choubin

在：postprocess.cc中nms错误： **源代码：** static int nms(int validCount, std::vector &outputLocations, std::vector classIds, std::vector &order, int filterId, float threshold) { for (int i = 0; i < validCount; ++i) { if (order[i] ==...

在 params = torch.load(f) in core/nnet/py_factory.py时 出现RuntimeError: storage has wrong size: expected 0 got 1，是模型不对吗？我用的是CornerNet_Saccade_500000.pkl

RuntimeError: copy_if failed to synchronize: device-side assert triggere

3

出现错误：loss_c[pos.view(-1,1)] = 0 # filter out pos boxes for now RuntimeError: copy_if failed to synchronize: device-side assert triggered 我的实际类别是1，设置了config中'num_classes': 2,但是还是出现这个问题，设置num_classes为3却可以正常训练！请问怎么解决？