Comments (5)
A few questions and comments:
-
Did you run the config with the same batch size, learning rate and schedule that we suggest? Deviating from the recipe we suggest will certainly change the behavior of the losses during training (as is expected)
-
Yes, occasionally we do encounter high losses during training. This is because an image might be out of distribution or have extreme annotations -- something that 3D suffers more from compared to 2D. For this reason, we provide checks and skip gradient updates for these cases. The model, given you use the recipe we provide, should have trained successfully though.
from omni3d.
- I ran Base_Omni3D_out.yaml provided in your repo without any modification. And it will restart training
!! Restarting training at 51028 iters. Exploding loss 2% of iters !!
. Maybe I should keep training and hope after some restarting, the training will be complete? :( - I tried using gradient clip, but it doesn't help.
- Any plan to clear the dataset?
from omni3d.
- Large losses during training
And to confirm you ran with the same batch size. You should certainly keep training the model. We skip updates in the case of large losses to make training robust. The training should complete.
- Gradient clip
Gradient clip is another way to secure your model from large losses (and thus large gradients). We chose to skip the updates; gradient clipping clips the gradients. Our way of skipping updates when losses are large is certainly less aggressive than gradient clipping which is why we prefer it.
- Clear the dataset
@Hiusam this is not a dataset issue. There is nothing in the dataset to clear. 3D detection is simply much much harder than 2D detection. For instance, there are scenes with really far away objects (e.g. scenes with objects as far as 200m) in which case a wrong depth prediction in metric space will produce a large loss and thus large gradients. The solution is not to "clear" the dataset in any way, but to robustify training, which we do.
from omni3d.
Hi @gkioxari , nice work! I also encountered the same issue. Do you have an estimation of how many "retry" it usually needs? It seems that my experiments have been retried many times, e.g.., EST is 21 hours yet after two days it is still in retry. I also use the same Base_Omni3D_out config without any changes. Your suggestions would be very helpful!
from omni3d.
I encountered the same problem. Without modifying the code, the training loss explodes during training in both indoor and outdoor scenes. I have tried resuming the experiments from the saved checkpoint, but it does not work. The training loss explodes soon again.
from omni3d.
Related Issues (20)
- Why some class label is -1
- Code for converting the raw annotation into Omni3d format
- Cannot download category_meta.json even with the link mentioned in the previously closed issues
- How to know whether an image is flipped
- Script for converting objectron to omni3d format HOT 1
- How to obtain the depth sensor point cloud of objectron images in Omni3D
- Installation gets stuck on Google Colab HOT 3
- Unstable training with keypoint loss HOT 1
- training kitti only HOT 6
- The issues of adapting the other models to the omni3d datasets
- Conda install environment HOT 3
- More details about default camera intrinsics in demo.py file
- Incorrect 2D Bbox Labels in Objectron Dataset
- Category Conversion Code from SUN RGB-D to Omni3D Dataset
- Running Cube-RCNN on a different dataset
- KITTI Annotations
- Camera Pose Information
- Hello, if the model requests the same pitch angle of the camera in different dataset?
- How to perform real-time detection
- Run on mobile
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 omni3d.