1

我正在从这里开始阅读泰坦尼克号教程。完成后,我想保存模型,然后再加载它。保存后,我收到一条警告:

TensorFlow's V1 checkpoint format has been deprecated.
WARNING:tensorflow:Consider switching to the more efficient V2 format:

当我加载它时,我收到一条错误消息

NotFoundError (see above for traceback): Unsuccessful TensorSliceReader constructor: Failed to find any matching files for model.tflearn
 [[Node: save_1/RestoreV2_2 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save_1/Const_0, save_1/RestoreV2_2/tensor_names, save_1/RestoreV2_2/shape_and_slices)]]

这就是我保存/加载模型的方式。

net = tflearn.input_data(shape=[None, 6])
net = tflearn.fully_connected(net, 32)
net = tflearn.fully_connected(net, 32)
net = tflearn.fully_connected(net, 2, activation='softmax')
net = tflearn.regression(net)


model = tflearn.DNN(net)

model.fit(data, labels, n_epoch=10, batch_size=16, show_metric=True)
model.save('model.tflearn')

然后当我加载它时,我只是做一个......

model.load('model.tflearn')

如果哪位有这方面经验的可以帮帮我,我将不胜感激,谢谢。

4

1 回答 1

1

采用model.load('./model.tflearn')

于 2016-12-26T01:21:45.700 回答