Chiyuan Zhang

Based on #253 from @ianshmean - [x] Pass unit tests on CPU - [ ] Make sure examples run on CPU - [ ] Pass unit tests on GPU -...

Roadmap

33

Discussions and/or suggestions are welcome! - Interface - Network architecture visualization - Recurrent Neural Networks - Infrastructure - [ ] CUDA Stream - [ ] Multi-GPU support - [x] 4D...

Fix for Makefile on OS X

2

On my OS X, the shared libraries of CUDA are placed in `CUDA_HOME/lib` instead of `CUDA_HOME/lib64`. Please change the [following line](https://github.com/dmlc/mshadow/blob/master/make/mshadow.mk#L22) from ``` MSHADOW_LDFLAGS += -L$(USE_CUDA_PATH)/lib64 ``` to ``` MSHADOW_LDFLAGS...

How to change default columns?

2

Thanks for creating Marta! I would like to display file extensions by default. I'm able to do it for specific tabs via `View -> Edit Columns`. However, I was not...

remove calling initialize automatically

1

Hi, I noticed that `initialize` is automatically called when the `CUDA` module is imported. I think it's better to let the user to make that call explicitly: the users will...

[TODO] More optimizers

5

Currently we have SGD and Adam. Should be relatively simple to add more, like RMSProp, etc. Some references: - http://cs231n.github.io/neural-networks-3/#update - https://github.com/Lasagne/Lasagne/blob/master/lasagne/updates.py - https://github.com/fchollet/keras/blob/master/keras/optimizers.py

rewrite: feature request, per-file filter

9

Hi, thanks for making the `rewrite` branch. It looks very promising. However, I would like to request for a per-file control. e.g. maybe a per-file directive like `@file{Foo/bar.jl}`. Here are...