Performance issue in neural_style.py (by P3)

[DLPerf]

Hello! I've found a performance issue in neural_style.py: with tf.Session() as sess(here) is defined in the function stylize(here) which is repeatedly called in the loop for frame in range(args.start_frame, args.end_frame+1)(here).

tf.Session being defined repeatedly could lead to incremental overhead. If you define tf.Session out of the loop and pass tf.Session as a parameter to the loop, your program would be much more efficient. Here is the Stack Overflow post to support it.

Looking forward to your reply. Btw, I am very glad to create a PR to fix it if you are too busy.

[DLPerf]

Hello, I'm looking forward to your reply~