1
bwael Aug 3, 2018
抢个沙发试试。auto-keras,有点可怕。
|
2
geekcorn Aug 3, 2018 via iPhone
哇&&&)
|
3
sangleft Aug 3, 2018 via Android
等会就试试…😯
|
4
ddzzhen Aug 3, 2018 via Android
看起来有点牛批,sklearn 的翻版?
|
5
xxxy Aug 3, 2018 sklearn 不是有个 gridSearch?跟那个有什么区别?
|
6
owenliang Aug 3, 2018 via Android
深度学习帮码农挑选优质特征
|
8
OLDPAN Aug 3, 2018
之前是自动调参数,现在是自动调网络
|
9
1722332572 OP @xxxy 看文档,这个模型也会调。
|
10
takato Aug 3, 2018
本质是个 NAS 吧。
|
11
eastrd Aug 4, 2018 via Android
不是已经有 hpot 了吗?
|
12
northisland Aug 4, 2018
厉害了!
虽然 tensorflow 很难用,但为了这些周边,还是值得搞 TF 的~ First, each dataset is split by60-20-20 into training, validation and testing set. Second, **run the method for 12 hours** on a single GPU (NVIDIA GeForce GTX 1080Ti) on the training and validation set. Third, the output architecture is trained with both training and validation set. Fourth, the testing set is used to evaluate the trained architecture 最近经常见 200 块 gpu,训练个把月的 RL 文章,这方法简直是一股清流 |
13
1722332572 OP @northisland 调参侠的福音,还顺便调网络结构,美滋滋。
|