|View source on GitHub|
tf.keras model with the default quantization implementation.
tfmot.quantization.keras.quantize_model( to_quantize, quantized_layer_name_prefix='quant_' )
Used in the notebooks
|Used in the guide|
Quantization constructs a model which emulates quantization during training. This allows the model to learn parameters robust to quantization loss, and also model the accuracy of a quantized model.
For more information, see https://www.tensorflow.org/model_optimization/guide/quantization/training
Quantize a model:
# Quantize sequential model model = quantize_model( keras.Sequential([ layers.Dense(10, activation='relu', input_shape=(100,)), layers.Dense(2, activation='sigmoid') ])) # Quantize functional model in = tf.keras.Input((3,)) out = tf.keras.Dense(2)(in) model = tf.keras.Model(in, out) quantized_model = quantize_model(model)
Note that this function removes the optimizer from the original model.
The returned model copies over weights from the original model. So while it preserves the original weights, training it will not modify the weights of the original model.
||tf.keras model to be quantized. It can have pre-trained weights.|
Name prefix for the quantized layers. The
Returns a new