Simple-Image-Classification - Simple Image Classification Code (PyTorch)

Overview

Simple-Image-Classification

Simple Image Classification Code (PyTorch)

Yechan Kim

This repository contains:

  • Python3 / Pytorch code for multi-class image classification

Prerequisites

  • See requirements.txt for details.
torch
torchvision
matplotlib
scikit-learn
tqdm            # not mandatory but recommended
tensorboard     # not mandatory but recommended

How to use

  1. The directory structure of your dataset should be as follows. (You can use our toy-examples: unzip cifar10_dummy.zip.)
|โ€”โ€” ๐Ÿ“ your_own_dataset
	|โ€”โ€” ๐Ÿ“ train
		|โ€”โ€” ๐Ÿ“ class_1
			|โ€”โ€” ๐Ÿ–ผ๏ธ 1.jpg
			|โ€”โ€” ...
		|โ€”โ€” ๐Ÿ“ class_2 
			|โ€”โ€” ๐Ÿ–ผ๏ธ ...
	|โ€”โ€” ๐Ÿ“ valid
		|โ€”โ€” ๐Ÿ“ class_1
		|โ€”โ€” ๐Ÿ“ ... 
	|โ€”โ€” ๐Ÿ“ test
		|โ€”โ€” ๐Ÿ“ class_1
		|โ€”โ€” ๐Ÿ“ ... 
  1. Check __init__.py. You might need to modify variables and add somethings (transformation, optimizer, lr_schduler ...). ๐Ÿ’ Tip You can add your own loss function as follows:
...
def get_loss_function(loss_function_name, device):
    ... 
    elif loss_function_name == 'your_own_function_name':  # add +
        return your_own_function()
    ...
...
  1. Run train.py for training. The below is an example. See src/my_utils/parser.py for details. ๐Ÿ’ Tip --loss_function='CE' means that you choose softmax-cross-entropy (default) for your loss.
python train.py --network_name='resnet34_for_tiny' --dataset_dir='./cifar10_dummy' \
--batch_size=256 --epochs=5  \
--lr=0.1 --lr_step='[60, 120, 160]' --lr_step_gamma=0.5 --lr_warmup_epochs=5 \
--auto_mean_std --store_weights --store_loss_acc_log --store_logits --store_confusion_matrix \
--loss_function='your_own_function_name' --transform_list_name='CIFAR' --tag='train-001'
  1. Run test.py for test. The below is an example. See src/my_utils/parser.py for details.
python test.py --network_name='resnet34_for_tiny' --dataset_dir='./cifar10_dummy' \
--auto_mean_std --store_logits --store_confusion_matrix \
--checkpoint='pretrained_model_weights.pt'

Trailer

  1. If you install tqdm, you can check the progress of training. readme1

  2. If you install tensorboard, you can check the acc/loss changes and confusion matrices during training. readme1

Contribution

๐Ÿ› If you find any bugs or have opinions for further improvements, feel free to contact me ([email protected]). All contributions are welcome.

Reference

  1. https://github.com/weiaicunzai/pytorch-cifar100
  2. https://medium.com/@djin31/how-to-plot-wholesome-confusion-matrix-40134fd402a8 (Confusion Matrix)
  3. https://pytorch.org/ignite/generated/ignite.handlers.param_scheduler.create_lr_scheduler_with_warmup.html
Owner
Yechan Kim
GIST, Machine Learning and Vision Lab.
Yechan Kim
Deeplab-resnet-101 in Pytorch with Jaccard loss

Deeplab-resnet-101 Pytorch with Lovรกsz hinge loss Train deeplab-resnet-101 with binary Jaccard loss surrogate, the Lovรกsz hinge, as described in http:

Maxim Berman 95 Apr 15, 2022
DSAC* for Visual Camera Re-Localization (RGB or RGB-D)

DSAC* for Visual Camera Re-Localization (RGB or RGB-D) Introduction Installation Data Structure Supported Datasets 7Scenes 12Scenes Cambridge Landmark

Visual Learning Lab 143 Dec 22, 2022
DTCN IJCAI - Sequential prediction learning framework and algorithm

DTCN This is the implementation of our paper "Sequential Prediction of Social Me

Bobby 2 Jan 24, 2022
IJON is an annotation mechanism that analysts can use to guide fuzzers such as AFL.

IJON SPACE EXPLORER IJON is an annotation mechanism that analysts can use to guide fuzzers such as AFL. Using only a small (usually one line) annotati

Chair for Sysยญtems Seยญcuยญriยญty 146 Dec 16, 2022
ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation

ST++ This is the official PyTorch implementation of our paper: ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation. Lihe Ya

Lihe Yang 147 Jan 03, 2023
This project is a loose implementation of paper "Algorithmic Financial Trading with Deep Convolutional Neural Networks: Time Series to Image Conversion Approach"

Stock Market Buy/Sell/Hold prediction Using convolutional Neural Network This repo is an attempt to implement the research paper titled "Algorithmic F

Asutosh Nayak 136 Dec 28, 2022
Projecting interval uncertainty through the discrete Fourier transform

Projecting interval uncertainty through the discrete Fourier transform This repo

1 Mar 02, 2022
A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

Use this instead: https://github.com/facebookresearch/maskrcnn-benchmark A Pytorch Implementation of Detectron Example output of e2e_mask_rcnn-R-101-F

Roy 2.8k Dec 29, 2022
Art Project "Schrรถdinger's Game of Life"

Repo of the project "Team Creative Quantum AI: Schrรถdinger's Game of Life" Installation new conda env: conda create --name qcml python=3.8 conda activ

โ„โ—ฎโ„•โ„•โ—ญโ„ โ„โˆˆแ›”โˆˆโ„ 2 Sep 15, 2022
A repo with study material, exercises, examples, etc for Devnet SPAUTO

MPLS in the SDN Era -- DevNet SPAUTO Get right to the study material: Checkout the Wiki! A lab topology based on MPLS in the SDN era book used for 30

Hugo Tinoco 67 Nov 16, 2022
First-Order Probabilistic Programming Language

FOPPL: A First-Order Probabilistic Programming Language This is an implementation of FOPPL, an S-expression based probabilistic programming language d

Renato Costa 23 Dec 20, 2022
This script runs neural style transfer against the provided content image.

Neural Style Transfer Content Style Output Description: This script runs neural style transfer against the provided content image. The content image m

Martynas Subonis 0 Nov 25, 2021
Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs

Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs This is an implemetation of the paper Few-shot Relation Extraction via Baye

MilaGraph 36 Nov 22, 2022
Tool cek opsi checkpoint facebook!

tool apa ini? cek_opsi_facebook adalah sebuah tool yang mengecek opsi checkpoint akun facebook yang terkena checkpoint! tujuan dibuatnya tool ini? too

Muhammad Latif Harkat 2 Jul 17, 2022
Official PyTorch implementation of StyleGAN3

Modified StyleGAN3 Repo Changes Made tied to python 3.7 syntax .jpgs instead of .pngs for training sample seeds to recreate the 1024 training grid wit

Derrick Schultz (he/him) 83 Dec 15, 2022
A PyTorch Implementation of Single Shot MultiBox Detector

SSD: Single Shot MultiBox Object Detector, in PyTorch A PyTorch implementation of Single Shot MultiBox Detector from the 2016 paper by Wei Liu, Dragom

Max deGroot 4.8k Jan 07, 2023
Code for "Adversarial Attack Generation Empowered by Min-Max Optimization", NeurIPS 2021

Min-Max Adversarial Attacks [Paper] [arXiv] [Video] [Slide] Adversarial Attack Generation Empowered by Min-Max Optimization Jingkang Wang, Tianyun Zha

Jingkang Wang 12 Nov 23, 2022
Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

bottom-up-attention This code implements a bottom-up attention model, based on multi-gpu training of Faster R-CNN with ResNet-101, using object and at

Peter Anderson 1.3k Jan 09, 2023
Set of models for classifcation of 3D volumes

Classification models 3D Zoo - Keras and TF.Keras This repository contains 3D variants of popular CNN models for classification like ResNets, DenseNet

69 Dec 28, 2022
Boundary IoU API (Beta version)

Boundary IoU API (Beta version) Bowen Cheng, Ross Girshick, Piotr Dollรกr, Alexander C. Berg, Alexander Kirillov [arXiv] [Project] [BibTeX] This API is

Bowen Cheng 177 Dec 29, 2022