假设我有一个模型
from tensorflow.keras.applications import DenseNet201
base_model = DenseNet201(input_tensor=Input(shape=basic_shape))
model = Sequential()
model.add(base_model)
model.add(Dense(400))
model.add(BatchNormalization())
model.add(ReLU())
model.add(Dense(50, activation='softmax'))
model.save('test.hdf5')
然后我加载保存的模型,并尝试使最后40层DenseNet201
可训练,前161层不可训练:
saved_model = load_model('test.hdf5')
cnt = 44
saved_model.trainable = False
while cnt > 0:
saved_model.layers[-cnt].trainable = True
cnt -= 1
但这实际上不起作用,因为DenseNet201
被确定为单个层,而我只是得到了索引超出范围的错误
Layer (type) Output Shape Param #
=================================================================
densenet201 (Functional) (None, 1000) 20242984
_________________________________________________________________
dense (Dense) (None, 400) 400400
_________________________________________________________________
batch_normalization (BatchNo (None, 400) 1600
_________________________________________________________________
re_lu (ReLU) (None, 400) 0
_________________________________________________________________
dense_1 (Dense) (None, 50) 20050
=================================================================
Total params: 20,665,034
Trainable params: 4,490,090
Non-trainable params: 16,174,944
问题是,我如何才能使DenseNet的前161层不可训练,而最后40层可在负载模型上训练
densenet201 (Functional)
是一个嵌套模型,因此您可以像访问“最顶层”模型的层一样访问它的层其中
saved_model.layers[0]
是具有自己层的模型在循环中,您需要像这样访问层
更新
默认情况下,加载的模型的层是可训练的(
trainable=True
),因此您需要将底层的trainable
属性改为False
相关问题 更多 >
编程相关推荐