Comments (6)
Hi, we are using fp16 training with a gradscaler. The gradscaler should tale care of nan/infs.
So to answer your question, the nans should not affect the training. But let me know if you have issues.
from roma.
Thank you so much for your reply. I guess it won't be a problem if nan/inf grads only exist once for every dozens of steps?
from roma.
Exactly, but make sure youre using the gradscaler. Actually I had a lot of issues getting fp16 training to be stable, so let me know if you get any other issues.
from roma.
I meet some backward issues when training:
Have you ever met such problem? I add epipolar error by estimating E matrix when training.
from roma.
Is this the backward of the E solver?
I haven't tried myself, but perhaps if you save the inputs to the solver you may be able to find the issue.
Maybe you picked the same correspondence twice?
from roma.
I find out the problem is caused by backward of torch.linalg.solve in E solver. I added an regularization item to A and solved the problem. Thank u a lot for your kindly reply.
from roma.
Related Issues (20)
- How does T_1to2 generated? HOT 1
- About coordinates normalization
- question about pos_embed in tiny roma HOT 2
- Why use 5 different resolutions in the same convolutional refiner HOT 5
- Training set and test set setting? HOT 23
- How is the performance of dinov2-b14? HOT 1
- Ran into issue with running the demo due to unsupported autocast device_type 'cuda:0' ! Can you tell me how to resolve this ? HOT 2
- Performance regression HOT 1
- about match_keypoints HOT 9
- Draw certainty map in TinyRoma
- The running environment is faulty HOT 3
- download checkpoint?
- Evaluation Metric of WxBS Benchmark HOT 4
- Invalid gradient when finetuning and learning rate with gradient clip setting HOT 2
- image resolution to get percent correct keypoints (PCK)/ EPE
- Has the developer done the detailed effect of feature point matching
- retrained xfeat?
- Coarse vs upsample res HOT 1
- torch AMP for DINOv2 precision issue HOT 2
- Use coco_20k data? HOT 6
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 roma.