AurusHuang

Your post is badly formatted that I can't figure out what is changed.

Thank you for your answer. However, I need some details in order to make such a network. Do you have any tutorials or outlines about how to adapt a classification...

If I designed my own network (with region layer), can I run training by just typing `.\darknet detector train %datafile.data% %cfgfile.cfg%` with %datafile.data% and %cfgfile.cfg% replaced with actual filenames? If...

But on my machine, I can't. Darknet will terminate itself even before it loads the network.

Well...it's probably not cfg's problem. Because it also crashes when using YOLO's original cfgs.

Well...the debugger has located the problem here: ``` char *weights = (argc > 5) ? argv[5] : 0; if (weights[strlen(weights) - 1] == 0x0d) weights[strlen(weights) - 1] = 0; ```...

`.\darknet detector train cfg\voc07.data tiny-yolo-voc07.cfg` will result a program termination. `.\darknet detector train cfg\voc07.data tiny-yolo-voc07.cfg darknet19_448.conv.23` will work.

Yes. I'm using @AlexeyAB 's Darknet Windows repository. I'll checkout the latest version to see if it's modified.

Let me rephrase... `delta_sigx_l1b` is a X by 4096 by X tensor, `dsigma0_g_ii` is a 4052 by 1 vector. `nx(ii, beam)` is a scalar value and is equal to 4052....

The following code works: ``` int main() { xtensor nx = { 4052,4052,4052 }; auto shape_t = xt::shape({ 3,4096,3 }); xtensor delta_sigx_l1b = xt::eval(xt::random::rand(shape_t)); xtensor dsigma0_g_ii = xt::eval(xt::random::rand({ 4052 }));...