Comments (4)
Hey both of you, and sorry for the late answer. It is a known issue, and it seems like training the whole network from scratch leads to instability. The fix is to load pre-trained weight from a 1-timestep model (FIERY Static) first because training the whole future prediction model as discussed here: #8
from fiery.
Hey,
Thanks for sharing the Fiery model and article publicly, it was a great read.
I also tried the same setup and have the same issue. I tried to dig a little bit deeper and found out that running means and running variances of batch normalization are getting first to -infinity and then to nan. This also causes the loss to go to nan. The loss seems to get back from the nan-values, however, the model will still output -infinities for the segmentation.
Best regards,
Markus
from fiery.
Hey,
Thanks for sharing the Fiery model and article publicly, it was a great read.
After I train the model for epoch I got loss as negative value.Do you know the reason?
Best regards,
Cara
from fiery.
Hey Cara, the negative loss value is due to the adaptive weighting of the losses using uncertainty. There is an additional loss term that prevents the weight from growing too large (see page 5 https://arxiv.org/pdf/1705.07115.pdf)
from fiery.
Related Issues (20)
- No module named 'pytorch_lightning.metrics' HOT 1
- AssertionError: Database version not found: /opt1/data/nuscenes/trainval/v1.0-trainval HOT 2
- Is future_egopose necessary for inference? HOT 3
- xavier possible?
- def get_feature()
- May I know where is the checkpoint getting saved? HOT 2
- Pytorch Lightning stuck the computer and finally killed HOT 1
- During the evaluation, why are you storing uncertainty values which is multiplied by 0.5 ? I could not find anything related to that in paper
- RAM is getting accumulated for each epoch
- Dear author, how to generate the gt labels for the Nuscenes dataset? thanks.
- Dear author,the total loss value <0 ,is it normal?
- How long would it take for training
- Bad results when evaluating pretrained checkpoints HOT 1
- How to get VPQ during the evaluation HOT 2
- How to visualize like in th epaper shown ,, only show the cam_front part with a mask?
- How to Run visualization on custom images using pretrained model inference HOT 1
- Black ego vehcihle is not in predicted visualization HOT 1
- Visualization about distribution of futures HOT 1
- output of visualization is BLANK HOT 3
- Colab Link in README.md is broken
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 fiery.