# EMP-SSL-Eval

**Repository Path**: askuasen/emp-ssl-eval

## Basic Information

- **Project Name**: EMP-SSL-Eval
- **Description**: A evaluation in oil images, based on the work "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch".
- **Primary Language**: Python
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-03-31
- **Last Updated**: 2025-03-31

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# EMP-SSL Eval
A self-supervised learning framework in oil images classfication based on the work "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch"(paper Authors: Shengbang Tong*, Yubei Chen*, Yi Ma, Yann LeCun)
[![arXiv](https://img.shields.io/badge/arXiv-2304.03977-b31b1b.svg)](https://arxiv.org/abs/2304.03977)


![Training Pipeline](pipeline.png)


Repo Authors: Binsen XU

## Introduction
This repository contains the implementation for the paper "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch." The paper introduces a simplistic but efficient self-supervised learning method called Extreme-Multi-Patch Self-Supervised-Learning (EMP-SSL). EMP-SSL significantly reduces the training epochs required for convergence by increasing the number of fix size image patches from each image instance.

## Preparing Training Data
Oilimage dataset is like cifar 10. Details can be found in this [link](https://pan.quark.cn/s/dffdb9d5cfd4).this passwor is WDBq.

## Getting Started
Current code implementation supports Cifar10, Cifar100 and ImageNet100， Oilimages.

To get started with the EMP-SSL implementation, follow these instructions:

### 1. Clone this repository
```bash
git clone https://gitee.com/askuasen/emp-ssl-eval
cd emp-ssl-eval
``` 
### 2. Install required packages
```
pip install -r requirements.txt
```
### 3. Training

#### Reproducing 1-epoch results


```
python main.py --data cifar10 --epoch 2 --patch_sim 200 --arch 'resnet18-cifar' --num_patches 20 --lr 0.3
```
For ImageNet100  
Please follow the instruction in [this](https://github.com/zhirongw/lemniscate.pytorch) to download the ImageNet dataset. For small datasets like SVHN, you can either download them manually or set the **download** parameter in torchvision.dataset **True** to download them automatically.

After downloading them, please put them in data/, an SSD is highly recommended for training on ImageNet.  

```
python main.py --data imagenet100 --epoch 2 --patch_sim 200 --arch 'resnet18-imagenet' --num_patches 20 --lr 0.3
```
For SmallOil
```
python main.py --data smalloil --epoch 2 --patch_sim 200 --arch 'conv-encoder' --num_patches 20 --lr 0.3
```

#### Reproducing multi epochs results


Change num_patches here to change the number of patches used in EMP-SSL training.
```
python main.py --data cifar10 --epoch 30 --patch_sim 200 --arch 'resnet18-cifar' --num_patches 20 --lr 0.3
```



### 4. Evaluating
Because our model is trained with only fixed size image patches. To evaluate the performance, we adopt bag-of-features model from intra-instance VICReg paper. Change test_patches here to adjust number of patches used in bag-of-feature model for different GPUs.
```
python evaluate.py --model_path 'path to your evaluated model' --test_patches 128
```
```
python evaluate.py --test_patches 128 --data smalloil --arch conv-encoder --knn --model_path logs/EMP-SSL-Training/patchsim200_numpatch20_bs100_lr0.3_NONE/save_models/1.pt
```
## Acknowledgment
This repo is inspired by [MCR2](https://github.com/Ma-Lab-Berkeley/MCR2), [solo-learn](https://github.com/vturrisi/solo-learn) and [NMCE](https://github.com/zengyi-li/NMCE-release) repo.

## Citation
If you find this repository useful, please consider giving a star :star: and citation:

```
@article{tong2023empssl,
title={EMP-SSL: Towards Self-Supervised Learning in One Training Epoch},
author={Shengbang Tong and Yubei Chen and Yi Ma and Yann Lecun},
journal={arXiv preprint arXiv:2304.03977},
year={2023}
}
```
# E-mail
xbs150@163.com