Closed buttomnutstoast closed 8 years ago
in line 43 and line 46
features:add(nn.BatchNormalization(4096, 1e-3)) features:add(nn.BatchNormalization(4096, 1e-3))
I think it should be classifier rather than features, because the whole fully connected layer lies in GPU1 (or the preferred one)
You're right. Fixed via: https://github.com/soumith/imagenet-multiGPU.torch/commit/cf7d7d40be58968f34900c2f7362b979ab340bd2
in line 43 and line 46
I think it should be classifier rather than features, because the whole fully connected layer lies in GPU1 (or the preferred one)