2018-12-27 | 改代码，跑DoF map的prediction model

Q：

Exception: "concat" mode can only merge layers with matching output shapes except for the concat axis. Layer shapes: [(None, 512, 30, 512), (None, 16, 30, 40)]

作者说是keras.json文件需要改成

{ "image_dim_ordering": "th", "epsilon": 1e-07, "floatx": "float32", "backend": "theano" }

然后就可以跑了耶！ヽ(●´∀`●)ﾉ
--------------------------分割线----------------------------------------------------------------------
test过程中遇到的warning：

Using Theano backend.
Using cuDNN version 6021 on context None
Mapped name None to device cuda: GeForce GTX 1070 (0000:01:00.0)
/home/yifang/anaconda2/envs/py35/lib/python3.5/site-packages/keras/backend/theano_backend.py:1500: UserWarning: DEPRECATION: the 'ds' parameter is not going to exist anymore as it is going to be replaced by the parameter 'ws'.
mode='max')
/home/yifang/anaconda2/envs/py35/lib/python3.5/site-packages/keras/backend/theano_backend.py:1500: UserWarning: DEPRECATION: the 'st' parameter is not going to exist anymore as it is going to be replaced by the parameter 'stride'.
mode='max')
/home/yifang/anaconda2/envs/py35/lib/python3.5/site-packages/keras/backend/theano_backend.py:1500: UserWarning: DEPRECATION: the 'padding' parameter is not going to exist anymore as it is going to be replaced by the parameter 'pad'.
mode='max')

• theano cudnn不兼容问题，解决过程：

1. 测试theano能不能用gpu
   theano官网：使用gpu

By default, when device indicates preference for GPU computations, Theano will fall back to the CPU if there is a problem with the GPU. You can use the flag force_device=True to instead raise an error when Theano cannot use the GPU.

所以就是有问题，不是设置问题。

dnn.include_path ()
Doc: Location of the cudnn header
Value: /usr/local/cuda/include

dnn.library_path ()
Doc: Location of the cudnn link library.
Value: /usr/local/cuda/lib64