Comments (10)
@YoushaaMurhij yes your correct, there was issue in the color encoding , thanks for point it out currently have resolved this issue now getting correct output
from cylinder3d.
Are you using RVIZ? Can you also show the GT?
from cylinder3d.
@YoushaaMurhij @xinge008 i am using pptk viewer to look into the annotations and predictions of semantic kitti data , below is the gt and right is predictions
from cylinder3d.
It feels like you have a color encoding problem .. no more, when converting the labels to colors.
Could u check that?
from cylinder3d.
how to get the visual results from raw network output?
the Cylinder3D network get [1, 480, 360, 32] input, and output is [1, 20, 480, 360, 32] torch tensor
res = model(train_pt_fea_ten, train_vox_ten, batch_size)
predicted_labels = torch.argmax(res, dim=1)
from cylinder3d.
@muzi2045 i am actually saving the labels and then using semantic kitti code base to view the predicitions please find the reference which worked for me https://github.com/edwardzhou130/PolarSeg/blob/master/test_pretrain_SemanticKITTI.py
from cylinder3d.
thanks a lot, I'll try it.
from cylinder3d.
with the semantic-kitti api codebase, here is some result output:
why the road points are colored as black?
maybe the color map need to be change or something wrong when generate the points label file.
@abhigoku10
from cylinder3d.
@muzi2045 you have to use proper color map during saving and visualization
from cylinder3d.
@muzi2045 i am actually saving the labels and then using semantic kitti code base to view the predicitions please find the reference which worked for me https://github.com/edwardzhou130/PolarSeg/blob/master/test_pretrain_SemanticKITTI.py
when i use the same code as you, i got the error "ValueError: Input must be 1- or 2-d."---do you know what the problems ?
(pytorch) ziudarkin@ziudarkin-ubuntu:~/PolarSeg$ python train_SemanticKITTI.py
train_SemanticKITTI.py
Namespace(check_iter=4000, data_dir='data', grid_size=[480, 360, 32], model='polar', model_save_path='./SemKITTI_PolarSeg.pt', train_batch_size=2, val_batch_size=2)
0%| | 0/136 [00:00<?, ?it/s]Traceback (most recent call last):
File "train_SemanticKITTI.py", line 197, in <module>
main(args)
File "train_SemanticKITTI.py", line 129, in main
iou = per_class_iu(sum(hist_list))
File "train_SemanticKITTI.py", line 27, in per_class_iu
return np.diag(hist) / (hist.sum(1) + hist.sum(0) - np.diag(hist))
File "<__array_function__ internals>", line 6, in diag
File "/home/ziudarkin/anaconda3/envs/pytorch/lib/python3.7/site-packages/numpy/lib/twodim_base.py", line 303, in diag
raise ValueError("Input must be 1- or 2-d.")
ValueError: Input must be 1- or 2-d.
0%| | 0/136 [00:01<?, ?it/s]
from cylinder3d.
Related Issues (20)
- 怎么制作自己的数据集,我的数据是无人机激光雷达扫描的
- Does it currently support distributed multi card training ? HOT 3
- hello,how to convert onnx model ? how to deploy to embedded ?
- How to load a pretrained model?
- Fix: data_path vor train and val dataloaders are the same
- TypeError: No matching definition for argument type(s) array(uint8, 3d, C), array(int32, 2d, C) HOT 6
- How to output a shape of (N,1) ?
- RuntimeError: radix_sort: failed on 1st step: cudaErrorUnsupportedPtxVersion: the provided PTX was compiled with an unsupported toolchain. HOT 2
- 请问一下kitti的背景类为什么不需要训练
- The performance of the baseline model was 10 percentage lower than Cylinder
- The size of cubic voxel in the paper
- About multi-scan task on SemanticKITTI
- About the weights in WCE HOT 5
- Error when trying to re-train
- Details request HOT 2
- About DDP HOT 1
- How to submit nuscenes results on Test set
- Generalization Experiment-Related Questions
- C++ version?
- about pretrained model
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 cylinder3d.