Stars
Trial OSS for QUBO-meta-expression, fork from tytansdk/tytan
Tesseract 4 traineddata for recognizing Seven Segment Display
Code repository for the paper - "Matryoshka Representation Learning"
Wikipediaの日本語記事を元に、ユーザの質問に回答するGradioベースのRAGのサンプル
Simple, reliable seven-segment OCR using OpenCV
This is a tesseract based OCR to read from seven segment display.
Digitizes numbers from videos & images of seven segment displays
Autoware - the world's leading open-source software project for autonomous driving
A Japanese NLP Library using spaCy as framework based on Universal Dependencies
Instant, easy, and predictable development environments
💯 CSPostgraduate 计算机考研 408 专业课资料及真题资源
You Only Look Once for Panopitic Driving Perception.（MIR2022）
Unofficial implemention of lanenet model for real time lane detection
Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification (TPAMI 2022)
Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
Companion webpage to the book "Mathematics For Machine Learning"
[ICCV 2019] Monocular depth estimation from a single image
Python SDK, Proxy Server to call 100+ LLM APIs using the OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
Metric depth estimation from a single image
[CVPR 2024] Aligning and Prompting Everything All at Once for Universal Visual Perception
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots