BYOL¶
摘要¶
Bootstrap Your Own Latent (BYOL) is a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from each other. From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view. At the same time, we update the target network with a slow-moving average of the online network.
使用方式¶
from mmpretrain import inference_model
predict = inference_model('resnet50_byol-pre_8xb512-linear-coslr-90e_in1k', 'demo/bird.JPEG')
print(predict['pred_class'])
print(predict['pred_score'])
import torch
from mmpretrain import get_model
model = get_model('byol_resnet50_16xb256-coslr-200e_in1k', pretrained=True)
inputs = torch.rand(1, 3, 224, 224)
out = model(inputs)
print(type(out))
# To extract features.
feats = model.extract_feat(inputs)
print(type(feats))
Prepare your dataset according to the docs.
训练：
python tools/train.py configs/byol/byol_resnet50_16xb256-coslr-200e_in1k.py
测试：
python tools/test.py configs/byol/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-7596c6f5.pth
Models and results¶
Pretrained models¶
模型 |
Params (M) |
Flops (G) |
配置文件 |
下载 |
|---|---|---|---|---|
|
68.02 |
4.11 |
Image Classification on ImageNet-1k¶
模型 |
预训练 |
Params (M) |
Flops (G) |
Top-1 (%) |
配置文件 |
下载 |
|---|---|---|---|---|---|---|
|
25.56 |
4.11 |
71.80 |
引用¶
@inproceedings{grill2020bootstrap,
title={Bootstrap your own latent: A new approach to self-supervised learning},
author={Grill, Jean-Bastien and Strub, Florian and Altch{\'e}, Florent and Tallec, Corentin and Richemond, Pierre H and Buchatskaya, Elena and Doersch, Carl and Pires, Bernardo Avila and Guo, Zhaohan Daniel and Azar, Mohammad Gheshlaghi and others},
booktitle={NeurIPS},
year={2020}
}