Renato Violin

How obtain the predicted text

3

How can I get the predicted text from the start/end tokens?

Fine Tuning - SQuAD 2.0 on GPU 8 GB

20

I've been fine tuning the original xlnet model to run on a 8 GB GPU (RTX 2080). The modifications make possible to fine tuning the model on SQuAD 2.0 dataset...

yolov8 memory usage while training - higher than v5 using same config

3

I'm trying to migrate my project from v5 to v8, using the same dataset, batchsize, imgsize and model size (yolov8m.pt) but with v8 I get OOM in the first epoch....