Comments (4)
Thanks for your interests in our work!
Here are my answers to the questions:
- For the first question, the best way to choose the threshold is to visualize the label with a couple of scenes and then decide on the threshold. The general rule of thumb is that you want to include labels as dense as possible while not overlapping with too many points in other surfaces or edges.
- For the second question, we tried to eliminate it and we did not observe too much performance decrease.
- Yes. It will. It does not affect the performance much as long as you have dense labels in each surface. Even if for same faces, let's say right and front, there are some in-balanced distribution in the labels. It still does not affect the performance much if you have dense labels for some face.
Hope this answers your question!
from h3dnet.
Thanks for your reply.
I have another question: how are the l_f, l_c, l_o in Eq 2 implemented in the code (ie, loss_helper.py)?
What do objectness_loss_opt
and potential_loss
mean?
Besides, there seems several errors in the code. Please confirm:
H3DNet/models/proposal_module_refine.py
Line 82 in e89d092
[:,:,start+3+num_heading_bin*2+num_size_cluster*4:]
. PS: I don't understand why u use if-else when decoding size and class (ie, L68-87), the code inside the two conditions are the same.- If I didn't understand wrongly, in these two pieces of code:
Line 356 in e89d092
Line 373 in e89d092
'center'
should bemode
.
from h3dnet.
l_f is implemented in here, l_c is implemented in here and it was called here and the majority of l_o is implemented in here.
For the errors:
- This is actually a small trick. I found out that optimizing the semantic label on the box type works slightly better. You can change it to semantic label (what you suggested). I think it should not make much difference. From L68-79, I think you can remove the if-else. I did not fully optimize the code.
- For heading and size, we are only refining the angle offset or box size offset. It we are also changing the semantic type, then it will choose a different starting angle or a starting box size each time with optimization. Then, it will cause the angle offset and box size offset refinement unstable.
from h3dnet.
Got it. Thanks a lot.
from h3dnet.
Related Issues (20)
- How to use H3DNet on custom dataset? HOT 4
- Request for trained models. HOT 3
- Doubt regarding heading angle and box sizes !! HOT 5
- Evaluating on custom data/images HOT 6
- OSError: /lib/x86_64-linux-gnu/libm.so.6: version `GLIBC_2.27' not found HOT 12
- ImportError: Could not import _ext module. HOT 13
- Performance of a model with single backbone HOT 6
- Can you share with us pretrained model ? HOT 3
- Question about data augmentation on ScanNet HOT 1
- RuntimeError: Expected isFloatingType(grads[i].type().scalarType()) to be true, but got false HOT 5
- RuntimeError: Error(s) in loading state_dict for DataParallel: HOT 2
- Finetunning H3DNet on Sub ScannetV2 ( 3 class only) HOT 8
- Train H3DNet on Stanford 3D-Semantics Dataset HOT 4
- viewpoint.json HOT 17
- Error when train on sunrgbd HOT 3
- Visualizations HOT 2
- Problems for pre-processed data HOT 1
- One inplace error HOT 1
- Pre-train model for H3DNet?
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 h3dnet.