利用函数API进行量化感知训练的迁移学习

Question

我有一个模型，我使用转移学习的MobileNetV2，我想量化它，并比较精度的差异，与一个非量化的模型和转移学习。然而，它们并不完全支持递归量化，但是根据这一点，这个方法应该量化我的模型：https://github.com/tensorflow/model-optimization/issues/377#issuecomment-820948555。

我试着做的是：

import tensorflow as tf
import tensorflow_model_optimization as tfmot
pretrained_model = tf.keras.applications.MobileNetV2(include_top=False)
pretrained_model.trainable = True
    
for layer in pretrained_model.layers[:-1]:
    layer.trainable = False
    
quantize_model_pretrained = tfmot.quantization.keras.quantize_model
q_pretrained_model = quantize_model_pretrained(pretrained_model)
    
    
original_inputs = tf.keras.layers.Input(shape=(224, 224, 3))
y = tf.keras.layers.experimental.preprocessing.Rescaling(1./255)(original_inputs)
y = base_model(original_inputs)
y = tf.keras.layers.GlobalAveragePooling2D()(y)
original_outputs = tf.keras.layers.Dense(5, activation="softmax")(y)

model_1 = tf.keras.Model(original_inputs, original_outputs)
quantize_model = tfmot.quantization.keras.quantize_model
q_aware_model = quantize_model(model_1)

它仍然给了我以下错误：

ValueError: Quantizing a tf.keras Model inside another tf.keras Model is not supported.

在这种情况下，我想了解什么是执行量化感知训练的正确方法？

Answer 1

根据您提到的问题，您应该分别量化每个模型，然后将它们组合在一起。就像这样：

import tensorflow as tf
import tensorflow_model_optimization as tfmot

pretrained_model = tf.keras.applications.MobileNetV2(input_shape=(224, 224, 3), include_top=False)
pretrained_model.trainable = True
    
for layer in pretrained_model.layers[:-1]:
    layer.trainable = False
    
q_pretrained_model = tfmot.quantization.keras.quantize_model(pretrained_model)
q_base_model = tfmot.quantization.keras.quantize_model(tf.keras.Sequential([tf.keras.layers.GlobalAveragePooling2D(input_shape=(7, 7, 1280)), tf.keras.layers.Dense(5, activation="softmax")]))
   
original_inputs = tf.keras.layers.Input(shape=(224, 224, 3))
y = tf.keras.layers.experimental.preprocessing.Rescaling(1./255)(original_inputs)
y = q_pretrained_model(original_inputs)
original_outputs = q_base_model(y)

model = tf.keras.Model(original_inputs, original_outputs)

虽然这是索要，但它似乎已经不受支持了。