Comments (2)
The unlabeled and labeled byol loss seem to get no lower after several epochs...
from propos.
I do not know what's wrong with you.
Here are the config and logs for BYOL on STL10 with image size 96.
{
"seed": {
"desc": null,
"value": 2
},
"_wandb": {
"desc": null,
"value": {
"framework": "torch",
"cli_version": "0.10.8",
"is_jupyter_run": true,
"python_version": "3.7.10",
"is_kaggle_kernel": false
}
},
"epochs": {
"desc": null,
"value": 1000
},
"dataset": {
"desc": null,
"value": "stl10"
},
"feat_dim": {
"desc": null,
"value": 256
},
"img_size": {
"desc": null,
"value": 96
},
"momentum": {
"desc": null,
"value": 0.9
},
"reassign": {
"desc": null,
"value": 10
},
"run_name": {
"desc": null,
"value": "stl10_org_byol_resnet34_3"
},
"use_copy": {
"desc": null,
"value": 1
},
"save_freq": {
"desc": null,
"value": 50
},
"symmetric": {
"desc": null,
"value": 1
},
"batch_size": {
"desc": null,
"value": 64
},
"latent_std": {
"desc": null,
"value": 0
},
"local_rank": {
"desc": null,
"value": 0
},
"model_name": {
"desc": null,
"value": "offline_contrast"
},
"print_freq": {
"desc": null,
"value": 10
},
"data_folder": {
"desc": null,
"value": "/apdcephfs/private_freyaxiong/ft_local/STL10"
},
"hidden_size": {
"desc": null,
"value": 4096
},
"num_workers": {
"desc": null,
"value": 32
},
"temperature": {
"desc": null,
"value": 0.5
},
"encoder_name": {
"desc": null,
"value": "resnet34"
},
"resume_epoch": {
"desc": null,
"value": 0
},
"shuffling_bn": {
"desc": null,
"value": 1
},
"weight_decay": {
"desc": null,
"value": 0.0005
},
"byol_momentum": {
"desc": null,
"value": 0.996
},
"data_resample": {
"desc": null,
"value": 0
},
"learning_rate": {
"desc": null,
"value": 0.05
},
"warmup_epochs": {
"desc": null,
"value": 50
},
"whole_dataset": {
"desc": null,
"value": 1
},
"fix_predictor_lr": {
"desc": null,
"value": 0
},
"use_gaussian_blur": {
"desc": null,
"value": 0
},
"cluster_loss_weight": {
"desc": null,
"value": 0
},
"lambda_predictor_lr": {
"desc": null,
"value": 10
}
}
The accuracy is ~83%, reaching the highest at ~800th epoch.
from propos.
Related Issues (18)
- About spherical k-means implementation HOT 2
- About Performance on Imagenetdogs HOT 4
- Got 65% ACC for BYOL on ImageNetdogs HOT 2
- About cifar10 performance on SimSiam HOT 5
- How to change parameters when num_device =2 HOT 1
- How to train ProPos on the STL-10 dataset?
- what does the memory data loader do in the basic_template.py? HOT 1
- Could you provide the pre-trained models for ProPos on ImageNet-1k, ImageNet-50/100/200 HOT 17
- Could you provide the config file for training Tiny-ImageNet?
- How to obtain the clustering result after training? HOT 3
- how to reproduce pcl HOT 2
- Can't Reproduce Result in CIFAR-20 HOT 14
- How to generate pseudo label for unlabeled data in STL-10 and use them in PSL term? HOT 1
- I can't get the results in the paper using the pretrained models you provided HOT 7
- How to train Propos on STL-10 dataset HOT 1
- Results on CIFAR10 with ResNet34 HOT 1
- Training speed of ImageNet-10 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 propos.