我正在尝试在 TensorFlow 中训练自定义 CNN 模型。我想以某种方式在训练仍在运行时冻结特定时期模型的某些层。我已经实现了冻结层，但我必须在某些时期训练模型，然后在我想要冻结的特定层中将可训练属性更改为 False，然后编译模型，然后再次开始训练。
我尝试使用 CustomCallback() 类来实现它，并在某些时期冻结某些层，但似乎这不起作用。至于 TensorFlow 提到更改层的 .trainable 属性，那么您必须编译模型才能将更改应用于模型，但出现错误“TypeError：‘NoneType’对象不可调用” 。
这是我的代码：
加载库
import tensorflow as tf
from tensorflow.keras import datasets, layers, models
import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
from keras.callbacks import ModelCheckpoint, EarlyStopping
from tensorflow.keras.utils import Sequence
from keras.models import load_model
加载数据集
#Load dataset
(X_train, y_train), (X_test, y_test) = tf.keras.datasets.cifar10.load_data()
#Normalize
X_train, X_test = X_train/255.0, X_test/255.0
搭建模型
cnn = models.Sequential([
layers.Conv2D(filters = 32, kernel_size = (1,1), padding = "same", activation = "relu", input_shape = (32,32,3)),
layers.Conv2D(filters = 64, kernel_size = (3,3), padding = "same", activation = "relu"),
layers.MaxPool2D(pool_size = (2,2)),
layers.Conv2D(filters = 64, kernel_size = (3,3), padding = "same", activation = "relu"),
layers.Conv2D(filters = 128, kernel_size = (5,5), padding = "same", activation = "relu"),
layers.MaxPool2D(pool_size = (2,2)),
layers.Flatten(),
layers.Dense(64, activation = "relu"),
layers.Dense(128, activation = "relu"),
layers.Dense(64, activation = "relu"),
layers.Dense(10, activation = "softmax")
])
创建自定义回调类
class CustomCallback(tf.keras.callbacks.Callback):
def on_epoch_begin(self, epoch, logs = None):
if epoch == 5:
cnn.layers[0].trainable, cnn.layers[1].trainable, cnn.layers[2].trainable = (False, False, False)
cnn.compile(optimizer = optimizer, loss = "sparse_categorical_crossentropy", metrics = ["accuracy"])
elif epoch == 10:
cnn.layers[3].trainable, cnn.layers[4].trainable, cnn.layers[5].trainable = (False, False, False)
cnn.compile(optimizer = optimizer, loss = "sparse_categorical_crossentropy", metrics = ["accuracy"])
elif epoch == 15:
cnn.layers[6].trainable, cnn.layers[7].trainable, cnn.layers[8].trainable = (False, False, False)
cnn.compile(optimizer = optimizer, loss = "sparse_categorical_crossentropy", metrics = ["accuracy"])
定义优化器并编译
#Define the optimizer
optimizer = tf.keras.optimizers.Adam(learning_rate = 0.001)
#Compile the model
cnn.compile(optimizer = optimizer , loss = "sparse_categorical_crossentropy", metrics = ["accuracy"])
火车模型
results = cnn.fit(X_train, y_train, epochs = 20, validation_data = (X_test, y_test), batch_size = 1024, callbacks = [CustomCallback()])
弹出错误“TypeError: 'NoneType' object is not callable”。
如果我在冻结某些层后不编译模型，它似乎不会出现错误，但在训练时所有层都会在所有时期更新。
