Expected training time? about asyfod HOT 3 CLOSED

Hi I sometimes meet the same problem. I guess the reason is that the MMD selection process can be optimized. During this process, the utilization of GPU is somewhat low. I run Cityscpes to Foggy at around 1 or 1.5 days for convergence with one V100 and around 150-200 epochs. May this help you :)

from asyfod.

Thanks for the reply!
I have one more question.
I ran the code using command given in the main page, which is python train.py --img 640 --batch 12 --epochs 300 --data ./data/city_and_foggy8_3.yaml --cfg ./models/yolov5x.yaml --hyp ./data/hyp_aug/mm1.yaml --weights '' --name "test"

But I got mAP50 value of 0.3482 (averaged over two experiments, 0.3498 and 0.3466 each).
Did I miss something?

from asyfod.

Hi can you share your training log? And does the few-shot target dataset contain 8 images?

from asyfod.