报错FloatingPointError: Loss became infinite or NaN at iteration=88!,程序员大本营,技术文章内容聚合第一站。
loss_dict = {'loss_fcos_cls': tensor(nan, device='cuda:0', grad_fn=<DivBackward0>), 'loss_fcos_loc': tensor(0.5552, device='cuda:0', grad_fn=<DivBackward0>), 'loss_fcos_ctr': tensor(0.7676, device='cuda:0', grad_fn=<DivBackward0>), 'loss_mask': tensor(0.8649, device='...
The second constraint is that the width of the space Ws(n) should decrease as a function of grating index n, because as the light travels from the SOI waveguide through the gratings it goes from a space of effectively infinite width to, eventually, a space of a constant width. The ...