ValueError：`to_quantize`只能是 keras 顺序模型或函数模型

Question

我目前正在使用 Tensorflow Lite 和 Tensorflow Lite for Micro 学习 TinyML。 我正在研究 R. Banerjee 的《Hands-on TinyML》一书。

我正在尝试量化模型，但它产生了错误：

q_aware_model = tfmot.quantization.keras.quantize_model(basemodel)

量化模型中的文件/usr/local/lib/python3.12/site-packages/tensorflow_model_optimization/python/core/quantization/keras/quantize.py:135 引发值错误（

ValueError：

to_quantize

只能是keras顺序模型或功能模型。

这是我练习的Python源代码：

import numpy as np
import matplotlib.pyplot as plt

import tensorflow as tf

from tensorflow.keras.datasets import cifar10
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dropout, Dense

def base_model():

  model = Sequential()      
  model.add(Conv2D(32, kernel_size=(3, 3), activation="relu", input_shape = (28,28,1)))
  model.add(MaxPooling2D(pool_size=(2, 2)))
  model.add(Conv2D(64, kernel_size=(3, 3), activation="relu"))
  model.add(MaxPooling2D(pool_size=(2, 2)))
  model.add(Flatten())
  model.add(Dropout(0.5))
  model.add(Dense(100, activation = "relu"))
  model.add(Dense(10, activation="softmax"))
  
  return model

basemodel = base_model()
basemodel.summary()

import tensorflow_model_optimization as tfmot

quantized_model = tfmot.quantization.keras.quantize_model

# q_aware stands for for quantization aware.
q_aware_model = tfmot.quantization.keras.quantize_model(basemodel)

# `quantize_model` requires a recompile.
q_aware_model.compile(optimizer='adam',
              loss=tf.keras.losses.CategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

q_aware_model.summary()

引发的错误位于以下行：q_aware_model = tfmot.quantization.keras.quantize_model(basemodel)

我不知道为什么。 你能帮我吗？

我的环境：spyder 5.5.6，Python 3.12.6 64位，tensorflow 2.17.0，tensorflow-model-optimization 0.8.0，keras 3.5.0。

谢谢。 埃迪33

Answer 1

我通过重写人工智能模型解决了自己的问题：

import numpy as np
import matplotlib.pyplot as plt

import tensorflow as tf

from tensorflow.keras.datasets import cifar10
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dropout, Dense
from tensorflow_model_optimization.python.core.keras.compat import keras
#import tf_keras as keras

def base_model():

  model = keras.Sequential([
  keras.layers.Conv2D(32, kernel_size=(3, 3), activation="relu", input_shape = (28,28,1)),
  keras.layers.MaxPooling2D(pool_size=(2, 2)),
  keras.layers.Conv2D(64, kernel_size=(3, 3), activation="relu"),
  keras.layers.MaxPooling2D(pool_size=(2, 2)),
  keras.layers.Flatten(),
  keras.layers.Dropout(0.5),
  keras.layers.Dense(100, activation = "relu"),
  keras.layers.Dense(10, activation="softmax") 
])
  
  return model

basemodel = base_model()
basemodel.summary()

import tensorflow_model_optimization as tfmot

quantized_model = tfmot.quantization.keras.quantize_model

# q_aware stands for for quantization aware.
q_aware_model = tfmot.quantization.keras.quantize_model(basemodel)

# `quantize_model` requires a recompile.
q_aware_model.compile(optimizer='adam',
              loss=tf.keras.losses.CategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

q_aware_model.summary()

谢谢。 埃迪33