Cannot use FireModule with CUDA

[Jonathan Shen]

gradParameters becomes nan.

Of course, if I just use the constituent layers and build my own FireModule function like:

function FireModule(nInputPlane, s1x1, e1x1, e3x3)
  local module = nn.Sequential()
  module:add(nn.SpatialConvolution(nInputPlane, s1x1, 1, 1)):add(nn.ReLU(true))
  local expand = nn.Concat(2)
  expand:add(nn.SpatialConvolution(s1x1, e1x1, 1, 1))
  expand:add(nn.SpatialConvolution(s1x1, e3x3, 3, 3, 1, 1, 1, 1))
  module:add(expand):add(nn.ReLU(true))
  return module
end
model:add(FireModule(a,b,c,d))

then everything works fine, but then I don't get the neat __tostring__.

Is there any way of fixing this from your side? Thanks

[Nicholas Léonard]

@sagarwaghmare69 Could you look into this when you have time?

[Sagar M Waghmare]

@jonathanasdf I am not able to reproduce the error. Can you please provide your code snippet ?

[Sagar M Waghmare]

Yes.

On Fri, Mar 11, 2016 at 3:37 PM, Nicholas Léonard [e-mail]
wrote:

@sagarwaghmare69 https://github.com/sagarwaghmare69 Could you look into
this when you have time?

—
Reply to this email directly or view it on GitHub
#45 (comment)
.

[Jonathan Shen]

Apparently it randomly becomes 0, inf, or nan. Also, zeroGradParameters doesn't seem to do anything.

require 'dpnn'
require 'cutorch'

local m = nn.Sequential()
m:add(nn.FireModule(1,1,1,1))
_, p = m:getParameters()
print(p:sum())

m = m:cuda()
_, p = m:getParameters()
print(p:sum())

m:zeroGradParameters()
print(p:sum())

Some outputs (randomly one of these)

-1.5261873854701e+236
nan
nan

1.117789947961e+138
inf
inf

4.8518308672707e-309
0
0

[Sagar M Waghmare]

@jonathanasdf Thanks for reporting the bug and providing an example. I was able to reproduce the bug. We will fix it (latest by Monday evening). Thanks.

[Nicholas Léonard]

@jonathanasdf fixed via #46 . Thanks @sagarwaghmare69

[Jonathan Shen]

Thank you for the fast fix!