convolutional train error

来源:-

minip

2018-06-23 21:32

(Tensorflow) ubt@ubt: ~$: python convolutional.py

......

......

step 10000, training accuracy 0.94

2018-06-23 21:11:16.991132: W tensorflow/core/framework/allocator.cc:101] Allocation of 1003520000 exceeds 10% of system memory.

2018-06-23 21:11:19.599471: W tensorflow/core/framework/allocator.cc:101] Allocation of 250880000 exceeds 10% of system memory.

2018-06-23 21:11:19.811417: W tensorflow/core/framework/allocator.cc:101] Allocation of 501760000 exceeds 10% of system memory.

terminate called after throwing an instance of 'std::bad_alloc'

  what():  std::bad_alloc

Aborted (core dumped)

(Tensorflow) ubt@ubt: ~$

写回答 关注

3回答

  • 过客260837
    2018-10-29 14:51:54

    I5 6400 16G内存 卷积模型训练  训了一天了,还没搞定

  • minip
    2018-07-13 19:02:09

    和我报错一毛一样,配置低了兄弟

    超级大傻花_...

    配置低了还能继续做吗? AMD四核 8G 无独显 是不是啥都做不成。。。

    2019-11-18 11:56:21

    共 1 条回复 >

  • fengshunsgit
    2018-07-13 17:54:27

    内不能不足了吧,你机器内存多大啊。就训练10000次吧

TensorFlow与Flask结合打造手写体数字识别

TensorFlow和flask结合识别自己的手写体数字

20432 学习 · 102 问题

查看课程

相似问题