Hi,
I am running SegNet on TX1 and I get this error:

RuntimeError: cuda runtime error (7) : too many resources requested for launch at /home/nvidia/pytorch/torch/lib/THCUNN/generic/SpatialUpSamplingBilinear.cu:63

I want to know how to fix it ?
I tried to add 'launch_bounds(1024)' in '/home/nvidia/pytorch/torch/lib/THCUNN/generic/SpatialUpSamplingBilinear.cu ', but it dose not work.
What is difference between '/pytorch/torch/lib/THCUNN/generic/xx.cu' and '/pytorch/torch/lib/THCUNN/xx.cu' ?

• PyTorch : v0.3.0
• install PyTorch : source
• Build command : python setup.py build_deps
  sudo python setup.py develop
• Python version: 2.7
• CUDA/cuDNN version: CUDA9.0/cuDNN 7.0
• GPU models and configuration: Maximum number of threads per multiprocessor: 2048
  Maximum number of threads per block: 1024
• GCC version : 5.4.0
• CMake version:3.11.3