vasiloglou / mltrain-nips-2017 Goto Github PK
View Code? Open in Web Editor NEWThis repository contains all the material for the MLTrain NIPS workshop
Home Page: http://bit.ly/2A9BSWR
This repository contains all the material for the MLTrain NIPS workshop
Home Page: http://bit.ly/2A9BSWR
Thanks for sharing your code, my question are:
class ComplementCrossEntropyLoss(torch.nn.Module):
def init(self, except_index=None, weight=None, ignore_index=-100, size_average=True, reduce=True):
super(ComplementCrossEntropyLoss, self).init()
self.except_index = except_index
self.weight = weight
self.ignore_index = ignore_index
self.size_average = size_average
self.reduce = reduce
def forward(self, input, target=None):
# Use target if not None, else use self.except_index
if target is not None:
assert_no_grad(target)
else:
assert self.except_index is not None
target = torch.autograd.Variable(torch.LongTensor(input.data.shape[0]).fill(self.except_index).cuda())
result = torch.nn.functional.nll_loss(
torch.log(1. - torch.nn.functional.softmax(input) + 1e-4),
target, weight=self.weight,
size_average=self.size_average,
ignore_index=self.ignore_index)
return result
Hi, how do you get observed=1000
for generator and observed=50000
for discriminator in PriorLoss
and NoiseLoss
in bayes.py
? Thanks!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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. 📊📈🎉
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 ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.