Comments (5)
Hi @lxy5513 ,
We've updated and tested support for transfer learning. The dataset folder structure should be the same as ImageNet structure https://github.com/zihangJiang/TokenLabeling#requirements (with train
and val
split). You can clone the main branch, try to specify --num-classes
flag, and add --token-label --dense-weight 0
for fine-tuning.
Let me know if you have any further questions.
from tokenlabeling.
Hi,
Can you post your training script? The label smoothing is handled in Mixup & Cutmix here
Lines 484 to 488 in 9f71792
and here
Lines 678 to 690 in 9f71792
If you train without token labeling, We suggest you add --mixup 0.8
or --cutmix 1.0
as regularization, and use lvvit model. Model like lvvit_s returns all tokens by default which will cause error if you train without token labeling.
If you train with token labeling, please add --token-label
flag.
from tokenlabeling.
@zihangJiang Thanks for your response.
My training script is here:
python main.py /home/liuxingyu/data/patrol/comfort_classification/nursery_v16 --model lvvit_m -b 64 --apex-amp --img-size 384 --drop-path 0.2 --token-label-size 24 --model-ema --finetune lvvit_m-56M-384-85.4.pth.tar --token-label-data ''
I train without token labeling, because I have not generate token labels for my custome dataset.
Model like lvvit_s returns all tokens by default which will cause error if you train without token labeling
Is this mean if I want to train without token labeling, I can't use pretrain model ?
from tokenlabeling.
We haven't tested on other datasets yet, but you can of course use the pre-trained model. I think you can add --token-label --dense-weight 0
flag. This can work without token label data.
However, some other bugs may occur. You can wait for our further update supporting transfer learning.
from tokenlabeling.
Well, thanks, expect for further update.
from tokenlabeling.
Related Issues (20)
- not use distributed_train.sh
- The model parameters couldn't be downloaded. HOT 4
- A Bag of Training Techniques for ViT HOT 1
- Python3.6, ok; Python3.8, error HOT 1
- RuntimeError: CUDA error: device-side assert triggered HOT 4
- The accuracy of the validation set is 0,and the loss is always around 13 HOT 7
- label_map does not do the same augmentation (random crop) as the input image HOT 1
- How to print the output of the wrong prediction of validation dataset? HOT 10
- Can Token labeling reach higher than annotator model? HOT 1
- Could you please provide the training log ? HOT 5
- generate_label.py unable to find model lvvit_s HOT 2
- Pretrained weights for LV-ViT-T HOT 5
- Generating label for custom dataset HOT 2
- 关于TokenLabel的疑问 HOT 2
- BatchSize Specified HOT 2
- [ LV-ViT-S pretrained model ] HOT 1
- Model settings for Cifar10
- how to apply token labeling to CNN ?
- Dimension inconsistency of the token labels
- target_cls 部分代码有问题??
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 tokenlabeling.