Comments (6)
Thank you very much. And you can choose any of them to answer.
from sgpn.
Hi @LZDSJTU ,
which file are you looking at?
Edit: nvm it's model.py
from sgpn.
@LZDSJTU the only one I've worked out so far since the code includes a comment:
- line 167:
pts_group_label is a Batch x num_points x num_groups ndarray, I think one hot style so for each point if there are 50 groups then it has 49 0s and one 1. Transposed it's B x NG x NP, so multiplying with itself you get B x NP x NP.
As the comment says # BxNxN: (i,j) if i and j in the same group
So the B x NP x NP has 0s everywhere where point (i, j) not in same group, and 1s where they are.
from sgpn.
Hi, @Ziggareto
When I test the pre-trained model in area 1, I even got the 1
pre-trained model test in area 1 AP in 6 cate. What's more, this also happened in area 5.
Do I set the wrong parameters? And Could you please provide the pergroupthres.txt file to us?
Instance Segmentation AP: [0.77272727 0.96409938 0.58364528 0.9 0.27223911 1.
0.77928571 0.67933635 0.70536131 0.48571429 0.59607843 0.8
0.32612594]
Instance Segmentation mAP: 0.6818933128790516
Semantic Segmentation IoU: [0.98613754 0.98480023 0.93936964 0.95665216 0.82676315 0.95118879
0.9408741 0.89464145 0.88190051 0.95819404 0.83323726 0.91617618
0.88444496]
Semantic Segmentation Acc: %f 0.973563616147
Looking forward your reply.
from sgpn.
Hi @LittleLampChen I haven't been following for ages, but I think pergroupthres.txt is generated by valid.py? Have you run that already?
from sgpn.
Issue 1:
@Ziggareto has given the point.
Issue 2:
diffgroup_samesem_mat_label reprensents points of same semantic class but not same instance. And diffgroup_diffsem_mat_label represents points of neither same class nor same instance.
Issue 3:
pred_simmat represents ||Fsim1 - Fsim2||^2 in the paper. It is the calculation of Lsim.
Issue 4:
Referd from the paper:
"Since the semantic segmentation network is actually wrongly trying to bring pairs of points in our second similarity class closer together in feature space, we also add an α > 1 term to increase the weight of our loss to dominate the gradient from the semantic segmentation output branch."
Issue 5:
When a point belongs to the background, the corresponding row of Pr_obj is 0 not 1. You can refer to section 3.1 of the paper
from sgpn.
Related Issues (20)
- how to train shapenet using SGPN? HOT 1
- Should I retrain the pre-trained model in cross-validation on S3DIS Dataset? HOT 4
- How to prepare h5 files with nuy dataset HOT 2
- Gap test file HOT 1
- invalid syntax: incomplete "try" block
- some question about train.py
- Could you provide the trained model on NYU dataset
- KeyError: "Unable to open object (object 'data' doesn't exist)" HOT 2
- error loading custom checkpoint
- Training and Inference on Semanttic3D and Semanttic Kitti
- KeyError: "Unable to open object (object 'pid' doesn't exist)" HOT 7
- Scannet Evaluation:Page not found HOT 2
- What is the purpose of decreasing group id by 1 in group merging? HOT 1
- Some questions about DBSCAN for the experiments of ShapeNet.
- Could you provide the dataset used in your code?
- IndexError was encountered,does anyone have the same problem
- Pretrained Model: is it still there? if so, how to "tf.load_model" it?
- Prepare ShapeNet Dataset for SGPN
- SGPN on ShapeNet HOT 2
- GroupMerging_old function
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 sgpn.