Comments (16)
We are processing that. I will keep you updated. And thank you for the pointer!
from planercnn.
Hi, I was trying to run the training code, and I found in
planercnn/datasets/plane_dataset.py
Line 94 in 557583f
it asked a .tsv file named
scannetv2-labels.combined.tsv
is needed, and inplanercnn/datasets/plane_dataset.py
Line 43 in 557583f
a
.txt
file named with the scene_id seems required to be under each scene's directory.
May I ask where I can get access to these files?
from planercnn.
They are from the original ScanNet dataset. You need to download the data and uncompress the .sens file (maybe delete the .sens file after uncompression to save space).
from planercnn.
Thanks.
Just for someone else who is not familiar with ScanNet dataset, to get thees files, please use the argument --type .sens .txt
and --label_map
during download.
By the way, how can I run the training with multiple gpu? I cannot find any line contain the function torch.nn.DataParallel(model).cuda()
, which I usually use for multi-gpu training. I tried to uncommment
Line 360 in 41a0f63
but it seems does not work as well.
from planercnn.
Sorry but is there any way we can run ScanNet original sens reader.py for all sens files scattered in different scene files? It looks like I cannot move all .sens file into one directory as it is important to map to corresponding annotations in later merging operation.
from planercnn.
Hi @dreamPoet , I just simply set the --filename
as the path/to/Scannet_data/scans/
, and it seems work well for me.
from planercnn.
Hi @yangengt123, do you simply use --filename path/to/scans/
οΌ I get the error Is a directory: '../../ScanNet/scans/'
. If I use ../../ScanNet/scans/*/*.sens
, it gives error unrecognized arguments: scans/scene0000_01/scene0000_01.sens
...
from planercnn.
Yeah, the only difference is I used absolute path, something like /hdd/Scannet_data/scans/
, and I did not meet any trouble to parse it. But I think it is always possible to look into the SensorData.py
to check which path the load
function is using.
from planercnn.
Thanks.
Just for someone else who is not familiar with ScanNet dataset, to get thees files, please use the argument--type .sens .txt
and--label_map
during download.By the way, how can I run the training with multiple gpu? I cannot find any line contain the function
torch.nn.DataParallel(model).cuda()
, which I usually use for multi-gpu training. I tried to uncommmentLine 360 in 41a0f63
but it seems does not work as well.
Thank you, but have you solve the problem of multi-GPU training now? I meet the same problem.
from planercnn.
By the way I use srun with gpu:8 and -n8 as bash command.
from planercnn.
And there are three parameters related to batch size, one in config, one in option, and one for dataset loader...Frankly, I am a bit of confused...
from planercnn.
@dreamPoet did you solve the .sens files extraction problem using reader.py? I'm in the exactly same problem. Any idea?
Best.
from planercnn.
Well, I could solve it using python 2.7 but calling one .sens file per once. And dont forget about the reader.py options arguments such as --export_depth_images, --export_color_images, etc.
from planercnn.
That is right, I use python2.7. Maybe this is the reason I did not meet any problem.
By the way, may I ask if you can still download the data from ScanNet recently? I tried to download the data to a new server but it seems my download script cannot work.
from planercnn.
Ah thanks.
Yes, I've downloaded the whole data last week. Maybe they've changed the urls. I think you can contact [email protected] and ask them about the script.
from planercnn.
yeah, maybe I should. Thanks.
I will close this issue now.
Please let me know if any pre-processed data become available.
from planercnn.
Related Issues (20)
- how can i get the normal of planes for each frame extracted from /scene_id/scene_id.sens? HOT 2
- Pretrained model links are not working HOT 3
- Nothing happened with nvcc HOT 6
- FileNotFoundError: [Errno 2] No such file or directory: '../../Data/ScanNet//scannetv2-labels.combined.tsv' HOT 5
- Pretrained model links are not working now HOT 2
- Torch summary on the model
- The ground truth provided by PlaneRCNN has large errors! HOT 2
- After training scannet from scratch while inferencing the trained model facing error HOT 1
- Plane parameter
- Unable to compile NMS and ROI-Align on RTX 3080 HOT 3
- Question about Training Data
- Docker image HOT 2
- Keep the order of original image files while detecting planes
- plane_XYZ coordinate system
- cuda 8.0 on Ubuntu 18.0.4
- Plane segmentation evaluation experiment on ScanNet
- Trained Models
- Problem on download of scannet plane annotation
- How to find the plane normal? HOT 1
- How to transfer module from 'pth' to βonnxβοΌ eg: checkpoint_refine.pth to checkpoint_refine.onnx
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from planercnn.