Anders Boesen Lindbo Larsen

I'm terribly sorry, but I have never succeeded to install CUDArray on Windows. The problem is my choice of Cython and C++ with templates. The different name mangling schemes between...

I should add that the above only goes for CUDArray with the CUDA backend. On Windows, you can easily install CUDArray with only the NumPy backend. :)

Do you have CUDArray with the CUDA-backend working on Windows? If so, I would like to see the recipe. :)

Hey, subdividing the image is a bit problematic since the image borders overlap quite a lot (after 5 downsamplings the 3x3 conv regions might span around 96 pixels ). Also,...

filmo: The memory usage blows up as the images are propagated through the network. The exact formula for calculating the memory footprint isn't simple because it depends on the number...

@theJollySin: Unfortunately, I don't think that removing 2 channels in the input layer will save you a lot of memory relative to the total memory required of the method. For...

@errolgr: Alas, the method runs on 1 GPU only meaning that you cannot utilize the memory on the remaining 3 GPUs. I'm not exactly sure what causes the error message...

@FabienLavocat : Ok! I don't know what causes that error - but it is probably safe to assume that it is caused by a lack of memory then. Thanks. Maybe...

> @andersbll is there a way we could implement model parallelism with this method? This way we could have multiple GPU's run on a task. Unfortunately, there is not a...

@errolgr : > [..], however I want to allocate multiple GPU memory to one image, so I can process larger images. ~~If you want to run the code on large...