Mykola Pavlov

Exact error message is the following: ``` 31-Aug 02:31:47:INFO:root:Constructing net SVHN-train on GPUBackend... 31-Aug 02:31:47:INFO:root:Topological sorting 14 layers... 31-Aug 02:31:47:INFO:root:Setup layers... 31-Aug 02:31:49:INFO:root:Network constructed! 31-Aug 02:31:49:INFO:root:Constructing net SVHN-train-prediction on GPUBackend......

Here is also my video card info: ``` ./deviceQuery Starting... CUDA Device Query (Runtime API) version (CUDART static linking) Detected 1 CUDA Capable device(s) Device 0: "GeForce GTX TITAN X"...

Ok. It seems like I have found a workaround. I have to init and shutdown the GPU backend between each new set of hyperparameters. Though the actual implementation looks weird,...

It doesn't work. It fails after several iterations. ``` 08-Sep 08:25:09:INFO:root:Initializing CuDNN backend... INFO: CuDNN backend initialized! 08-Sep 08:25:10:INFO:root:Constructing net SVHN-train on GPUBackend... 08-Sep 08:25:10:INFO:root:Topological sorting 12 layers... 08-Sep 08:25:10:INFO:root:Setup...

BTW, the shutdown() works well. The only thing, if you get some error during the grid search, for example, when some of hyperparams in a set are incompatible, you have...

Just curious, can you make the backend initialization implicit?. Why not to hide `init()` and `shutdown()` into the functions like `solve()` and `forward_epoch()`?

- It would be nice to have [maxout layer](http://jmlr.csail.mit.edu/proceedings/papers/v28/goodfellow13.pdf) in addition to dropout.. - [Max-norm Regularization](http://www.cs.toronto.edu/~hinton/absps/JMLRdropout.pdf) can help for optimal dropout nets tuning.

@pluskid Great, I'll try to play with PoolingLayer.