Closed tastyminerals closed 6 years ago
Resolved it by using a different file name for restoring:
# starting default session
with tf.Session() as session:
saver = tf.train.Saver(tf.global_variables())
saver.restore(session, "saved_model/model.ckpt")
I have successfully trained a sequential classifier model using TF-NNLM-TK code as a baseline. The model was saved using the following code:
The model is then stored in
saved_models/
dir as a set of files:Attempting to restore it
throws
DataLossError
tensorflow-gpu: 1.5.0 running on Linux