{"id":26911304,"url":"https://github.com/kimrass/kimrass","last_synced_at":"2026-02-05T06:03:50.481Z","repository":{"id":300240457,"uuid":"915575595","full_name":"KimRass/KimRass","owner":"KimRass","description":null,"archived":false,"fork":false,"pushed_at":"2025-01-12T08:18:13.000Z","size":3,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-19T18:22:18.657Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/KimRass.png","metadata":{},"created_at":"2025-01-12T08:17:05.000Z","updated_at":"2025-01-12T08:19:14.000Z","dependencies_parsed_at":null,"dependency_job_id":"5f06fb9d-b5e8-42fa-ad8f-5fd02bd9c3f3","html_url":"https://github.com/KimRass/KimRass","commit_stats":null,"previous_names":["kimrass/kimrass"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/KimRass/KimRass","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KimRass%2FKimRass","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KimRass%2FKimRass/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KimRass%2FKimRass/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KimRass%2FKimRass/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/KimRass","download_url":"https://codeload.github.com/KimRass/KimRass/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KimRass%2FKimRass/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29114512,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-05T05:31:32.482Z","status":"ssl_error","status_checked_at":"2026-02-05T05:31:29.075Z","response_time":65,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["business-intelligence","data-analysis","data-collection","image-inpainting","scene-text-detection","tableau","textual-attribute-recognition"],"created_at":"2025-04-01T14:37:37.697Z","updated_at":"2026-02-05T06:03:50.476Z","avatar_url":"https://github.com/KimRass.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# 1. Personal Projects\n\n## 1) From-scratch PyTorch Implementations of AI papers\n|연도|논문|내용|\n|:-:|:-|:-|\n|Vision|\n|2014|[VAE](https://github.com/KimRass/VAE) (Kingma and Welling)|[✓] Training on MNIST\u003cbr\u003e[✓] Visualizing Encoder output\u003cbr\u003e[✓] Visualizing Decoder output\u003cbr\u003e[✓] Reconstructing image|\n|2015|[CAM](https://github.com/KimRass/CAM) (Zhou et al.)|[✓] Applying GoogLeNet\u003cbr\u003e[✓] Generating 'Class Activatio Map'\u003cbr\u003e[✓] Generating bounding box|\n|2016|[Gatys et al.](https://github.com/KimRass/Gatys-et-al.-2016)|[✓] Experimenting on input image size\u003cbr\u003e[✓] Experimenting on VGGNet-19 with Batch normalization\u003cbr\u003e[✓] Applying VGGNet-19|\n||[YOLO](https://github.com/KimRass/YOLO) (Redmon et al.)|[✓] Model architecture\u003cbr\u003e[✓] Visualizing ground truth on grid\u003cbr\u003e[✓] Visualizing model output\u003cbr\u003e[✓] Visualizing class probability map\u003cbr\u003e[ㅤ] Loss function\u003cbr\u003e[ㅤ] Training on VOC 2012|\n||[DCGAN](https://github.com/KimRass/DCGAN) (Radford et al.)|[✓] Training on CelebA at 64 × 64\u003cbr\u003e [✓] Sampling\u003cbr\u003e[✓] Interpolating in latent space\u003cbr\u003e[ㅤ] Training on CelebA at 32 × 32|\n||[Noroozi et al.](https://github.com/KimRass/Mehdi-Noroozi-et-al.-2016)|[✓] Model architecture\u003cbr\u003e[✓] Chromatic aberration\u003cbr\u003e[✓] Permutation set|\n||[Zhang et al.](https://github.com/KimRass/Richard-Zhang-et-al.-2016)|[✓]  Visualizing empirical probability distribution\u003cbr\u003e[ㅤ] Model architecture\u003cbr\u003e[ㅤ] Loss function\u003cbr\u003e[ㅤ] Training|\n|2014\u003cbr\u003e2017|[Conditional GAN](https://github.com/KimRass/Conditional-WGAN-GP) (Mirza et al.)\u003cbr\u003e[WGAN-GP](https://github.com/KimRass/Conditional-WGAN-GP) (Gulrajani et al.)|[✓] Training on MNIST|\n|2016\u003cbr\u003e2017|[VQ-VAE](https://github.com/KimRass/VQ-VAE-PixelCNN) (Oord et al.)\u003cbr\u003e[PixelCNN](https://github.com/KimRass/VQ-VAE-PixelCNN) (Oord et al.)|[✓] Training on Fashion MNIST\u003cbr\u003e[✓] Training on CIFAR-10\u003cbr\u003e[✓] Sampling|\n|2017|[Pix2Pix](https://github.com/KimRass/Pix2Pix) (Isola et al.)|[✓] Experimenting on image mean and std\u003cbr\u003e[✓] Experimenting on `nn.InstanceNorm2d()`\u003cbr\u003e[✓] Training on Google Maps\u003cbr\u003e[✓] Training on Facades\u003cbr\u003e[ㅤ] higher resolution input image|\n||[CycleGAN](https://github.com/KimRass/CycleGAN) (Zhu et al.)|[✓] Experimenting on random image pairing\u003cbr\u003e[✓] Experimenting on LSGANs\u003cbr\u003e[✓] Training on monet2photo\u003cbr\u003e[✓] Training on vangogh2photo\u003cbr\u003e[✓] Training on cezanne2photo\u003cbr\u003e[✓] Training on ukiyoe2photo\u003cbr\u003e[✓] Training on horse2zebra\u003cbr\u003e[✓] Training on summer2winter_yosemite|\n|2018|[PGGAN](https://github.com/KimRass/PGGAN) (Karras et al.)|[✓] Experimenting on image mean and std\u003cbr\u003e[✓] Training on CelebA-HQ at 512 × 512\u003cbr\u003e[✓] Sampling|\n||[DeepLabv3](https://github.com/KimRass/DeepLabv3) (Chen et al.)|[✓] Training on VOC 2012\u003cbr\u003e[✓] Predicting on VOC 2012 validation set\u003cbr\u003e[✓] Average mIoU\u003cbr\u003e[✓] Visualizing model output|\n||[RotNet](https://github.com/KimRass/RotNet) (Gidaris et al.)|[✓] Visualizing Attention map|\n||[StarGAN](https://github.com/KimRass/StarGAN) (Yunjey Choi et al.)|[✓] Model architecture|\n|2020|[STEFANN](https://github.com/KimRass/STEFANN) (Roy et al.)|[✓] FANnet architecture\u003cbr\u003e[✓] Colornet architecture\u003cbr\u003e[✓] Training FANnet on Google Fonts\u003cbr\u003e[✓] Custom Google Fonts dataset\u003cbr\u003e[✓] Average SSIM\u003cbr\u003e[ㅤ] Training Colornet|\n||[DDPM](https://github.com/KimRass/DDPM) (Ho et al.)|[✓] Training on CelebA at 32 × 32\u003cbr\u003e[✓] Training on CelebA at 64 × 64\u003cbr\u003e[✓] Visualizing denoising process\u003cbr\u003e[✓] Sampling using linear interpolation\u003cbr\u003e[✓] Sampling using coarse-to-fine interpolation|\n||[DDIM](https://github.com/KimRass/DDIM) (Song et al.)|[✓] Normal sampling\u003cbr\u003e[✓] Sampling using spherical linear interpolation\u003cbr\u003e[✓] Sampling using grid interpolation\u003cbr\u003e[✓] Truncated normal|\n||[ViT](https://github.com/KimRass/ViT) (Dosovitskiy et al.)|[✓] Training on CIFAR-10\u003cbr\u003e[✓] Training on CIFAR-100\u003cbr\u003e[✓] Visualizing Attention map using Attention Roll-out\u003cbr\u003e[✓] Visualizing position embedding similarity\u003cbr\u003e[✓] Interpolating position embedding\u003cbr\u003e[✓] CutOut\u003cbr\u003e[✓] CutMix\u003cbr\u003e[✓] Hide-and-Seek|\n||[SimCLR](https://github.com/KimRass/SimCLR) (Chen et al.)|[✓] Normalized temperature-scaled cross entropy loss\u003cbr\u003e[✓] Data augmentation\u003cbr\u003e[✓] Pixel intensity histogram|\n||[DETR](https://github.com/KimRass/DETR) (Carion et al.)|[✓] Model architecture\u003cbr\u003e[ㅤ] Bipartite matching \u0026 loss\u003cbr\u003e[ㅤ] Batch normalization freezing\u003cbr\u003e[ㅤ] Training on COCO 2017\n|2021|[Improved DDPM](https://github.com/KimRass/Improved-DDPM) (Nichol and Dhariwal)|[✓] Cosine diffusion schedule|\n||[Classifier-Guidance](https://github.com/KimRass/Classifier-Guidance) (Dhariwal and Nichol)|[✓] Training on CIFAR-10\u003cbr\u003e[ㅤ] AdaGN\u003cbr\u003e[ㅤ] BiGGAN Upsample/Downsample\u003cbr\u003e[ㅤ] Improved DDPM sampling\u003cbr\u003e[ㅤ] Conditional/Unconditional models\u003cbr\u003e[ㅤ] Super-resolution model\u003cbr\u003e[ㅤ] Interpolation|\n||[ILVR](https://github.com/KimRass/ILVR) (Choi et al.)|[✓] Sampling using single reference\u003cbr\u003e[✓] Sampling using various downsampling factors\u003cbr\u003e[✓] Sampling using various conditioning range|\n||[SDEdit](https://github.com/KimRass/SDEdit) (Meng et al.)|[✓] User input stroke simulation\u003cbr\u003e[✓] Applying CelebA at 64 × 64\u003cbr\u003e[ㅤ] Total repeats.\u003cbr\u003e[ㅤ] VE SDEdit.\u003cbr\u003e[ㅤ] Sampling from scribble.\u003cbr\u003e[ㅤ] Image editing only on masked regions.|\n||[MAE](https://github.com/KimRass/MAE) (He et al.)|[✓] Model architecture for self-supervised pre-training\u003cbr\u003e[✓] Model architecture for classification\u003cbr\u003e[ㅤ] Self-supervised pre-training on ImageNet-1K\u003cbr\u003e[ㅤ] Fine-tuning on ImageNet-1K\u003cbr\u003e[ㅤ] Linear probing|\n||[Copy-Paste](https://github.com/KimRass/Copy-Paste) (Ghiasi et al.)|[✓] COCO dataset processing\u003cbr\u003e[✓] Large scale jittering\u003cbr\u003e[✓] Copy-Paste (within mini-batch)\u003cbr\u003e[✓] Visualizing data\u003cbr\u003e[ㅤ] Gaussian filter|\n||[ViViT](https://github.com/KimRass/ViViT) (Arnab et al.)|[✓] 'Spatio-temporal attention' architecture\u003cbr\u003e[✓] 'Factorised encoder' architecture\u003cbr\u003e[✓] 'Factorised self-attention' architecture|\n|2022|[CFG](https://github.com/KimRass/CFG) (Ho et al.)|\n|Language|\n|2017|[Transformer](https://github.com/KimRass/Transformer) (Vaswani et al.)|[✓] Model architecture\u003cbr\u003e[✓] Visualizing position encoding|\n|2019|[BERT](https://github.com/KimRass/BERT) (Devlin et al.)|[✓] Model architecture\u003cbr\u003e[✓] Masked language modeling\u003cbr\u003e[✓] BookCorpus data processing\u003cbr\u003e[✓] SQuAD data processing\u003cbr\u003e[✓] SWAG data processing|\n||[Sentence-BERT](https://github.com/KimRass/Sentence-BERT) (Reimers et al.)|[✓] Classification loss\u003cbr\u003e[✓] Regression loss\u003cbr\u003e[✓] Constrastive loss\u003cbr\u003e[✓] STSb data processing\u003cbr\u003e[✓] WikiSection data processing\u003cbr\u003e[ㅤ] NLI data processing|\n||[RoBERTa](https://github.com/KimRass/RoBERTa) (Liu et al.)|[✓] BookCorpus data processing\u003cbr\u003e[✓] Masked language modeling\u003cbr\u003e[ㅤ] BookCorpus data processing ('SEGMENT-PAIR' + NSP)\u003cbr\u003e[ㅤ] BookCorpus data processing ('SENTENCE-PAIR' + NSP)\u003cbr\u003e[✓] BookCorpus data processing ('FULL-SENTENCES')\u003cbr\u003e[ㅤ] BookCorpus data processing ('DOC-SENTENCES')|\n|2021|[Swin Transformer](https://github.com/KimRass/Swin-Transformer) (Liu et al.)|[✓] Patch partition\u003cbr\u003e[✓] Patch merging\u003cbr\u003e[✓] Relative position bias\u003cbr\u003e[✓] Feature map padding\u003cbr\u003e[✓] Self-attention in non-overlapped windows\u003cbr\u003e[ㅤ] Shifted Window based Self-Attention|\n|2024|[RoPE](https://github.com/KimRass/RoPE) (Su et al.)|[✓] Rotary Positional Embedding|\n|Vision-Language|\n|2021|[CLIP](https://github.com/KimRass/CLIP) (Radford et al.)|[✓] Training on Flickr8k + Flickr30k\u003cbr\u003e[✓] Zero-shot classification on ImageNet1k (mini)\u003cbr\u003e[✓] Linear classification on ImageNet1k (mini)|\n\u003c!-- ||[Noroozi et al.](https://github.com/KimRass/Mehdi-Noroozi-et-al.-2017)|[✓] Model architecture\u003cbr\u003e[✓] Constrastive loss| --\u003e\n\u003c!-- ||[PixelLink](https://github.com/KimRass/PixelLink)|Deng et al.|[✓] Model architecture\u003cbr\u003e[✓] Instance-balanced cross entropy loss\u003cbr\u003e[✓] Model output post-processing| --\u003e\n\n## 2) [Fine-tuning 'EasyOCR' on the '공공행정문서 OCR' Dataset Provided by 'AI-Hub'](https://github.com/KimRass/train_easyocr)\n\n## 3) [Recognizing Book Content Using the 'CLOVA OCR API'](https://github.com/KimRass/book_text_recognizer)\n\n## 4) [A Rule-based Algorithm for Solving Edge-matching Puzzles of Arbitrary Sizes Using L2 Distance](https://github.com/KimRass/Jigsaw-Puzzle)\n\n## 5) [A 'FastAPI'-based API for Performing Semantic Segmentation Using a 'DeepLabv3' Pretrained on the 'VOC2012' dataset](https://github.com/KimRass/FastAPI)\n\n\u003c!-- # 2. Resume\n- [이력서-김종범](https://github.com/KimRass/KimRass/blob/main/이력서-김종범.md) --\u003e\n\n\u003c!-- # 2. Github Stats\n![KimRass' GitHub stats](https://github-readme-stats.vercel.app/api?username=KimRass\u0026show_icons=true\u0026theme=radical) --\u003e\n\u003c!-- \n# 2. 'Baekjoon Online Judge' Solved Rank\n![hyp3rflow's solved.ac stats](https://github-readme-solvedac.hyp3rflow.vercel.app/api/?handle=rmx1000)\n --\u003e","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkimrass%2Fkimrass","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkimrass%2Fkimrass","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkimrass%2Fkimrass/lists"}