Yakhyokhuja Valikhujaev

uniface. UniFace: A Unified Face Analysis Library for Python | A comprehensive suite of high-performance face analysis components that outperform leading alternatives.

face-parsing. Real-Time Face Parsing with BiSeNet, PyTorch, ONNX Runtime, and Pretrained Weights

gaze-estimation. Real-Time Gaze Estimation with ResNet, MobileNet, MobileOne, PyTorch, ONNX Runtime, and Demo Inference

face-reidentification. Face Re-Identification with SCRFD, ArcFace, FAISS, ONNX Runtime, and Vector Search

retinaface-pytorch. RetinaFace Face Detection in PyTorch with Pretrained Weights, ONNX Export, and Runtime Inference

head-pose-estimation. Real-Time Head Pose Estimation with ResNet, MobileNet, and ONNX Runtime

yolo2voc. YOLO ↔ VOC format converter | Fast and simple tool for converting annotations between YOLO and Pascal VOC formats, with optional multiprocessing support.

crack-segmentation. Road crack segmentation with UNet in PyTorch — Includes implementations of multiple loss functions such as Focal, Dice, and Dice + CE.

facial-analysis. 👤🔍 | Face Detection , Gender and Age, Face Recognition, Facial Landmarks

face-anti-spoofing. Silent-Face-Anti-Spoofing minimal PyTorch and ONNX Runtime Inference codebase

pytorch-tutorials. 🤖 | A collection of comprehensive PyTorch tutorials covering fundamental and advanced deep learning concepts

face-recognition. High-Performance Face Recognition Framework (models trained on MS1MV2) | In PyTorch >> ONNX Runtime Inference

smolvlm-realtime-webcam-vllm. Real-time webcam demo using SmolVLM with vLLM backend

yolov1-pytorch. 📦🔍 | YOLOv1 (Real-Time Object Detection) implementation using PyTorch

darknet-pytorch. 📷 | DarkNet19, DarkNet53, DarkNet53-ELASTIC and CSPDarkNet53 Implementation using PyTorch

fast-neural-style-transfer. Fast Neural Style Transfer implementation using PyTorch > ONNX Inference

korean-license-plate-generator. 🚗 | Korean License Plate Generator with YOLO format labels

unet-pytorch. 🚗 | UNet implementation using PyTorch | CARVANA Dataset | Car Segmentation

tiny-face-pytorch. 🚀 | Ultra-lightweight 1MB face detection & landmarks models for mobile and edge devices. > ONNX > WebCam

mobilenetv3-pytorch. PyTorch Implementation of MobileNetV3 large and small

captcha-reader-keras. OCR model for reading Captchas using Keras API

people-tracker. People Tracker using ByteTracker and YOLOv8-nano ONNX Runtime

deep-text-recognition. 📃 | Deep Text Recognition Implementation using PyTorch

yolov1-resnet. YOLOv1 re-implementation using PyTorch. Backbone is ResNet50.

yolov5-crowdhuman-onnx. Person detection using YOLOv5m, ONNX Runtime. Trained on Crowdhuman dataset.

east-pytorch. Reimplementation of "EAST: An Efficient and Accurate Scene Text Detector" using PyTorch

faceboxes-pytorch. Re-Implementation of "FaceBoxes: A CPU Real-time Face Detector with High Accuracy" | Less than 4MB

kokoro-onnx. Kokoro-82m TTS ONNX Runtime inference | Gradio Demo | HuggingFace Demo | Docker

efficientnet-pytorch. PyTorch Implementation of EfficientNet b0-b7 models

yolov5-license-plate-detection. License plate detection using YOLOv5, ONNX Runtime

yolov5-onnx-inference. YOLOv5 ONNX inference for Image, Video and Webcam

deeplabv3-pytorch. Implementation of DeepLabV3 using PyTorch

yolov5-pytorch. Simplified version of YOLOv5n-x architecture using PyTorch

algorithms-roadmap. Problems by Topics to master Problem Solving (NeetCode Roadmap)

polyp-segmentation. 🫁 | Polyp Segmentation using PyTorch

clovaai-craft. CRAFT-PyTorch official implementation using PyTorch

mobileone-inference. MobileOne: An Improved One millisecond Mobile Backbone

captcha-reader-pytorch. Captcha recognition using PyTorch

yolov5-face-onnx-inference. YOLOv5 Face Detection ONNX inference for Image, Video and Webcam

widerface_evaluation. Python Evaluation Code for Wider Face Dataset

pytorch-losses. Implementation of various Loss function using PyTorch

dcgan-pytorch. DCGAN implementation using PyTorch

llm-practice. LLM Study with DataTalksClub

llama-tokenizer. Llama tokenizer for Uzbek Language

document-parsing. End-to-end pipeline to crop PDF pages, run vision-language OCR with Qwen2.5-VL, and merge outputs into structured text.

yakhyo.github.io. Personal website, portfolio, and blog built with Jekyll

face-landmark-detection. 👤 | Face Landmark Detection using PFDL | In PyTorch >> ONNX Runtime Inference | Pre-trained weights & Training code

mobilenetv2-pytorch. PyTorch Implementation of MobileNetV2

video-classification-pytorch. Video Classification using R(2+1)D based on ResNet18 on UCF-101 dataset. PyTorch Implementation.