The neural network model running on the GPU is accelerated by multi-threading in parallel. If something goes wrong, the real error message is easily overwhelmed by the error message of cuda, so it is difficult to see the error message. The general cause of the problem is that the array etc. exceed the limit and the positioning To be specific, anchor_ratios=[0.2, 0.5, 1.0, 2.0, 5.0] can be modified to the default anchor_ratios=[0.5, 1.0, 2.0]
Undertake programming in Matlab, Python and C++, machine learning, computer vision theory implementation and guidance, both undergraduate and master's degrees, salted fish trading, professional answers please go to know, please contact QQ number 757160542 for details, if you are the one.