Comments (5)
Hi, thanks for your interest in our work ! I've included some models trained with only two 224x224 crops during 400 epochs. See commit: 2d898a4
from swav.
Hi, thanks for your reply. Can I know the performance during 200 epochs? Thank you for your excellent work and code release.
from swav.
I'm sorry, I have not run it for 200 epochs.
If this is really critical for you, I can try to find the bandwidth to run it. Let me know
from swav.
Hi, due to the limited computing resources of the academic groups, it will be easier for us to reproduce your results with less time cost. I will appreciate it if you could provide the performance of 200 epochs. Thanks a lot.
from swav.
Hi, @mathildecaron31 did you happen to have the time and resources to run 200 epochs with batch size 256 and without multi-crop? I am asking because this seems a standard configuration in the literature but it is missing both in the paper and the repo. I think this would help a lot of less lucky researchers (in terms of resource availability).
from swav.
Related Issues (20)
- Degraded DCv2 Training Loss
- [Discussion] Can I use DeepClusterV2 for the sole purpose of learning to cluster unlabelled dataset? HOT 1
- Is it possible to use a pretrained ResNet50 for SWAV for custom dataset? HOT 2
- A question about dataloader setting : `shufflu`? HOT 2
- How can I load DeepCluster-v2?
- instability with prediction while using resnet 50 pretrained model HOT 1
- About the format of dataset
- image segmentation
- question of loading pre-trained model in eval_linear.py and eval_semisup.py
- how to prepare the training data? HOT 1
- urllib.error.HTTPError: HTTP Error 403: Forbidden
- How to get the correct answer
- About SwAV_ver2
- ImageNet pretraining size
- About Loss function. HOT 1
- A question about batch_size and nmb prototypes HOT 1
- Slow Training with Swav on 2 GPUs using torch.distributed HOT 1
- About the loss HOT 1
- Missing "resnet50w5" linear config in eval_linear.py
- train models with multicrops
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 swav.