Comments (8)
Yes, it is possible. In our original DN-DETR repo, DN-Deformable-DETR can get 46.1
in 12 epochs.
One reason for your better performance is that training with small batchsize will accelerate convergence in the early stage, I have verified this before.
In addition, detrex implementation is better than our original DN-DETR repo. (:
from detrex.
Yes, it is possible. In our original DN-DETR repo, DN-Deformable-DETR can get
46.1
in 12 epochs. One reason for your better performance is that training with small batchsize will accelerate convergence in the early stage, I have verified this before. In addition, detrex implementation is better than our original DN-DETR repo. (:
Thanks, but I wonder why the result of DN-Deformable-DETR in paper[1] is 43.4 and why 'Deformable' can bring so large improvement. DN-Detr-R50 get only 38.5 in paper[2] and I also verified it.
from detrex.
[1] DN-DETR: Accelerate DETR Training by Introducing Query DeNoising
[2] GROUP DETR: FAST DETR TRAINING WITH GROUPWISE ONE-TO-MANY ASSIGNMENT
from detrex.
The 43.4
result is our initial implementation without deformable attention in the decoder and some other optimizations. Our released model performs better by better combine deformable detr and dn-detr.
DN-Detr-R50 gets only 38.5 because detection models without multi-scale features converge slowly and cannot do well on small objects. Multi-scale features are strong, and deformable attention is also strong to fuse multi-scale features well.
All these make it even stronger.
from detrex.
The
43.4
result is our initial implementation without deformable attention in the decoder and some other optimizations. Our released model performs better by better combine deformable detr and dn-detr.DN-Detr-R50 gets only 38.5 because detection models without multi-scale features converges slowly and cannot do well on small objects. Multi-scale features are strong, and deformable attention is also strong to fuse multi-scale features well.
All this make it even more stronger.
Thanks very much for your answer!
from detrex.
man i just wanna know how long you train your model on "dataloader.train.total_batch_size = 4 and train.max_iter = 360000" ? appreciate!!
from detrex.
man i just wanna know how long you train your model on "dataloader.train.total_batch_size = 4 and train.max_iter = 360000" ? appreciate!!
Training DN-Deformable-DETR-R50 (12 epoch) cost me about 55 hours on one Tesla A100
from detrex.
man i just wanna know how long you train your model on "dataloader.train.total_batch_size = 4 and train.max_iter = 360000" ? appreciate!!
Training DN-Deformable-DETR-R50 (12 epoch) cost me about 55 hours on one Tesla A100
i use one v100 32g,same settings as you,detrex shows more than 4 days🤣
Anyway, thks for your reply!!
from detrex.
Related Issues (20)
- Single Class detection HOT 4
- Question: How come the MaskDINO Encoder can't use half-precision (AMP) training? HOT 1
- Errror when run in rtx 2080ti error in ms_deformable_im2col_cuda HOT 1
- Could you add the Co-DETR model in the future? HOT 4
- customize HOT 2
- GroupDETR performance reproduction HOT 1
- [Solved] help with detrex build needed HOT 8
- A simple inference script HOT 1
- LVIS Pretrained Models HOT 2
- parameters count HOT 1
- How to train unregular box? HOT 5
- Why is maskDINO's bunding box the smallest outer rectangle of multiple objects?
- Why is H-deformable-detr's mAP(49.1) higher than official implementation(48.7)? HOT 1
- CUDA runs out of memory HOT 4
- Wandb init HOT 2
- Very noisy loss of Dino HOT 4
- About finetuning a DINO model you provided on my custom dataset HOT 2
- Cannot import 'detrex._C', therefore 'MultiScaleDeformableAttention' is not available. detrex is not compiled successfully, please build following the instructions! HOT 1
- [Bug] FocusDetr report min size error HOT 1
- LexerNoViableAltException: dates.from_date=2023-09-16 HOT 1
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 detrex.