Comments (12)
Sorry, I did not realize you have metioned "the up sampling or change weight" is about pneumonia binary classification problem. what I was asking is all about 14 classes classification problem
from chexnet.
I ran your trained model on the testset, but it seems that something has been done to adjust the mean probability of each disease. Such values will not be obtained by the original training strategy (If my experiment is correct).
from chexnet.
what method do you use to address the class unbalanced?
from chexnet.
I do not think the v2 changed the weights, the paper says
, and v1 says "We also augment the training
data with random horizontal flipping."
from chexnet.
If without data augment, how to address data positive & negtive uneven problem? I think the original paper use data augment...
from chexnet.
Hello, so which way do you use? upsampling or changing sample weights?
from chexnet.
Thank you @arnoweng for sharing the code. I have implemented the training procedure, and strangely enough, was able to obtain better AUROC score (0.8508). Following imagenet example I used random crops and flips during training stage, learning rate was set to 0.0001.
from chexnet.
I've tried several data augmentation methods that work well in other domains, but they do not work in this task somehow. The training code is adopted from PyTorch examples and you can easily find them in offical page.
from chexnet.
The problem can be addressed by oversampling positive classes or changing sample weights which are elaborated in original paper v1 and v2 respectively.
from chexnet.
When training the model, did you freeze the model parameters except for the modified parts? Or, just train all parameters? @arnoweng
from chexnet.
@chaoyan1073 I have tried both. This released model was trained without freezing parameters.
from chexnet.
@arnoweng Thanks for your kind reply! I have tried both, too. However, In my case, freezing partial parameters will produce better AUC score 0.810. But it is still not as good as your 0.847. But I did not adopt any sampling strategies at present. I will try some sampling skills and see if them helps.
from chexnet.
Related Issues (20)
- what torchvision version? HOT 1
- Tencrop on test images & preprocessing imbalanced data HOT 2
- Broken Pipeline error HOT 1
- model.load_state_dict(checkpoint['state_dict']) error with pytorch 0.4.0 HOT 10
- RuntimeError: CUDA Error: out of memory HOT 11
- where can i get the pretrained model?
- Unable to run the model on CPU
- Where can i configure GPU details? HOT 5
- cannot be unzipped HOT 1
- FPGA Development
- Low AUROC HOT 6
- can you share pre trained model
- I have an error with the first line of the code. the error is about 'tuple' object is not callable HOT 1
- How to Cite?
- Code to make Class Activation Maps?
- Replication having probelm.
- torch._C._cuda_init() RuntimeError: The NVIDIA driver on your system is too old (found version 10020)
- isn't the training labels should be 15 (14 disease labels+ No Findings) instead of 14?
- How long will it take for training?
- 协议声明
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 chexnet.