-
Yang Liu authored
* Bug fix of cifar10_eval.py line 120: changed from eval_data = FLAGS.eval_data == 'test' to: eval_data = FLAGS.eval_data comment: the original code assigns 'true' to eval_data, when the script is being used to evaluate networks on the evaluation set, it DOES NOT load the evaluation set as intended, but actually loads the trainning set (line 105 of cifar10_input.py). * Remove one line that was an artifact of issue.
cad067d8
