我正在使用TensorFlow的量化感知训练API，希望部署一个具有任意位宽的模型。由于tflite部署仅支持8位量化，因此我将使用自定义推理算法进行部署，但我仍然需要以正确的大小访问模型的权重。
目前，在使用量化感知训练后，我的模型仍然是浮点型的，据我所知，访问量化权重的唯一方法是将模型转换为tflite格式。然而，当使用实验函数时，这是不可能的。
下面是我的quantization配置类：

class Quantizer(tfmot.quantization.keras.QuantizeConfig):
    # Configure how to quantize weights.
    def get_weights_and_quantizers(self, layer):
        return [(layer.kernel, tfmot.quantization.keras.quantizers.LastValueQuantizer(num_bits=8, symmetric=True, narrow_range=False, per_axis=False))]

    # Configure how to quantize activations.
    def get_activations_and_quantizers(self, layer):
        return [(layer.activation, tfmot.quantization.keras.quantizers.MovingAverageQuantizer(num_bits=8, symmetric=False, narrow_range=False, per_axis=False))]

    def set_quantize_weights(self, layer, quantize_weights):
        # Add this line for each item returned in `get_weights_and_quantizers`
        # , in the same order
            layer.kernel = quantize_weights[0]

    def set_quantize_activations(self, layer, quantize_activations):
        # Add this line for each item returned in `get_activations_and_quantizers`
        # , in the same order.
        layer.activation = quantize_activations[0]

    # Configure how to quantize outputs (may be equivalent to activations).
    def get_output_quantizers(self, layer):
        return []

    def get_config(self):
        return {}
    
class ModifiedQuantizer(Quantizer):
    # Configure weights to quantize with 4-bit instead of 8-bits.
    def get_weights_and_quantizers(self, layer):
        return [(layer.kernel, quantizer(num_bits=bits, symmetric=symmetric, narrow_range=narrow_range, per_axis=per_axis))]

下面是我如何量化模型：

supported_layers = [
    tf.keras.layers.Conv2D,
    tf.keras.layers.DepthwiseConv2D
]

class Quantizer(tfmot.quantization.keras.QuantizeConfig):
    # Configure how to quantize weights.
    def get_weights_and_quantizers(self, layer):
        return [(layer.kernel, tfmot.quantization.keras.quantizers.LastValueQuantizer(num_bits=8, symmetric=True, narrow_range=False, per_axis=False))]

    # Configure how to quantize activations.
    def get_activations_and_quantizers(self, layer):
        return [(layer.activation, tfmot.quantization.keras.quantizers.MovingAverageQuantizer(num_bits=8, symmetric=False, narrow_range=False, per_axis=False))]

    def set_quantize_weights(self, layer, quantize_weights):
        # Add this line for each item returned in `get_weights_and_quantizers`
        # , in the same order
            layer.kernel = quantize_weights[0]

    def set_quantize_activations(self, layer, quantize_activations):
        # Add this line for each item returned in `get_activations_and_quantizers`
        # , in the same order.
        layer.activation = quantize_activations[0]

    # Configure how to quantize outputs (may be equivalent to activations).
    def get_output_quantizers(self, layer):
        return []

    def get_config(self):
        return {}
    
class ModifiedQuantizer(Quantizer):
    # Configure weights to quantize with 4-bit instead of 8-bits.
    def get_weights_and_quantizers(self, layer):
        return [(layer.kernel, quantizer(num_bits=bits, symmetric=symmetric, narrow_range=narrow_range, per_axis=per_axis))]
    
    # Configure how to quantize activations.
    def get_activations_and_quantizers(self, layer):
        return [(layer.activation, tfmot.quantization.keras.quantizers.MovingAverageQuantizer(num_bits=bits, symmetric=False, narrow_range=False, per_axis=False))]

    def quantize_all_layers(layer):
        for supported_layer in supported_layers:
            if isinstance(layer, supported_layer):
                return quantize_annotate_layer(layer, quantize_config=ModifiedQuantizer())
        # print(layer.name)
        return layer
    annotated_model = clone_model(
        model,
        clone_function=quantize_all_layers
    )

with quantize_scope(
    {'Quantizer': Quantizer},
    {'ModifiedQuantizer': ModifiedQuantizer},
    {'_relu6': models._relu6}):
    q_aware_model = quantize_apply(annotated_model)

optimizer = keras.optimizers.Adam(
    learning_rate=0.001)
q_aware_model.compile(loss=tf.keras.losses.SparseCategoricalCrossentropy(
    from_logits=True),
    optimizer=optimizer, metrics=['sparse_categorical_accuracy'])

train_images, train_labels, val_images, val_labels, _, _ = cifar10.load()

q_aware_model.fit(train_images, train_labels, batch_size=64, epochs=1, verbose=1,
                  validation_data=(val_images, val_labels))

如前所述，当在ModifiedQuantizer中使用例如bits=4时，模型仍然以浮点形式保存，并且我不知道如何访问量化的权重。
谢谢！