We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Created Neural Style (markdown)
Revert b052a1121501a41a02bce0648eb8582388f48b7a...88af7f2b17e182288bce5707548f1209ed50d36a on Windows
Updated Windows (markdown)
Updated Cheatsheet (markdown)
Updated Torch for Numpy users (markdown)
fixed nElement to nelement
LuaJIT and LuaRocks section: Mention how to get a bit cleaner directory structure
Add link to hiili's binary build
Cmder: Show how to set paths via a startup script
Remove spaces from windows 'set' commands (does not work with them)
Add equivalent of np.fill, np.multiply, ndarray.dot for torch. Tested on both numpy and torch.
Add note on success with some additional packages with 64-bit build
Add and update information on newest working versions (head versions of torch and nn still don't compile)
CMake: Emphasize that we need the Windows version of it
Added a note that installing Torch using the Windows Subsystem for Linux works, although I haven't done much with it beyond running some of the demos.
Add visdom in Visualization category
Include missing instructions for downloading required .lib files
Corrected typo.
Updated Home (markdown)
Destroyed Cheatsheet) (markdown)
Created Cheatsheet) (markdown)
add "usegpu"
Updated resources
Capitalized iTorch in EC2 Public AMI section. Added a section below EC2 Public AMI which provides another fast-start AWS option for Torch users. A similar link was added to TensorFlow docs for TensorFlow AMI and the community has been very positive about it.