tkocisky / oxnn Goto Github PK
View Code? Open in Web Editor NEWLicense: Other
License: Other
While building on CUDA 7.5, following error messages were printed
/tmp/luarocks_oxnn-scm-1-943/oxnn/src/LSTM12Part2.cu(102): error: this declaration has no storage class or type specifier
/tmp/luarocks_oxnn-scm-1-943/oxnn/src/LSTM12Part2.cu(103): error: expected a ";"
/tmp/luarocks_oxnn-scm-1-943/oxnn/src/LSTM12Part2.cu(115): warning: parsing restarts here after previous syntax error
After the 102-th line in LSTM12Part2.cu, which is
__thrust_hd_warning_disable__
,is commented out, the compiling becomes successful.
Do we need to omit the line?
While connecting the units of the prediction made by the network and the targets
local losses = r.S('loss')
for i=len,2,-1 do
r.E { { after_out[i-1], targets[i] },
mod_crit,
losses[1] }
end
But, from my understanding the target of the output of first time step (i.e. after_out[len-1]) is the input of second timestep (i.e. targets[len-1])... Does that mean the code actually should be
local losses = r.S('loss')
for i = len - 1 , 1 , -1 do
r.E { { after_out[i], targets[i] },
mod_crit,
losses[1] }
end
Correct me if I me wrong. Thanks.
Would be very useful to have a rockspec to make this installable.
If you want, I can open a PR, copying from here:
https://github.com/torch/nn/blob/master/rocks/nn-scm-1.rockspec
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.