Skip to content

Issues: xingyizhou/CenterNet

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

Clear current search query, filters, and sorts
444 Open 557 Closed
444 Open 557 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

wh_loss is too large
#319 opened Sep 5, 2019 by unlabeledData
8
hello author, have you explored the reason why CenterNet-HG can't converage in reasonable time on PASCAL VOC?
#314 opened Sep 1, 2019 by JacobYuan7
2
my hm_loss in val is very large and won't decrease, can you give me some advice?
#312 opened Aug 31, 2019 by xiaosibai
1
It occur 'OSError: [Errno 22] Invalid argument' when load the site to retrain.
#309 opened Aug 30, 2019 by Beam-wi
1
demo.py: error: the following arguments are required: task An exception has occurred, use %tb to see the full traceback.
#308 opened Aug 30, 2019 by GuoChuan1314
1
Transfer learning on very small dataset
#307 opened Aug 29, 2019 by duklin
4
The worse with hourglass than dla to train my datasets. The parameers were set as follow.
#304 opened Aug 29, 2019 by Beam-wi
7
现在的HG网络用的是Hourglass-104，显存占的太大，可不可以提供小一些的HG网络，比如Hourglass-50、Hourglass-30？Now the HG network uses Hourglass-104, which occupies too much memory. Can we provide a smaller HG network, such as Hourglass-50, Hourglass-30?
#302 opened Aug 29, 2019 by zoufangyu1987
5
请问谁有支持DCNv2结构的pytorch模型转caffe模型的脚本吗？Does anyone have a script to support the conversion of pytorch model to Caffe model in DCNv2 structure?
#299 opened Aug 29, 2019 by zoufangyu1987
5
--keep_res gpu memory is fifferent
#297 opened Aug 27, 2019 by lg12170226
1
DCN. Can I use DCN with kernel_size 7x7
#296 opened Aug 27, 2019 by shuoshuoa
1
Msra_network without DCN
#295 opened Aug 26, 2019 by mmanoharahere
5
ResNet101-FPN
#294 opened Aug 26, 2019 by FightStone
3
How to set 2D detection training？And how to get the calib. Whether there is no need the calib for 2D detection?
#293 opened Aug 25, 2019 by Beam-wi
1
I have meet error in make.sh
#282 opened Aug 20, 2019 by leavewave
2
How to calc dataset specific eigenvalues and eigenvectors
#280 opened Aug 19, 2019 by dvbvr
2
Unable to run
#275 opened Aug 16, 2019 by soulslicer
7
train my own dataset and the effect is bad
#274 opened Aug 16, 2019 by thinkyang88
6
Bugs in gaussian_radius
#273 opened Aug 16, 2019 by sh1r0
1
DLA32 1x performance
#270 opened Aug 15, 2019 by twangnh
4
Comparing with ExtremeNet and CornerNet
#269 opened Aug 14, 2019 by vinbhaskara
11
offset loss
#266 opened Aug 14, 2019 by CF2220160244
4
syncbn ?
#265 opened Aug 13, 2019 by windyrobin
1
other low flop backbone
#263 opened Aug 12, 2019 by twangnh
2
inference without --flip_test runs way slower bug Something isn't working
#261 opened Aug 9, 2019 by vinbhaskara
2
ProTip! Follow long discussions with comments:>50.