What about the hardware configuration？

[qinxiaoyu222]

Hardware operating environment is a number of gpu or server?

[zouchuhang]

@qinxiaoyu222 We train & test our network on a single NVIDIA Titan X GPU. You shall be able to run it on a GPU with 12GB memory.

[qinxiaoyu222]

Thank you very much. My GPU is NVIDIA GtX1080 with 8GBmemory.

[zouchuhang]

@qinxiaoyu222 I think you encounter the "out of memory" issue, our model use nearly all the 12GB memory for better performance. You can try down sampling the resolution of the input image by a factor of 2 and change the related network structure to fit this resolution. In this way you shall be able to run the experiments. Alternatively you can try it on a GPU with 12GB memory.

[qinxiaoyu222]

@zouchuhang Thank you very much, I try it.

[zoubochao]

Mine is 1080Ti with 11GB memory, and I still get the "out the memory" error, is there anyway to work around besides down sampling the resolution? thx

[zouchuhang]

@zoubochao I checked "driver_pano_joint.lua" and it needed around 10.969GB to run, nearly touch to your 11GB memory limitation. If you don't want to down sample the resolution, it's better to locally get a Titan xp GPU with 12GB memory, or try running the network on paid public servers like AWS.

[zouchuhang]

You can try down sampling the resolution of the input image by a factor of 2 and change the related network structure to fit this resolution. In this way you shall be able to run the experiments. Alternatively you can try it on a GPU with 12GB memory.