|View source on GitHub|
Specifies to prune only 1x1 Conv2D layers in the model.
Used in the notebooks
|Used in the guide|
PruneForLatencyOnXNNPack checks that the model contains a subgraph that can
leverage XNNPACK's sparse inference and applies pruning wrapper only to
kernel_size = (1, 1).
allow_pruning( layer )
Allows to prune only 1x1 Conv2D layers.
ensure_model_supports_pruning( model )
Ensures that the model contains only supported layers.