deepRacin yields wrong results on AMD graphics cards

[BjoernLange]

I compared the results of a deepRacin run with the expected results given by the tensorflow training. On an NVIDIA GTX 1080 Ti everything is fine, the results look like this:

Required result: [-3.32278252  7.10063839]
Actual result: [array([-3.32278347,  7.10063887], dtype=float32)]
Squared difference: [[  9.09494702e-13   2.27373675e-13]]

(the difference of something with e-13 seems to be acceptable)
However on an AMD Radeon RX 580 the results look like this:

Required result: [-3.32278252  7.10063839]
Actual result: [array([-1.49906969,  5.0553546 ], dtype=float32)]
Squared difference: [[ 3.32592847  4.1831858 ]]

[janericlenssen]

Thank you for reporting. Can you send the graph.dr file so that i can see which nodes are used?

Maybe it makes sense two wait until i implemented the Tests. Then, one could see directly which node is not accurate.

[BjoernLange]

Here is the graph.dr file.

[BjoernLange]

I also tested on an Intel CPU, which is also working fine.