Skip to content

fix for cutorch index* changes #924

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
soumith merged 1 commit into from
Aug 12, 2016
Merged

fix for cutorch index* changes #924

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions LookupTable.lua
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ function LookupTable:updateOutput(input)
end

function LookupTable:updateGradInput(input, gradOutput)
-- the input can be of any type (as in the forward it's
-- the input can be of any type (as in the forward it's
-- converted anyway to LongTensor) thus, need to allocate
-- new memory each time the user changes the input type
if torch.type(self.gradInput) ~= torch.type(input) then
Expand Down Expand Up @@ -148,10 +148,10 @@ function LookupTable:type(type, tensorCache)

if type == 'torch.CudaTensor' then
-- CUDA uses _sorted and _indices temporary tensors
self._sorted = self.weight.new()
self._indices = self.weight.new()
self._count = self.weight.new()
self._input = self.weight.new()
self._sorted = torch.CudaLongTensor.new()
self._indices = torch.CudaLongTensor.new()
self._count = torch.CudaLongTensor.new()
self._input = torch.CudaLongTensor.new()
else
-- self._count and self._input should only be converted if using Cuda
self._count = torch.IntTensor()
Expand Down