Comments (4)
Thanks, following your advice, I tried tunning LR a little lesser (1e-3) and use different Optimizer (AdamW instead of SGD like before) and the result is a lot better now :D Still wait to see the fully trained model performance and I will give some feedback later
Anyway, thanks for this model. Very cool architecture :D
from edgenext.
Hi, currently I'm using an exact implementation of edgenext_small, resolution of my input is (3, 112, 112), training on a set of 4 million images and starting with learning rate of 6e-3. It's still reducing the loss and accuracy still getting higher but I just feel it's slow, compare to some other pure CNN networks :D
Thank you for providing the details,
We do notice in our detection experiments that EdgeNeXt is sensitive to LR and usually works well at slightly lesser LR as compared to pure ViTs. If you can afford, try tuning the LR for your training, let's say trying out some randomly sampled values around the current LR value. I hope this would be helpful.
Please let me know if you have any questions or get any useful insights out of your experiments. Thanks
from edgenext.
Hi @leduy99,
Thank You for your interest in EdgeNeXt. Could you provide some more information about your experiment, such as dataset and detection network? At what input resolution you are training your detector? Also please make sure that the backbone weights for EdgeNeXt are loaded correctly.
Thanks
from edgenext.
Hi, currently I'm using an exact implementation of edgenext_small, resolution of my input is (3, 112, 112), training on a set of 4 million images and starting with learning rate of 6e-3.
It's still reducing the loss and accuracy still getting higher but I just feel it's slow, compare to some other pure CNN networks :D
from edgenext.
Related Issues (19)
- Can I learn with Gray Scale Image or other size Images? HOT 6
- Suggested network configs for student model for knowledge distillation HOT 5
- Is there any way to finetune EdgeNeXt_xx_small? HOT 2
- classification HOT 1
- Code for Det/Seg HOT 1
- Convert model to libtorch. HOT 1
- Edgenext checkpoints on 224X224 resolution. HOT 4
- Faster Inference INT8 HOT 3
- About ablation HOT 2
- edgenext_small is faster than edgenext_x_small ? HOT 1
- about channels HOT 2
- Hi, great work, but how can I use it as the backbone of my object detection network? thanks for answer HOT 1
- What the year of datasets of ImageNet-1K to use? HOT 2
- EdgeNeXt for semantic segmentation HOT 5
- Jetson model for benchmarking HOT 3
- ValueError: max() arg is an empty sequence HOT 5
- Reproduced 79.1 for edgenext_small, a random error? HOT 1
- other task---edgenext HOT 2
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 edgenext.