EmmaVnPybr-10
EmmaVnPybr-10
hello, is there an easy way to create the precision-recall curve after training?
hallo, What is the best backbone you should use if you are working with tiny granular objects? Or how do you choose it? Thanks
In the eval.py you use AverageMeanPrecision from torchmetrics, in the train.py for evaluation you use the evaluation using pycocotools. When I use them both, I obtain different values for AP....
When I use the fasterrcnn model with backbone resnet101, I always have CUDA out of memory in the "evaluate" after one epoch. in the evaluate itself it gives an error...