Comments (2)
Hi, Thanks for your interest in our work. The settings inside of the parameters.txt should be the right ones. Regarding reinit_var yes your interpretation is right, if you didn't change anything for the architecture, you dont have to set reinit_var as True.
For the 3rd and 4th questions, I was checking segmentation accuracy of validation for the pre-training stage, and for the full training checking the instance loss. In my experience, these lidar segmentation models really hard for overfitting as they do random sampling in every iteration. And you are right as it takes too much time I was not doing synchronized validation, I would suggest checking validation segmentation performance along with instance loss during training. But if I remember correctly 1000 epochs should be more than enough to get similar performance with the model that we shared.
Hope these details would help, otherwise please do not hesitate to ask more details.
from 4d-pls.
Thank you for the prompt reply. I will train following your instructions and come back to you if I have further questions!
from 4d-pls.
Related Issues (15)
- "RuntimeError: Error(s) in loading state_dict for KPFCNN:" when running test_models.py HOT 5
- 4D-PLS on PanopticNuscenes HOT 1
- Single-frame panoptic segmentation results on validation set HOT 1
- Question about testing of the pre-trained model HOT 2
- evaluation HOT 3
- visualization tools
- Inquiry on GPU Memory Requirements for 4D Panoptic Lidar Segmentation Training
- Dataloader structure for other datasets HOT 1
- A question about training HOT 4
- Traning schedule and problem when running test_models.py HOT 5
- Questions about merged_points and test_models.py HOT 7
- Testing model and time HOT 20
- Ground Truth Labels for 4D Volume Formation during Training HOT 1
- single-frame 4DPLS model HOT 23
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 4d-pls.