Comments (7)
@razvypp
have you done it sucessfully ?
if yes, how to do?
from birefnet.
Hi, could you check your texts and correct their formats?
from birefnet.
About the comparison with u-2-net, I don't think that is a problem. It's almost impossible to bring much improvement on accuracy with same number of parameters.
Statistics about BiRefNet with different backbones can be referred to this issue.
You can also find some other issues where we talked about increasing the speed of inference (ONNX, FP16, ...). By now, there haven't been very good methods for it. You can wait for the version with swin_v1_tiny, which could be 4 times faster than the official one.
from birefnet.
Will the v1_tiny have the same performance on general datasets?
I failed to convert to onnx i get crash, is there a guide for this?
from birefnet.
Of course not, that's a trade-off.
Sorry, as for the issues I mentioned above, I currently have no time for this kind of thing.
from birefnet.
The well-trained BiRefNet with the swin_v1_tiny
backbone has been uploaded to my Google Drive. Check the stuff
in README for access to the weights, performance, predicted maps, and training log in the corresponding folder (exp-xxx). The performance is a bit lower than the official version, but still good (HCE↓: 1152 -> 1182 on DIS-VD). Feel free to download and use them.
from birefnet.
By the way, check the update in inference.py
. Set the torch.set_float32_matmul_precision
to 'high' can increase the FPS on A100 from 5 to 12 with ~0 performance downgrade (Because I set it to 'high' during training).
from birefnet.
Related Issues (20)
- CoreML model HOT 5
- Question: training time for different models HOT 6
- Model name correspondence HOT 6
- Custom dataset fine-tuning HOT 4
- Feature: Onnx Export HOT 8
- Model weights when trained on HQ-Seg44k dataset HOT 1
- training datset set HOT 2
- Releated to finetunning HOT 5
- KeyError: 'HOME' HOT 1
- I made local Windows, cloud RunPod, Massed Compute and free Kaggle and more advanced Gradio APP with batch inference and transparent background HOT 2
- Model Zoo - general use is matting or segment? HOT 4
- inquiry about the convneck in ViTMatte HOT 3
- So many models HOT 11
- Onnx accuracy HOT 6
- dont work on folder , dont work on image sets and if i download it is original image -> i mus t push my right mousebuttun to save it HOT 8
- 各数据集上分别使用的最佳backbone HOT 1
- Adapting Model Training for Custom Image Dimensions (200x200): Seeking Guidance and Solutions HOT 2
- Heavy and Portrait models HOT 5
- Availability of FAL's versions of the model (heavy/light/portrait) HOT 1
- 使用optimum-cli导出为ONNX报错 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 birefnet.