View source on GitHub |
Default 8 bit Prune Preserve Quantization Scheme.
Inherits From: Default8BitQuantizeScheme
, QuantizeScheme
tfmot.quantization.keras.collab_opts.Default8BitPrunePreserveQuantizeScheme(
disable_per_axis=False
)
Used in the notebooks
Used in the guide |
---|
Methods
get_layout_transformer
get_layout_transformer()
Returns the layout transforms for this scheme.
Returns | |
---|---|
Returns the QuantizeLayoutTransform for this quantization scheme. |
get_quantize_registry
get_quantize_registry()
Returns the quantization registry for this scheme.
Returns | |
---|---|
Returns the QuantizeRegistry for this quantization scheme. |