ValueError: This model has not yet been built. Build the model first by calling build()
or calling
当我们训练好模型保存下来之后,想要读取模型以及相关参数,可能会出现以下问题ValueError: This model has not yet been built. Build the model first by calling build()
or calling。
解决办法一:目前CSDN上的很多方法添加model.bulid((None,时间步/或W,特征/或H))
估计对大部分有用。
我的解决办法:修改原训练模型的出入层InputLayer
'''原始代码'''
model = Sequential()
model.add(InputLayer(input_shape=(X.shape[1],X.shape[2])))
model.add(Conv1D(filters=128,kernel_size=3,
padding="valid",activation="relu",
kernel_regularizer='l2'))
修改之后
model = Sequential()
model.add(Conv1D(filters=128,kernel_size=3,padding="valid",
activation="relu",kernel_regularizer='l2',
input_shape=(X.shape[1],X.shape[2])))
下次再训练完,加载模型就不会出现这项的问题了。