Comments (4)
Hi. Thanks for pointing out this problem.
It happened because the collected npy files should be put under ./datasets/S3DIS/scenes/data
folder.
Please check the latest version with the correct save path for both datasets:
attMPTI/preprocess/collect_s3dis_data.py
Lines 70 to 71 in 7ca79ab
attMPTI/preprocess/collect_scannet_data.py
Lines 120 to 121 in 7ca79ab
from attmpti.
Thank you for your reply, but the problem doesn't seem to be solved.
I've put the npy files under ./datasets/S3DIS/scenes/data and run
'python room2blocks.py --data_path=/attMPTI-main/datasets/S3DIS/scenes/data/' under the preprocess folder,
It show:
0 scenes to be split...
Total samples: 0
from attmpti.
Have u tried python ./preprocess/room2blocks.py --data_path ./datasets/S3DIS/scenes/
under the attMPTI
?
from attmpti.
Thank you very much.
I tried the instruction you said and it works.
from attmpti.
Related Issues (20)
- About class2scans.pkl HOT 1
- Model trained weights
- About eval script
- extra ) in preprocess/collect_scannet_data.py HOT 1
- gpu errors HOT 5
- room2blocks.py giving inconsistent number of blocks compared to paper. HOT 4
- model.train() mode not specified in pre_train.py HOT 1
- eval.py error for S3DIS-S0-N2-K5 HOT 1
- eval_attMPTI.sh HOT 2
- Question about pointcloud sampler HOT 1
- Training Time HOT 2
- transform: error
- Adapt to part-level segmentation
- The ScanNet dataset
- from torch-cluster import fps报错 HOT 1
- Errors occur when running 'bash train_attMPTI.sh' HOT 3
- transform: failed to synchronize: cudaErrorIllegalAddress: an illegal memory access was encountered
- Performance on different setting.
- How many graphics cards and how much memory are needed to run this experiment
- Visualization of Point Cloud Results HOT 11
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 attmpti.