Closed lucasjinreal closed 2 years ago
Hi, it will be useful to save the intermediate inputs to reproduce what has lead to nan results (a try catch will do). I've met a similar problem w/ ciou loss when the gt box of some samples is oversized. My walkthrough was (only when nan is occasional)
loss = torch.nan_to_num(loss)
Just curious, what is the possible gain for 700 epochs training?
V0.2.0 code use tal and different iou loss strategy. Training will be more stable.
@shensheng272 hi, what's new updates on v0.2.0 specifically?
@jinfagang In short: What new. Also tech report has been released.
Hi, I applied SIOU in yolov6 but after about 700 epoch get Nan values in iou loss, does there any possible reason?
my box is also cycywh