Comments (6)
I met the problem too, but I found that I did something wrong about my dataset. I believe you can check your data (especially label) first.
from dn-detr.
I met the problem too, but I found that I did something wrong about my dataset. I believe you can check your data (especially label) first.
I can use my data set normally in other methods, but only this method will have errors, which places have you modified when using your own data set?
from dn-detr.
You can transform your dataset to COCO format or write a new dataset class for your dataset.
from dn-detr.
You can transform your dataset to COCO format or write a new dataset class for your dataset.
Hi, I have recently tried to train other datasets (cityscapes) using for dn_dab_detr. The size of the training set is only 3000, we train the model on 4 Nvidia 3090 GPUs, batch size is 16 (4 images each GPU x 4 GPUs) , accordingly I adjusted the learning rate to 2e-4 (twice of the original), however, when training, I found that the model did not converge, so I changed back to 1e-4, the batch size is still 4, however, after 50 epochs, the result is not as good as baseline (Faster-RCNN), do I still need to try to modify other hyperparameters? Which hyperparameters will be modified to enable the model to work in the new dataset?
from dn-detr.
Hey, as our code and dataloader largely follows DETR and Deformable DETR. They have been widely adopted in many custom dataset. you can refer to their issues about how to train your own dataset. For example, in DETR github page, there are many issues about training on the custom dataset, like this.
For modifications to the code for your own dataset, there are also some suggestions, like this and this.
Hope these suggestions work for you.
from dn-detr.
Hey, as our code and dataloader largely follows DETR and Deformable DETR. They have been widely adopted in many custom dataset. you can refer to their issues about how to train your own dataset. For example, in DETR github page, there are many issues about training on the custom dataset, like this.
For modifications to the code for your own dataset, there are also some suggestions, like this and this.
Hope these suggestions work for you.
Thanks for the detailed reply which helped me a lot.
from dn-detr.
Related Issues (20)
- 关于“inference.py” HOT 2
- The normalization of sine positional embedding
- how to add DN to Anchor DETR with 2D Anchors HOT 1
- about the train log HOT 1
- Inverse sigmoid HOT 1
- note: This error originates from a subprocess, and is likely not a problem with pip. HOT 1
- Target detection application direction HOT 1
- How to visualize the coco dataset HOT 1
- error : python inference.py HOT 2
- how to add DN to vanillar DETR? HOT 3
- Add DN training into the original DETR HOT 2
- Concerns about the Rapid Decrease of Loss in Denoising Part during Training
- about attention.py HOT 1
- 初始化 HOT 2
- DN_DAB 12 epoch result HOT 1
- RuntimeError: Sizes of tensors must match except in dimension 0. Got 0 and 300 (The offending index is 0) HOT 4
- About Training Your Own Dataset HOT 1
- About DN-DETR-R50-DC5
- About the increasing memory of GPU
- TypeError: unsupported operand type(s) for *: 'int' and 'NoneType'
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 dn-detr.