摘要: 过程: Filling queue with 20000 CIFAR images before starting to train. This will take a few minutes. step 0, loss =4.68 (19.0 examples/sec; 6.734 sec/bat 阅读全文
posted @ 2018-12-14 20:38 云山之巅 阅读(3378) 评论(0) 推荐(0)