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 559 Closed
444 Open 559 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

There is no output result after running demo
#482 opened Nov 22, 2019 by forevergogi updated Nov 26, 2019
3
我想计算预测中心点和真值中心点之间的距离应该在那里修改？
#470 opened Nov 16, 2019 by 201814476 updated Nov 28, 2019
8
int-cast should be applied.
#489 opened Nov 28, 2019 by TatsuyaShirakawa updated Dec 1, 2019
1
use the hourglass backbone don't download the pretrain weights，how can i download this
#360 opened Sep 16, 2019 by leavewave updated Dec 2, 2019
4
how can I prepare the labels for multi_pose training?
#485 opened Nov 26, 2019 by zry12321 updated Dec 2, 2019
3
torch.jit.frontend.NotSupportedError: slicing multiple dimensions at the same time isn't supported yet
#516 opened Dec 8, 2019 by lyy-fighting updated Dec 8, 2019
1
pytorch转caffe 出现这个问题，怎么办？Cannot copy param 0 weights from layer 'conv_transpose1'
#257 opened Aug 7, 2019 by zoufangyu1987 updated Dec 18, 2019
7
多人姿态估计任务中，得到人的关节点，然后是怎么让这些关节点属于一个人？
#540 opened Dec 23, 2019 by zgsxwsdxg updated Dec 23, 2019
why the result of DLAV0-46 DLAV0-60 is worse than DLAV0-34
#542 opened Dec 25, 2019 by Dantju updated Dec 25, 2019
Dataloader crashes if num_worker>0
#566 opened Jan 3, 2020 by qingnanli updated Jan 4, 2020
1
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 15 and 4 in dimension 1 at /opt/conda/conda-bld/pytorch_1532581333611/work/aten/src/TH/generic/THTensorMath.cpp:3616
#370 opened Sep 20, 2019 by WZHsmile updated Jan 6, 2020
2
About the reval.py
#421 opened Oct 23, 2019 by DangerousY updated Jan 6, 2020
4
should w, h be h, w in draw_msra_gaussian()?
#483 opened Nov 25, 2019 by TatsuyaShirakawa updated Jan 7, 2020
7
why Hourglass-104 predict two output?
#573 opened Jan 6, 2020 by MTfast updated Jan 9, 2020
1
why not use log(w)&log(h) like CSP?
#572 opened Jan 6, 2020 by Dantju updated Jan 9, 2020
2
Segmentation fault when using: python demo.py ctdet --demo ../images/17790319373_bd19b24cfc_k.jpg --load_model ../models/ctdet_coco_dla_2x.pth --debug 2
#181 opened Jul 3, 2019 by Kenneth-X updated Jan 10, 2020
4
A question about the different residual module from original implementation
#580 opened Jan 10, 2020 by ethanyanjiali updated Jan 10, 2020
Needs help on some magic number and abbreviation used in the code
#581 opened Jan 10, 2020 by ethanyanjiali updated Jan 10, 2020
Where does the size and offset get used to calculate the loss?
#582 opened Jan 10, 2020 by ethanyanjiali updated Jan 15, 2020
3
Please provide ONNX or coreml model file for ctdet_coco_dla_2x.pth help wanted Extra attention is needed
#493 opened Nov 28, 2019 by ShreshthSaxena updated Jan 16, 2020
7
how to use demo.py get 3d detection?
#254 opened Aug 6, 2019 by z-hou updated Jan 16, 2020
2
change dla34 to dla60 result wrong
#578 opened Jan 9, 2020 by Amore-HDU updated Jan 16, 2020
2
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 updated Jan 19, 2020
5
Pose keypoints thresholding
#592 opened Jan 20, 2020 by teaddicted updated Jan 20, 2020
What are the AP and AR values of each category in the test task
#601 opened Feb 3, 2020 by zhanghongruiupup updated Feb 3, 2020
ProTip! Adding no:label will show everything without a label.