | :--------: | :--: | :-----------: | :---: | :---------: | :-------: | :---------: | :---------: | :--------: | :--------: | | optimization-fully-connected-pruning | 32 | 1e-3 | True | 48000 | "cosine" | 1 | 0 | None | 2 | 4 | -| Name | Batch Size | LR | Show Progress | Steps | LR Schedule | Num Procs | Num Threads | Checkpoints | Num Clusters | Cluster Centroids Init | -| :-------------------------------------: | :--------: | :--: | :-----------: | :---: | :---------: | :-------: | :---------: | :---------: | :----------: | :--------------------------------: | -| optimization-conv2d-clustering | 32 | 1e-3 | True | 48000 | "cosine" | 1 | 0 | None | 32 | "CentroidInitialization.LINEAR" | +| Name | Batch Size | LR | Show Progress | Steps | LR Schedule | Num Procs | Num Threads | Checkpoints | Num Clusters | Cluster Centroids Init | Activation | +| :-------------------------------------: | :--------: | :--: | :-----------: | :---: | :---------: | :-------: | :---------: | :---------: | :----------: | :--------------------------------: | :--------: | +| optimization-conv2d-clustering | 32 | 1e-3 | True | 48000 | "cosine" | 1 | 0 | None | 16 | "CentroidInitialization.LINEAR" | "relu" | -| Name | Batch Size | LR | Show Progress | Steps | LR Schedule | Num Procs | Num Threads | Checkpoints | Sparsity M | Sparsity N | -| :-----------------------------------: | :--------: | :--: | :-----------: | :---: | :---------: | :-------: | :---------: | :---------: | :--------: | :--------: | -| optimization-conv2d-pruning | 32 | 1e-3 | True | 48000 | "cosine" | 1 | 0 | None | 2 | 4 | +| Name | Batch Size | LR | Show Progress | Steps | LR Schedule | Num Procs | Num Threads | Checkpoints | Sparsity M | Sparsity N | Activation | +| :-----------------------------------: | :--------: | :--: | :-----------: | :---: | :---------: | :-------: | :---------: | :---------: | :--------: | :--------: | :--------: | +| optimization-conv2d-pruning | 32 | 1e-3 | True | 48000 | "cosine" | 1 | 0 | None | 2 | 4 | "relu" | These are summarized below: @@ -251,6 +251,12 @@ These are summarized below: * optimization-conv2d-clustering - Provides training parameters for rewrites and cluster specific parameters for the conv2d-clustering rewrite * optimization-conv2d-pruning - Provides training parameters for rewrites and pruning specific parameters for the conv2d-sparsity rewrite +Note for convolutional rewrites (e.g. optimization-conv2d-pruning). The activation function for the rewrite can be selected in the optimization profile from the following list: + +* "relu" - Standard ReLU activation function +* "relu6" - ReLU6 activation function i.e. ReLU activation function capped at 6 +* "none" - No activation function + The user can also specify custom augmentations as part of the training parameters. An example of this can be found in the following optimization profile: | Name | Batch Size | LR | Show Progress | Steps | LR Schedule | Num Procs | Num Threads | Checkpoints | Augmentations - gaussian_strength | Augmentations - mixup_strength | |