-
Notifications
You must be signed in to change notification settings - Fork 9.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
YOLOv3 - Continue on #1695 #3083
YOLOv3 - Continue on #1695 #3083
Conversation
Clean the comments in config file
# Conflicts: # mmdet/models/anchor_heads/__init__.py # mmdet/models/necks/__init__.py # mmdet/models/utils/__init__.py
Hi @ElectronicElephant Btw, @wuhy08 @ElectronicElephant may sign CLA first. |
This comment has been minimized.
This comment has been minimized.
Hi @ElectronicElephant @xvjiarui Sorry for the delay. I have signed the CLA. My effort for implementing YOLOv3 was related to my past project at Western Digital. Since WD has agreed to open source my contribution, I submitted a PR. Now as it is in public domain, you are free to continue to contribute on top of it. I just request you credit WD and me properly. Best HW |
Great, thanks! Frankly, your PR works like a charm under a single GPU, achieving very high mAP. I'll try to make it run on multiple GPUs. I'll reserve all your commit history, as long as the license. 🤝 |
port to mmdet-2.0 api
unify registry
port to ConvModule and remove ConvLayer
Refactor backbone, lint and format
Please merge master to resolve conflicts. |
My ap drops a lot in my own dataset after changing @ElectronicElephant head to the refactored one. Shouldn't it be the same to the old version with |
Hi @LMerCy, |
@sudo-rm-covid19 Yes, i agree all what you say. |
Yes, I think so and it will choose one anchor per gt. |
@sudo-rm-covid19 If two gt with similar size fall in the same cell, and they have the same iou with the same anchor, then only one gt will match the anchor. But maybe this may have little influence. What actually confuse me is my ap |
Hi, how do I replace Darknet53 in Yolov3 with MobileNetV2? |
IMHO, just changing the config file is OK. It should be working in the |
Hi all,
@WenqiangX and I are glad to help implement YOLOv3, and perhaps v4 as well, if everything goes on well. We are from (MVIG, SJTU)[http://mvig.sjtu.edu.cn] and have spent quite a little time surveying all kinds of YOLOv3 implementation in PyTorch. Also, we have spent a lot of time working on the
gluon-cv
version of YOLOv3, which relays onmxnet
. So, we are familiar with it.Months ago, @wuhy08 has contributed a lot (#1695), but there are still some problems to be solved. I have tested his implementation and found it can be trained using one vid card and achieve ~38 mAP in (618, 618) resolution, which is pretty good. However, it fails to train on multiple cards and achieves very low mAP even with
find_unused_parameters=True
. Still, great thanks to him and Western Digital.Basically, we aim to complete the following list:
If you have any suggestions, feel free to comment.
Also, I hope that the authors of this project can manage your time to review the code to see if there is any major problems so that we can save some time.
This pr is still in an early stage, but is expected to finish by the end of July.
If everything is good, could you please close the original pr so that we can continue to work here?