stanford-tensorflow-tutorials icon indicating copy to clipboard operation
stanford-tensorflow-tutorials copied to clipboard

Published 20 hours ago • verified publisher icon chiphuyen

examples/07_convnet_mnist.py: test accuracy stays constant at 0.11

Open aditya6992 opened this issue 7 years ago • 0 comments

the training loss decreases, training accuracy is also increasing. But the test accuracy remains constant.

aditya6992 avatar Jul 31 '18 07:07 aditya6992