Closed Angry-Biscuit closed 7 months ago
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 :)
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?
Hi can you share your training log? And does the few-shot target dataset contain 8 images?
Hi, I'm really excited by your work!
While replicating AsyFOD, I've noticed that it's utilizing GPU less than I expected.
How long did it take to run the model w/ Cityscapes to Foggy Cityscapes task?
I'm currently running it on one A5000 and it's estimated to run for 4~5 days.
Is this expected? Or am I doing something wrong?
Thank you for your time.