ZahlGraf

@kinoc and @soumith Have you trained a model on Jetson TX1 in the meanwhile? I always get "Segmentation faults" when trying to train on TX1 (see #160 ) and unfortunately...

Does anyone from this thread have a valid checkpoint, running on jetson available?

If I use the CPU checkpoint I get a slightly different error: ``` th eval.lua -model ../PreTrained/model_id1-501-1448236541.t7_cpu.t7 -gpuid -1 -image_folder ../TestImages -num_images 1 Warning: Failed to load function from bytecode:...