Open QCHighing opened 4 years ago
@QCHighing are you training only person data? what is the intention of doing this ? is it to obtain high accuracy for person dataset since the total mAP for yolact 29.8 and yolact_plus 34.6 will be get high accruacy for only person
@abhigoku10 Yeah, thanks for your Timely reply. I only need to detect the person, as same as Issue #65 . It would be better if I could get higher accuracy. If my environment can be configured, I will also try yolact_plus, but not. Can you give me some suggestions on model training for this issue? Why the score is getting lower and lower?What went wrong with my configuration? Thanks again!
S
is not score but an extra semantic segmentation loss. That going down is perfectly normal (and is what should be happening).
As for lr, I think what you have is fine? Make sure you're loading the pretrained weights with --resume
and have applied the fine-tuning change in #36.
Thanks a lot.
@QCHighing did you figure out how to improve person mAP? I tried retraining with your settings but person mAP gets worst than the pretrained model on the whole 80 classes.
@Maxinho96 i increased the person data and then used yolact++ architecture i was able to get good improvement
@Maxinho96 i increased the person data and then used yolact++ architecture i was able to get good improvement
Did you use a custom dataset or another online person dataset? I have found Open Images and Cityscapes but I am not sure if they can give an improvement.
@Maxinho96 I have stopped this job. I can reopen the issue.
@Maxinho96 i have used pedestrian dataset since my applications required pedestrains scenes
@Maxinho96 i have used pedestrian dataset since my applications required pedestrains scenes
You used Cityscapes maybe? Or you built your dataset? Building an instance segmentation dataset is expensive, so Cityscapes would save a lot of time.
@QCHighing did you figure out how to improve person mAP? I tried retraining with your settings but person mAP gets worst than the pretrained model on the whole 80 classes.
I have the same problem... @dbolya Do you have any good solutions instead of adding new dataset? Thank you very much!!!
@QCHighing Hi, did you managed to retain using COCO-person?
@QCHighing May I request for pre-trained model only for COCO-person class?
Hi, Thanks for the advance work you have done! This model helped me a lot. I would also like to retrain the model for one class(coco-person), and I have browsed many related issues, but I encountered some doubts.
Why the score is getting lower and lower?Looks like it finally converged to around 0.08.
【0】 10 || B: 1.702 | C: 3.531 | M: 2.854 | S: 0.607 | T: 8.694 || ETA: 7:15:17 || timer: 0.633 【0】100 || B: 1.460 | C: 2.346 | M: 2.624 | S: 0.353 | T: 6.784 || ETA: 7:07:40 || timer: 0.606 【0】300 || B: 1.438 | C: 1.732 | M: 2.513 | S: 0.169 | T: 5.852 || ETA: 7:07:18 || timer: 0.638 【0】800 || B: 1.522 | C: 1.586 | M: 2.468 | S: 0.106 | T: 5.682 || ETA: 7:02:46 || timer: 0.679 【0】2550 || B: 1.486 | C: 1.518 | M: 2.430 | S: 0.087 | T: 5.520 || ETA: 6:45:35 || timer: 0.672
How to set lr in this case? I just need to retrain on Person class.
Looking forward to your reply,Thanks a lot!
My config is:
I have removed other annotations and categories in the COCO dataset.
This is my dataset:
Train command is:
python train.py --config=yolact_coco_person_config --resume=weights/yolact_base_54_800000.pth --start_iter=0