[英]Keras: get training data from a saved model
Is it even possible? 它甚至可能吗? The model is saved by
该模型由。保存
ModelCheckpoint(model_path, save_best_only=True, monitor='val_acc', mode='max', save_weights_only=False)
Can I do something like this? 我可以这样做吗?
from keras.models import load_model
model = load_model(model_path)
X_train = model.inputs
No, this is not possible. 不,这是不可能的。 ModelCheckpoint with
save_weights_only=False
only saves the topology, the weights and the optimizer's state (if any) of the model. ModelCheckpoint与
save_weights_only=False
不仅节省了模型的拓扑结构,重量和优化的状态(如果有的话)。 The training data is not saved along with the model, and model.inputs
is just the list of the model's placeholders. 训练数据不会与模型一起保存,而
model.inputs
只是模型占位符的列表。
See also the source code for ModelCheckpoint . 另请参见ModelCheckpoint的源代码 。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.