Comments (2)
The main error of your log is Signal 11 (SIGSEGV). It's maybe an internal bug in torch/mmcv ddp. I don't encouter this issue in difference machines yet. But you can try to install another version of mm-series package and torch.
torch==2.0
torchvision==0.15.0
mmcls==0.25.0
mmcv-full==1.6.0
mmdet==2.26.0
mmdet3d==1.0.0rc6
mmsegmentation==0.29.1
with CUDA 11.7/11.8
from lanesegnet.
Hello, @sephyli
Thank you for reply.
I could run the LaneSegNet with --show
option after prepairing your telling environment by Docker.
As a result, I got the below output in colsole and visuallized image.
Would it be OK about the LaneSegNet behavior??
(lanesegnet) root@my-pc:/opt/LaneSegNet# ./tools/dist_test.sh 2 --show
++ date +%y%m%d.%H%M%S
+ timestamp=240228.014608
+ WORK_DIR=work_dirs/lanesegnet
+ CONFIG=projects/configs/lanesegnet_r50_8x1_24e_olv2_subset_A.py
+ CHECKPOINT=work_dirs/lanesegnet/lanesegnet_r50_8x1_24e_olv2_subset_A.pth
+ GPUS=2
+ PORT=28510
+ python -m torch.distributed.run --nproc_per_node=2 --master_port=28510 tools/test.py projects/configs/lanesegnet_r50_8x1_24e_olv2_subset_A.py work_dirs/lanesegnet/lanesegnet_r50_8x1_24e_olv2_subset_A.pth --launcher pytorch --out-dir work_dirs/lanesegnet/test --eval openlane_v2 --show
+ tee work_dirs/lanesegnet/test.240228.014608.log
WARNING:__main__:*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
*****************************************
load checkpoint from local path: work_dirs/lanesegnet/lanesegnet_r50_8x1_24e_olv2_subset_A.pth
load checkpoint from local path: work_dirs/lanesegnet/lanesegnet_r50_8x1_24e_olv2_subset_A.pth
[>>>>>>>>>>>>>>>>>>>>>>>>>>>] 4806/4806, 8.6 task/s, elapsed: 560s, ETA: 0s2024-02-28 01:55:49,196 - mmdet - INFO - Visualizing results at work_dirs/lanesegnet/test/vis/...
No protocol specified
2024-02-28 01:55:57,188 - mmdet - INFO - Visualize done.
2024-02-28 01:55:57,188 - mmdet - INFO - Starting format results...
2024-02-28 02:00:03,855 - mmdet - INFO - Starting openlanev2 evaluate...
calculating distances:: 100%|███████████████| 4806/4806 [09:37<00:00, 8.32it/s]
{'mAP': 0.3345044255256653, 'AP_ls': 0.31961587, 'AP_ped': 0.349393, 'TOP_lsls': 0.2537521315543861}
from lanesegnet.
Related Issues (20)
- CHILD PROCESS FAILED WITH NO ERROR_FILE HOT 1
- segmentation fault HOT 4
- ms_deform_attn_impl_forward implementation for cuda not found HOT 1
- Temporal fusion HOT 2
- 兄弟 ,你这个跟maptr有什么区别么 [无意引战,关闭issue了,主要是没太get到与maptr的区别] HOT 2
- potential bug in loading pipeline HOT 1
- dist_test.sh error HOT 2
- Migrate data to map element detection HOT 7
- any tutorial to convert Argoverse V2 data into lane segment annotation? HOT 1
- Performance of LaneSegNet for Map Element Bucket HOT 1
- point cloud range change,only use front camera HOT 1
- About evaluation results
- Question about evaluation code HOT 3
- The det_t is only 36.09. HOT 1
- wrong in the corner and how to visualize bev features? HOT 1
- EOFError: Ran out of input
- how to detect the curb HOT 1
- LaneSegNet-tiny and LaneSegNet HOT 1
- Cannot export ONNX model using mmdet v2.26.0
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 lanesegnet.