injo kim's repositories
Technology-forecasting-using-GNN
Prediction of promising technologies for autonomous driving based on GitHub open source data
Character-level-language-model
It aims to write new sentences by learning character units sentences using RNN. As training data, a collection of Shakespeare's novels was used.
GitHub-crawler
GitHub crawler for Graduate research
MVTec-SAM-Validation
This repository aims to measure the zero-shot segmentation performance of Segment Anything Models (SAM) on Industrial defect data
PyTorch-VAE
A Collection of Variational Autoencoders (VAE) in PyTorch.
Advanced-Machine-Learning-Lecture
Seoul National University of Science and Technology. Department of Data Science Fall 2020, Advanced machine learning Class Practice Code
anomalib
An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.
CLIP-SAM
Experiment on combining CLIP with SAM to do open-vocabulary image segmentation.
data-mining-lecture
Seoul National University of Science and Technology, Department of Data Science, Spring Semester 2020 Data Mining Class Practice Code
electricity_usage_forecast
Dacon AI friends third competiton 'electricity usage forecast'
evidential-deep-learning
This repo contains a PyTorch implementation of the paper: "Evidential Deep Learning to Quantify Classification Uncertainty"
Extract-company-preference-factors
Based on company review data, company preference factors are derived. This project was conducted as a part of the "Unstructured Data Analysis" class at the Department of Data Science, Seoul National University of Science and Technology
f-AnoGAN-PyTorch
Unofficial PyTorch implementation for f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks.
HIL-data-splitter
This repository functions to split the data into a form suitable for HIL.
lama-cleaner
Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
MNIST-classification
This project classifies MNIST data that is widely used in computer vision. A basic CNN model was used as the model.
ntis_crawler
국가과학기술정보서비스(NTIS)의 사업 정보용 크롤러
PatchCore-with-classifier
This repository compares the performance of features for anomaly detection. The baseline feature is hight-dim feature created using Patchcore. The subject feature is patchcore features with concatenated hand-crafted features.
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
recommenders
Best Practices on Recommendation Systems
Research-area-extract-from-papers
The major research areas are derived using the paper data of the researchers at Seoul National University of Science and Technology. This project was carried out as part of "Data and Business Innovation Lab."'s project.
Sam_LoRA
Segment Your Ring (SYR) - Segment Anything model adapted with LoRA to segment rings.
Segment-Any-Anomaly
This project addresses zero-shot anomaly detection by combining SAM and Grouding DINO.
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.