Comments (10)
the same question, so have you sloved it?
from towards-realtime-mot.
I meet the same question,do you solve it?If you do, please let me know,thanks.
from towards-realtime-mot.
One possible reason is that the 'utils' module conflicts with some system package, try rename the 'utils' module.
from towards-realtime-mot.
One possible reason is that the 'utils' module conflicts with some system package, try rename the 'utils' module.
from towards-realtime-mot.
I meet the same problem? Have you sloved it?
It seems that I have used the wrong model: Darknet-53
changed to JDE-1088x608-uncertainty seems OK
but meet another problem
Lenth of the video: 314 frames
2019-11-07 11:02:00 [INFO]: Processing frame 0 (100000.00 fps)
Segmentation fault (core dumped)
from towards-realtime-mot.
the same question, so have you sloved it?
change models.py like this:
batch_norm=nn.BatchNorm2d
#SyncBN #nn.BatchNorm2d
from towards-realtime-mot.
@MIXALER @Xianqi-Zhang @Zhongdao @xiaocc612
I change the file of models.py.
change SyncBN to nn.BatchNorm2d and it works!
from towards-realtime-mot.
@MIXALER @Xianqi-Zhang @Zhongdao @xiaocc612
I change the file of models.py.
change SyncBN to nn.BatchNorm2d and it works!
Thank you for your reply!
from towards-realtime-mot.
I am having this same problem both in my own virtualenv and in the docker. I tried changing SyncBN to nn.BatchNorm2d and that did not help. When I debug, I get the following call stack:
File "/home/denver/work/Towards-Realtime-MOT/demo.py", line 84, in
track(opt)
File "/home/denver/work/Towards-Realtime-MOT/demo.py", line 59, in track
save_dir=frame_dir, show_image=False, frame_rate=frame_rate)
File "/home/denver/work/Towards-Realtime-MOT/track.py", line 79, in eval_seq
tracker = JDETracker(opt, frame_rate=frame_rate)
File "/home/denver/work/Towards-Realtime-MOT/tracker/multitracker.py", line 161, in init
self.model = Darknet(opt.cfg, opt.img_size, nID=30)
builtins.TypeError: init() got multiple values for argument 'nID'
Any ideas?
from towards-realtime-mot.
On further investigation, it appears my initial problem above was related to issue #116 - when I remove the img_size parameter the code progresses beyond this point, but this error still ends up happening for another reason which I posted in issue #121.
from towards-realtime-mot.
Related Issues (20)
- The output file error HOT 3
- 输入视频检测时显示图片,未响应
- Cityperson.zip from google drive error: invalid zip file with overlapped components (possible zip bomb) HOT 1
- Could find no file with path ? HOT 1
- 图片上没有检测结果 HOT 1
- 怎么查看损失曲线?How to check loss curve?
- box, conf, id, total, nTargets meaning?
- What's the correct value of "conf" during training? HOT 2
- 1-based indexing MOT dataset
- Why the embedding representation of appearance is D*H*W, how can so many representations distinguish the representation of positive and negative samples
- 关于跟踪器update阶段轨迹最后的summarize中self.lost_strack轨迹问题
- can train multi-class Tracking ? HOT 1
- could I use this model with real-stream like camera?
- ZeroDivisionError: division by zero HOT 3
- Why do I train to get Nan result?
- Losing Tracking
- mAP 0 on custom dataset for Car tracking HOT 1
- Cityperson.zip cound not be downloaded from google drive
- TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
- Cityperson Link failure
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from towards-realtime-mot.