Dear all,
I'd like to load the offline saved GP. I am fairly new to Tensorflow and struggle finding the right syntax. It looks like I can import the saved graph quite easily but I am not able to get a full prediction out of a saver.
with tf.Session() as sess:
new_saver = tf.train.import_meta_graph('final_model.ckpt.meta')
new_saver.restore(sess, 'final_model.ckpt')
graph = tf.get_default_graph()
ydata = graph.get_operation_by_name('Y_data').outputs[0]
udata = graph.get_operation_by_name('U_data').outputs[0]
value = graph.get_operation_by_name('Y_value').outputs[0]
#doesn't exists but I guess this is what I need..
mean = sess.run(value ,feed_dict={ydata:[[[1,2,3,4]]],udata:[[[1,2,3,4,5,6]]]})
Any suggestions how to fix this?
Thanks in advance!
Dear all, I'd like to load the offline saved GP. I am fairly new to Tensorflow and struggle finding the right syntax. It looks like I can import the saved graph quite easily but I am not able to get a full prediction out of a saver.
Any suggestions how to fix this? Thanks in advance!