Comments (8)
Hi, @SimonSongg . Our R2D dataset is collected in the Carla simulation environment. Please refer to this link for the data format of depth maps and semantic segmentation maps.
from sne-roadseg.
Hi, @SimonSongg . Our R2D dataset is collected in the Carla simulation environment. Please refer to this link for the data format of depth maps and semantic segmentation maps.
Thank you very much!!! Sorry for the stupid question
from sne-roadseg.
Hi, @SimonSongg . Our R2D dataset is collected in the Carla simulation environment. Please refer to this link for the data format of depth maps and semantic segmentation maps.
Hi, @hlwang1124 . I just tried to train by the kitti dataset with resnet 18. And it had an error after an epoch.
(epoch: 1, iters: 290, time: 0.115, data: 0.068) segmentation: 0.463
End of epoch 1 / 1000 Time Taken: 119 sec
learning rate = 0.0010000
Traceback (most recent call last):
File "train.py", line 119, in
avg_valid_loss = torch.mean(torch.stack(valid_loss_iter))
RuntimeError: expected a non-empty list of Tensors
Could you help to fix it? Thanks!!!
from sne-roadseg.
Hi, @SimonSongg . Our R2D dataset is collected in the Carla simulation environment. Please refer to this link for the data format of depth maps and semantic segmentation maps.
I comment lines
119: avg_valid_loss = torch.mean(torch.stack(valid_loss_iter))
123: writer.add_scalar('valid/loss', avg_valid_loss, epoch)
in train.py and I can train without any error.
from sne-roadseg.
It seems that you did not split a validation set.
from sne-roadseg.
It seems that you did not split a validation set.
sorry for the stupid mistake!!!!!!!! I forgot it. Thank you for your patience.
from sne-roadseg.
It's OK. Happy to see that everything works now:)
from sne-roadseg.
Excuse me,I haved referred to https://carla.readthedocs.io/en/stable/cameras_and_sensors/ for the data format of depth maps and semantic segmentation maps,but I still don't how can I convert the depth images and the labels.Could you please tell me the
specific conversion operation?Thank you very much!!!!
from sne-roadseg.
Related Issues (20)
- Testing without depth image input HOT 1
- About palette.txt HOT 1
- error while training
- calib
- KITTI Sequence 00-10 HOT 1
- Save images
- Campus Dataset
- Question about result
- No such file 'latest_net_RoadSeg.pth' HOT 2
- calibration file of R2D dataset HOT 3
- usage of depth image in R2D dataset
- how to convert depth image in R2D HOT 1
- Questions on SNE-RoadSeg+
- Questions about sne
- kitti dataset without validation HOT 1
- R2D issue
- transform depth map to disparity map
- SNE-RoadSeg+ issue
- diffKernelArray HOT 1
- Inference on own data HOT 2
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 sne-roadseg.