Skip to content

Issues: twangnh/Distilling-Object-Detectors

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.

Sign up for GitHub

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

25 Open 5 Closed
25 Open 5 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Visualize the mask like the image in your paper
#31 opened Mar 12, 2024 by xthdsg
How to scale ground-truth to the feature layers?
#30 opened Nov 7, 2023 by aidevmin
3
training feature apdatation conv2d
#29 opened Oct 19, 2023 by minhhotboy9x
为什么Teacher模型是1G大小，Student也是1G大小
#28 opened Jun 17, 2022 by DonMuv
感谢您分享代码
#27 opened Aug 24, 2021 by zengbohan0217
res101h pretrained model
#26 opened Jun 4, 2021 by TheLostIn
about imitation loss weight
#25 opened Feb 23, 2021 by chongkuiqi
6
你好，请问arxiv出了嘛
#24 opened Jan 3, 2021 by xiweiya
ImportError: torch.utils.ffi is deprecated. Please use cpp extensions instead.
#23 opened Nov 16, 2020 by mmkamani7
1
Thanks for sharing your nice research and codes!
#22 opened May 29, 2020 by poperson1205
problem with installing
#21 opened Apr 22, 2020 by pipilurj
2
N_p calculation
#20 opened Apr 20, 2020 by adamwolff2
Hi! Have you guys try out batch size larger than 1?I want to know how to implement it?
#19 opened Apr 5, 2020 by moFang222
2
蒸馏带fpn的faster rcnn遇到问题
#18 opened Mar 23, 2020 by UcanSee
when distilling Faster RCNN with FPN, do we need to firstly assign gt box to different FPN level and then generate imitation region? Or for every FPN level, we generate imitation region according to all gt boxes?
#17 opened Feb 26, 2020 by UcanSee
3
when distillation with FPN，which feature map shuold we select to calculate imitation loss, feature map of FPN(P3、P4...) or feature of backbone(C3、C4...) or others?
#15 opened Jan 14, 2020 by UcanSee
4
warm step
#13 opened Dec 5, 2019 by ShaniGam
3
vgg11蒸馏跟非蒸馏的模型测试结果是一样的
#12 opened Nov 29, 2019 by Liys0558
1
VGG 16 (Teacher) mAP is lower than the reported
#11 opened Nov 14, 2019 by gauravkrnayak
10
关于mask_batch的问题
#10 opened Oct 22, 2019 by TangAL0203
lack of nms_cuda.c
#9 opened Oct 22, 2019 by ex-yangguoqing002
2
Is res50h pertained on ImageNet?
#8 opened Sep 12, 2019 by shuzhangcasia
2
请问有没有试过backbone 为resnet的蒸馏
#7 opened Sep 1, 2019 by cjt222
2
can't load model!
#6 opened Jul 24, 2019 by oxygenman
5
SSD
#2 opened Jun 13, 2019 by p517332051
10
ProTip! Mix and match filters to narrow down what you’re looking for.