A general, feasible, and extensible framework for classification tasks.

Overview

Pytorch Classification

  • A general, feasible and extensible framework for 2D image classification.

Features

  • Easy to configure (model, hyperparameters)
  • Training progress monitoring and visualization
  • Weighted sampling / weighted loss / kappa loss / focal loss for imbalance dataset
  • Kappa metric for evaluating model on imbalance dataset
  • Different learning rate schedulers and warmup support
  • Data augmentation
  • Multiple GPUs support

Installation

Recommended environment:

  • python 3.8+
  • pytorch 1.7.1+
  • torchvision 0.8.2+
  • tqdm
  • munch
  • packaging
  • tensorboard

To install the dependencies, run:

$ git clone https://github.com/YijinHuang/pytorch-classification.git
$ cd pytorch-classification
$ pip install -r requirements.txt

How to use

1. Use one of the following two methods to build your dataset:

  • Folder-form dataset:

Organize your images as follows:

├── your_data_dir
    ├── train
        ├── class1
            ├── image1.jpg
            ├── image2.jpg
            ├── ...
        ├── class2
            ├── image3.jpg
            ├── image4.jpg
            ├── ...
        ├── class3
        ├── ...
    ├── val
    ├── test

Here, val and test directory have the same structure of train. Then replace the value of 'data_path' in BASIC_CONFIG in configs/default.yaml with path to your_data_dir and keep 'data_index' as null.

  • Dict-form dataset:

Define a dict as follows:

your_data_dict = {
    'train': [
        ('path/to/image1', 0), # use int. to represent the class of images (start from 0)
        ('path/to/image2', 0),
        ('path/to/image3', 1),
        ('path/to/image4', 2),
        ...
    ],
    'test': [
        ('path/to/image5', 0),
        ...
    ],
    'val': [
        ('path/to/image6', 0),
        ...
    ]
}

Then use pickle to save it:

import pickle
pickle.dump(your_data_dict, open('path/to/pickle/file', 'wb'))

Finally, replace the value of 'data_index' in BASIC_CONFIG in configs/default.yaml with 'path/to/pickle/file' and set 'data_path' as null.

2. Update your training configurations and hyperparameters in configs/default.yaml.

3. Run to train:

$ CUDA_VISIBLE_DEVICES=x python main.py

Optional arguments:

-c yaml_file      Specify the config file (default: configs/default.yaml)
-o                Overwrite save_path and log_path without warning
-p                Print configs before training

4. Monitor your training progress in website 127.0.0.1:6006 by running:

$ tensorborad --logdir=/path/to/your/log --port=6006

Tips to use tensorboard on a remote server

Owner
Eugene
Eugene
CIFAR-10_train-test - training and testing codes for dataset CIFAR-10

CIFAR-10_train-test - training and testing codes for dataset CIFAR-10

Frederick Wang 3 Apr 26, 2022
Use AI to generate a optimized stock portfolio

Use AI, Modern Portfolio Theory, and Monte Carlo simulation's to generate a optimized stock portfolio that minimizes risk while maximizing returns. Ho

Greg James 30 Dec 22, 2022
General purpose GPU compute framework for cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends)

General purpose GPU compute framework for cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for advanced GPU data processing usec

The Kompute Project 1k Jan 06, 2023
BuildingNet: Learning to Label 3D Buildings

BuildingNet This is the implementation of the BuildingNet architecture described in this paper: Paper: BuildingNet: Learning to Label 3D Buildings Arx

16 Nov 07, 2022
Homepage of paper: Paint Transformer: Feed Forward Neural Painting with Stroke Prediction, ICCV 2021.

Paint Transformer: Feed Forward Neural Painting with Stroke Prediction [Paper] [PaddlePaddle Implementation] Homepage of paper: Paint Transformer: Fee

442 Dec 16, 2022
Rank 3 : Source code for OPPO 6G Data Generation Challenge

OPPO 6G Data Generation with an E2E Framework Homepage of OPPO 6G Data Generation Challenge Datasets H1_32T4R.mat H2_32T4R.mat Please put the original

Sen Pei 97 Jan 07, 2023
A collection of IPython notebooks covering various topics.

ipython-notebooks This repo contains various IPython notebooks I've created to experiment with libraries and work through exercises, and explore subje

John Wittenauer 2.6k Jan 01, 2023
CSKG is a commonsense knowledge graph that combines seven popular sources into a consolidated representation

CSKG: The CommonSense Knowledge Graph CSKG is a commonsense knowledge graph that combines seven popular sources into a consolidated representation: AT

USC ISI I2 85 Dec 12, 2022
Scalable Multi-Agent Reinforcement Learning

Scalable Multi-Agent Reinforcement Learning 1. Featured algorithms: Value Function Factorization with Variable Agent Sub-Teams (VAST) [1] 2. Implement

3 Aug 02, 2022
CURL: Contrastive Unsupervised Representations for Reinforcement Learning

CURL Rainbow Status: Archive (code is provided as-is, no updates expected) This is an implementation of CURL: Contrastive Unsupervised Representations

Aravind Srinivas 46 Dec 12, 2022
Adversarial Self-Defense for Cycle-Consistent GANs

Adversarial Self-Defense for Cycle-Consistent GANs This is the official implementation of the CycleGAN robust to self-adversarial attacks used in pape

Dina Bashkirova 10 Oct 10, 2022
Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks (MAPDN)

Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks (MAPDN) This is the implementation of the paper Multi-Age

Future Power Networks 83 Jan 06, 2023
Remote sensing change detection tool based on PaddlePaddle

PdRSCD PdRSCD(PaddlePaddle Remote Sensing Change Detection)是一个基于飞桨PaddlePaddle的遥感变化检测的项目,pypi包名为ppcd。目前0.2版本,最新支持图像列表输入的训练和预测,如多期影像、多源影像甚至多期多源影像。可以快速完

38 Aug 31, 2022
Defending against Model Stealing via Verifying Embedded External Features

Defending against Model Stealing Attacks via Verifying Embedded External Features This is the official implementation of our paper Defending against M

20 Dec 30, 2022
Neural network for digit classification powered by cuda

cuda_nn_mnist Neural network library for digit classification powered by cuda Resources The library was built to work with MNIST dataset. python-mnist

Nikita Ardashev 1 Dec 20, 2021
Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search

CLIP-GLaSS Repository for the paper Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search An in-browser demo is

Federico Galatolo 172 Dec 22, 2022
Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity

[ICLR 2022] Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity by Shiwei Liu, Tianlong Chen, Zahra Atashgahi, Xiaohan Chen, Ghada Sokar, Elen

VITA 18 Dec 31, 2022
Predict halo masses from simulations via graph neural networks

HaloGraphNet Predict halo masses from simulations via Graph Neural Networks. Given a dark matter halo and its galaxies, creates a graph with informati

Pablo Villanueva Domingo 20 Nov 15, 2022
code associated with ACL 2021 DExperts paper

DExperts Hi! This repository contains code for the paper DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts to appear at

Alisa Liu 68 Dec 15, 2022