Comments (2)
Hello @gomezzz .
Yes, you are right.
The code actually aim to process CIFAR datasets or other (32x32) size of images.
If you use another dataset, you can adjust the parts of augmentations.
Thank you.
from fixmatch-pytorch.
For example,
I am working on ImageNet dataset (it's not released in public, but i plan to do),
the randomcrop size is 224.
I also re-implement another BasicDataset class according to the target dataset.
from fixmatch-pytorch.
Related Issues (20)
- Training time HOT 2
- Questions about the EMA process for BN statics HOT 1
- Impossible to avoid including labelled data in unlabelled data HOT 3
- resuming checkpoints seems broken HOT 13
- argparse issues HOT 2
- how to cite your repo? HOT 1
- Unsupervised loss HOT 1
- About the version of python HOT 1
- No Validation Set HOT 1
- mask and mean HOT 1
- How can i using [sup + consistency or sup only] HOT 4
- NCCL error when train with single node & multi gpus HOT 3
- when [--num_labels 4000], then using 4000 labeled data and [50000 unlabeled data or 46000 unlabeled data] ?
- Error using single gpu for training HOT 5
- Confusion of Unlabeled batch size & eval steps
- Training time HOT 2
- I've never seem code that's so neat in the field of ML. HOT 1
- What are the important factors to improve performance? HOT 3
- Training time HOT 7
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 fixmatch-pytorch.