tfmot.quantization.keras.quantizers.LastValueQuantizer | TensorFlow Model Optimization (original) (raw)
tfmot.quantization.keras.quantizers.LastValueQuantizer
Stay organized with collections Save and categorize content based on your preferences.
Quantize tensor based on range the last batch of values.
Inherits From: Quantizer
tfmot.quantization.keras.quantizers.LastValueQuantizer(
num_bits, per_axis, symmetric, narrow_range
)
| Args | |
|---|---|
| num_bits | Number of bits for quantization |
| per_axis | Whether to apply per_axis quantization. The last dimension is used as the axis. |
| symmetric | If true, use symmetric quantization limits instead of training the minimum and maximum of each quantization range separately. |
| narrow_range | In case of 8 bits, narrow_range nudges the quantized range to be [-127, 127] instead of [-128, 127]. This ensures symmetric range has 0 as the centre. |
Methods
build
build(
tensor_shape, name, layer
)
Construct the weights required by the quantizer.
A quantizer may need to construct variables to hold the state for its algorithm. This function is invoked during the build stage of the layer that the quantizer is used for. Any variables constructed are under the scope of the layer and serialized as part of the layer.
| Args | |
|---|---|
| tensor_shape | Shape of tensor which needs to be quantized. |
| name | Name of tensor. |
| layer | Keras layer which is quantizing the tensors. The layer is needed to construct the weights, and is also the owner of the weights. |
Returns: Dictionary of constructed weights. This dictionary will be passed to the quantizer's call function as a weights dictionary.
from_config
@classmethod
from_config( config )
Instantiates a Quantizer from its config.
| Args | |
|---|---|
| config | Output of get_config(). |
| Returns |
|---|
| A Quantizer instance. |
get_config
get_config()
Returns the config used to serialize the Quantizer.
__call__
__call__(
inputs, training, weights, **kwargs
)
Quantize tensor.
| Args | |
|---|---|
| inputs | Input tensor to be quantized. |
| training | Whether the graph is currently training. |
| weights | Dictionary of weights the quantizer can use to quantize the tensor. This contains the weights created in the build function. |
| **kwargs | Additional variables which may be passed to the quantizer. |
| Returns |
|---|
| Quantized tensor. |
__eq__
__eq__(
other
)
Return self==value.
__ne__
__ne__(
other
)
Return self!=value.