Hello, I am following the object recognition tutorial from pytorch
https://pytorch.org/tutorials/intermediate/torchvision_tutorial.html . I use Windows 10 with CPU only and I had to make a couple of tweaks to the auxiliary scripts (utils, engine) to avoid calls to cuda.
However, the following line is giving silent error when run for the 2nd time in a loop, so I guess it is a memory problem. Both in Jupyter and in the terminal, no error shown, just restarting kernel or going to next command.
coco_dt = loadRes(self.coco_gt, results) if results else COCO()