[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-9582":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":10,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":39,"readmeContent":40,"aiSummary":41,"trendingCount":16,"starSnapshotCount":16,"syncStatus":42,"lastSyncTime":43,"discoverSource":44},9582,"learnopencv","spmallick\u002Flearnopencv","spmallick","Learn OpenCV  : C++ and Python Examples","https:\u002F\u002Fwww.learnopencv.com\u002F",null,"Jupyter Notebook",22966,11691,864,220,0,1,15,58,8,45,false,"master",true,[26,27,28,29,30,31,32,33,34,35,36,37,38],"ai","computer-vision","computervision","deep-learning","deep-neural-networks","deeplearning","machine-learning","opencv","opencv-cpp","opencv-library","opencv-python","opencv-tutorial","opencv3","2026-06-12 02:02:09","# LearnOpenCV\n\nThis repository contains code for Computer Vision, Deep learning, and AI research articles shared on our blog [LearnOpenCV.com](https:\u002F\u002Fwww.LearnOpenCV.com).\n\nWant to become an expert in AI? [AI Courses by OpenCV](https:\u002F\u002Fopencv.org\u002Fcourses\u002F) is a great place to start.\n\n\u003Ca href=\"https:\u002F\u002Fopencv.org\u002Fcourses\u002F\">\n\n\u003Cp align=\"center\">\n\u003Cimg src=\"https:\u002F\u002Flearnopencv.com\u002Fwp-content\u002Fuploads\u002F2023\u002F01\u002FAI-Courses-By-OpenCV-Github.png\">\n\u003C\u002Fp>\n\u003C\u002Fa>\n\n## List of Blog Posts\n\n| Blog Post | Code|\n| ------------- |:-------------|\n| [YOLO26 Keypoint Estimation: Real-Time Pose Estimation with Ultralytics](https:\u002F\u002Flearnopencv.com\u002Fyolo26-pose-estimation-tutorial\u002F) | [Code](https:\u002F\u002Fgithub.com\u002FSudip-329\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLO26_Keypoint_Estimation) |\n| [RF-DETR Segmentation: Real-Time Detection & Instance Segmentation Guide](https:\u002F\u002Flearnopencv.com\u002Frf-detr-segmentation-real-time-detection-instance-segmentation-guide\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FRF_DETR_Segmentation_Demo) |\n| [YOLO26 Instance Segmentation: Pixel-Perfect AI at Real-Time Speed](https:\u002F\u002Flearnopencv.com\u002Fyolo26-instance-segmentation-pixel-perfect-ai-at-real-time-speed\u002F) | [Code](YOLO26-instance-segmentation\u002F) |\n| [Multi-Object Tracking with Roboflow Trackers and OpenCV](https:\u002F\u002Flearnopencv.com\u002Fmulti-object-tracking-with-roboflow-trackers-and-opencv\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FRoboflow_Trackers_Demo) |\n| [Real-Time Face Blur and Pixelation with OpenCV YuNet](https:\u002F\u002Flearnopencv.com\u002Fface-blur-pixelation-opencv-yunet\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFaceBlurPixelate) |\n| [Breaking the Bottleneck: Achieving Native NMS-Free Inference with YOLO26](https:\u002F\u002Flearnopencv.com\u002Fyolo26-nms-free-inference\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLO26-NMS-Free-Demo) |\n| [YOLOv26: An Object Detector Built for Real-Time Deployment](https:\u002F\u002Flearnopencv.com\u002Fyolov26-real-time-deployment\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FInference_RF-DETR_YOLO26_RT-DETR) |\n| [Beyond Transformers: A Deep Dive into HOPE](https:\u002F\u002Flearnopencv.com\u002Fhope-beyond-transformers\u002F) | |\n| [Serving SGLang: Launch a Production-Style Server](https:\u002F\u002Flearnopencv.com\u002Fsglang-a-production-server\u002F) | |\n|[Deployment on Edge: LLM Serving on Jetson using vLLM](https:\u002F\u002Flearnopencv.com\u002Fdeployment-on-edge-vllm-on-jetson\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDeployment-on-Edge-LLM-Serving-on-Jetson-using-vLLM)|\n|[Nested Learning: Is Deep Learning Architecture an Illusion?](https:\u002F\u002Flearnopencv.com\u002Fnested-learning\u002F)||\n| [How to Build a GitHub Code-Analyser Agent for Developer Productivity](https:\u002F\u002Flearnopencv.com\u002Fhow-to-build-a-github-code-analyser-agent\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FHow_to_Build_a_GitHub_Code_Analyser_Agent_for_Developer_Productivity) |\n| [The Existential Problems in LLM Serving](https:\u002F\u002Flearnopencv.com\u002Fthe-existential-problems-in-llm-serving\u002F) | |\n| [SAM 3D: Foundation Model for Single-Image 3D Reconstruction](https:\u002F\u002Flearnopencv.com\u002Fsam-3d\u002F) | |\n| [SAM-3: What’s New, How It Works, and Why It Matters](https:\u002F\u002Flearnopencv.com\u002Fsam-3-whats-new\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FSAM-3) |\n| [Image-GS: Adaptive Image Reconstruction using 2D Gaussians](https:\u002F\u002Flearnopencv.com\u002Fimage-gs-image-reconstruction-using-2d-gaussians\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FImage_GS_Adaptive_Image_Reconstruction_using_2D_Gaussians) |\n| [Ultimate Guide to Vector Databases and RAG Pipeline](https:\u002F\u002Flearnopencv.com\u002Fvector-db-and-rag-pipeline-for-document-rag\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FUltimate_Guide_to_Vector_Databases_and_RAG_pipeline) |\n|[What Makes DeepSeek OCR So Powerful](https:\u002F\u002Flearnopencv.com\u002Fwhat-makes-deepseek-ocr-so-powerful\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FWhat-Makes-DeepSeek-OCR-So-Powerful)|\n| [2D Gaussian Splatting: Geometrically Accurate Radiance Field Reconstruction](https:\u002F\u002Flearnopencv.com\u002F2d-gaussian-splatting-2dgs\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002F2D_Gaussian_Splatting_Geometrically_Accurate_Radiance_Field_Reconstruction) |\n| [TRM: Tiny Recursive Models](https:\u002F\u002Flearnopencv.com\u002Ftrm-tiny-ai-models-outsmarting-giants-on-complex-puzzles\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FTRM) |\n|[Deploying ML Models on Arduino: From Blink to Think](https:\u002F\u002Flearnopencv.com\u002Fdeploying-ml-on-arduino\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDeploying-ML-Models-on-Arduino-From-Blink-to-Think)|\n| [VideoRAG: Redefining Long-Context Video Comprehension](https:\u002F\u002Flearnopencv.com\u002Fvideorag-long-context-video-comprehension\u002F) | |\n| [AI Agent in Action: Automating Desktop Tasks with VLMs](https:\u002F\u002Flearnopencv.com\u002Fbuild-ai-agents-using-vlm\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FLocal-VLM-Agents-in-Action-GUI-Automation-with-Moondream3-and-Gemini) |\n| [Top VLM Evaluation Metrics for Optimal Performance Analysis](https:\u002F\u002Flearnopencv.com\u002Fvlm-evaluation-metrics\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FVLM_Evaluation_Metrics) |\n|[Getting Started with VLM on Jetson Nano](https:\u002F\u002Flearnopencv.com\u002Fvlm-on-jetson-nano\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FGetting-Started-with-VLM-on-Jetson-Nano)|\n| [VLM on Edge: Worth the Hype or Just a Novelty?](https:\u002F\u002Flearnopencv.com\u002Fvlm-on-edge-devices\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FVLM-on-Edge-Worth-the-Hype-or-Just-a-Novelty) |\n| [AnomalyCLIP : Harnessing CLIP for Weakly-Supervised Video Anomaly Recognition](https:\u002F\u002Flearnopencv.com\u002Fanomalyclip-video-anomaly-recognition\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FAnomalyCLIP_Harnessing_CLIP_for_Weakly_Supervised_Video_Anomaly_Recognition) |\n| [AI_for_Video_Understanding_From_Content_Moderation_to_Summarization](https:\u002F\u002Flearnopencv.com\u002Fai-for-video-understanding\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FAI_for_Video_Understanding_From_Content_Moderation_to_Summarization) |\n| [Video-RAG: Training-Free Retrieval for Long-Video LVLMs](https:\u002F\u002Flearnopencv.com\u002Fvideo-rag-for-long-videos\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FVideo-RAG_Training_Free_Retrieval_for_Long_Video_LVLMs) |\n| [Object Detection and Spatial Understanding with VLMs ft. Qwen2.5-VL](https:\u002F\u002Flearnopencv.com\u002Fobject-detection-with-vlms-ft-qwen2-5-vl\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fobject-detection-with-vlms) |\n| [LangGraph: Building Self-Correcting RAG Agent for Code Generation](https:\u002F\u002Flearnopencv.com\u002Flanggraph-self-correcting-agent-code-generation\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FLangGraph_Building_Self_Correcting_RAG_Agent_for_Code_Generation) |\n| [Inside Sinusoidal Position Embeddings: A Sense of Order](https:\u002F\u002Flearnopencv.com\u002Fsinusoidal-position-embeddings\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FSinusoidal_Position_Embeddings) |\n| [Inside RoPE: Rotary Magic into Position Embeddings](https:\u002F\u002Flearnopencv.com\u002Frope-position-embeddings\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FInside_RoPE_Position_Embeddings) |\n| [SimLingo-Vision-Language-Action-Model-for-Autonomous-Driving](https:\u002F\u002Flearnopencv.com\u002Fsimlingo-vision-language-action-model-for-autonomous-driving\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FSimLingo-Vision-Language-Action-Model-for-Autonomous-Driving) |\n| [FineTuning Gemma 3n for Medical VQA on ROCOv2](https:\u002F\u002Flearnopencv.com\u002Ffinetuning-gemma-3n-medical-vqa\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Ffinetuning-gemma3n) |\n| [SmolLM3 Blueprint: SOTA 3B-Parameter LLM](https:\u002F\u002Flearnopencv.com\u002Fsmollm3-explained\u002F) | |\n| [LangGraph-A-Visual-Automation-and-Summarization-Pipeline](https:\u002F\u002Flearnopencv.com\u002Flanggraph-building-a-visual-web-browser-agent\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FLangGraph-A-Visual-Automation-and-Summarization-Pipeline) |\n| [Fine-Tuning AnomalyCLIP: Class-Agnostic Zero-Shot Anomaly Detection](https:\u002F\u002Flearnopencv.com\u002Ffine-tuning-anomalyclip-medical-anomaly-clip\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-Tuning-AnomalyCLIP) |\n| [SigLIP 2: DeepMind’s Multilingual Vision-Language Model](https:\u002F\u002Flearnopencv.com\u002Fsiglip-2-deepminds-multilingual-vision-language-model\u002F) | |\n| [MedGemma: Google’s Medico VLM for Clinical QA, Imaging, and More](https:\u002F\u002Flearnopencv.com\u002Fmedgemma-explained\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fmedgemma) |\n| [Nanonets-OCR-s: Enabling Rich, Structured Markdown for Document Understanding](https:\u002F\u002Flearnopencv.com\u002Fnanonets-ocr-s\u002F) | |\n| [Optimizing VJEPA-2: Tackling Latency & Context in Real-Time Video Classification Scripts](https:\u002F\u002Flearnopencv.com\u002Foptimizing-vjepa-2-in-real-time-video-classification\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FVJEPA-2-Video-Classification) |\n| [V-JEPA 2: Meta’s Breakthrough in AI for the Physical World](https:\u002F\u002Flearnopencv.com\u002F?p=73731&preview_id=73731&preview_nonce=beb70ccf8e&preview=true#heading-7) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FV-JEPA-2) |\n| [NVIDIA Cosmos Reason1: Video Understanding](https:\u002F\u002Flearnopencv.com\u002Fcosmos-reason-vlm-video-vqa\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FCosmos-Reason1-Video-Understanding) |\n| [GR00T N1.5 Explained](https:\u002F\u002Flearnopencv.com\u002Fgr00t-n1_5-explained\u002F) |  |\n| [LLaVA](https:\u002F\u002Flearnopencv.com\u002Fllava-training-a-visual-assistant\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FLLaVA) |\n| [SmolVLA: Affordable & Efficient VLA Robotics on Consumer GPUs](https:\u002F\u002Flearnopencv.com\u002Fsmolvla-lerobot-vision-language-action-model\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fsmolvla) |\n| [Fine-Tuning Grounding DINO: Open-Vocabulary Object Detection](https:\u002F\u002Flearnopencv.com\u002Ffine-tuning-grounding-dino\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-Tuning-Grounding-DINO-Open-Vocabulary-Object-Detection) |\n| [Getting Started with Qwen3 – The Thinking Expert](https:\u002F\u002Flearnopencv.com\u002Fqwen3\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fqwen3) |\n| [Inside the GPU: A Comprehensive Guide to Modern Graphics Architecture](https:\u002F\u002Flearnopencv.com\u002Fmodern-gpu-architecture-explained\u002F) | |\n| [Distributed Parallel Training: PyTorch](https:\u002F\u002Flearnopencv.com\u002Fdistributed-parallel-training-pytorch-multi-gpu-setup\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDistributed-Training-PyTorch) |\n| [MONAI: The Definitive Framework for Medical Imaging Powered by PyTorch](https:\u002F\u002Flearnopencv.com\u002Fmonai-medical-imaging-pytorch\u002F) | |\n| [SANA-Sprint: The One-Step Revolution in High-Quality AI Image Synthesis](https:\u002F\u002Flearnopencv.com\u002Fsana-sprint-the-one-step-revolution-in-high-quality-ai-image-synthesis\u002F) | |\n| [FramePack-Video-Diffusion-but-feels-like-Image-Diffusion](https:\u002F\u002Flearnopencv.com\u002Fframepack-video-diffusion\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFramePack-Video-Diffusion-but-feels-like-Image-Diffusion) |\n| [Model Weights File Formats in Machine Learning](https:\u002F\u002Flearnopencv.com\u002Fmodel-weights-file-formats-in-machine-learning\u002F) | |\n| [Unsloth: A Guide from Basics to Fine-Tuning Vision Models](https:\u002F\u002Flearnopencv.com\u002Funsloth-guide-efficient-llm-fine-tuning\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FUnsloth_A_Guide_From_Basics_to_Fine_Tuning_Vision_Models) |\n| [Iterative Closest Point (ICP) Algorithm Explained](https:\u002F\u002Flearnopencv.com\u002Fiterative-closest-point-icp-explained\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Fblob\u002Fmaster\u002FIterative-Closest-Point-ICP) |\n| [MedSAM2 Explained: One Prompt to Segment Anything in Medical Imaging](https:\u002F\u002Flearnopencv.com\u002Fmedsam2-explained\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Fblob\u002Fmaster\u002Fmedsam2-explained) |\n| [Batch Normalization and Dropout as Regularizers](https:\u002F\u002Flearnopencv.com\u002Fbatch-normalization-and-dropout-as-regularizers\u002F) | |\n| [DINOv2_by_Meta_A_Self-Supervised_foundational_vision_model](https:\u002F\u002Flearnopencv.com\u002Fdinov2-self-supervised-vision-transformer\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Fblob\u002Fmaster\u002FDINOv2_by_Meta_A_Self-Supervised_foundational_vision_model) |\n| [Beginner's Guide to Embedding Models](https:\u002F\u002Flearnopencv.com\u002Fembedding-models-explained\u002F) | |\n| [MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors](https:\u002F\u002Flearnopencv.com\u002Fmast3r-slam-realtime-dense-slam-explained\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Fblob\u002Fmaster\u002FMASt3R-SLAM) |\n| [Google's A2A Protocol](https:\u002F\u002Flearnopencv.com\u002Fgoogles-a2a-protocol-heres-what-you-need-to-know\u002F) | |\n| [Nvidia SANA : Faster Image Generation](https:\u002F\u002Flearnopencv.com\u002Fnvidia-sana-image-generation-model\u002F) | |\n| [Fine-tuning RF-DETR](https:\u002F\u002Flearnopencv.com\u002Frf-detr-object-detection\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Fblob\u002Fmaster\u002FFine-tuning-RF-DETR) |\n| [Qwen2.5-Omni: A Real-Time Multimodal AI](https:\u002F\u002Flearnopencv.com\u002Fqwen2.5-omni\u002F) | |\n| [Vision Language Action Models: Robotic Control](https:\u002F\u002Flearnopencv.com\u002Fvision-language-action-models-lerobot-policy\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FVision-Language-Action-Models) |\n| [Fine-Tuning Gemma 3 VLM using QLoRA for LaTeX-OCR Dataset](https:\u002F\u002Flearnopencv.com\u002Ffine-tuning-gemma-3\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-Tuning-Gemma-3-VLM-using-QLoRA-for-LaTeX-OCR-Dataset) |\n| [ComfyUI](https:\u002F\u002Flearnopencv.com\u002Fintroduction-to-comfyui-for-stable-diffusion\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FComfyUI) |\n| [Gemma-3: A Comprehensive Introduction](https:\u002F\u002Flearnopencv.com\u002Fgemma-3\u002F) | |\n| [YOLO11 on Raspberry Pi: Optimizing Object Detection for Edge Devices](https:\u002F\u002Flearnopencv.com\u002Fyolo11-on-raspberry-pi\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fyolo11-on-raspberry-pi) |\n| [VGGT: Visual Geometry Grounded Transformer – For Dense 3D Reconstruction](https:\u002F\u002Flearnopencv.com\u002Fvggt-visual-geometry-grounded-transformer-3d-reconstruction\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FVGGT-3D-Reconstruction) |\n| [DDIM: The Faster, Improved Version of DDPM for Efficient AI Image Generation](https:\u002F\u002Flearnopencv.com\u002Funderstanding-ddim\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDDIM-The-Faster-Improved-Version-of-DDPM-for-Efficient-AI-Image-Generation) |\n| [Introduction to Model Context Protocol (MCP)](https:\u002F\u002Flearnopencv.com\u002Fintroduction-to-model-context-protocol\u002F) | |\n| [MASt3R and MASt3R-SfM Explanation: Image Matching and 3D Reconstruction](https:\u002F\u002Flearnopencv.com\u002Fmast3r-sfm-grounding-image-matching-3d\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FMASt3R-SfM-3D-Reconstruction-Image-Matching) |\n| [MatAnyone Explained: Consistent Memory for Better Video Matting](https:\u002F\u002Flearnopencv.com\u002Fmatanyone-for-better-video-matting\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FMatAnyone-Explained-Consistent-Memory-for-Better-Video-Matting) |\n| [GraphRAG: For Medical Document Analysis](https:\u002F\u002Flearnopencv.com\u002Fgraphrag-explained-knowledge-graphs-medical\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FGraphrag-Medical-Document-Analysis) |\n| [OmniParser: Vision Based GUI Agent](https:\u002F\u002Flearnopencv.com\u002Fomniparser-vision-based-gui-agent\u002F) | |\n| [Fine-Tuning-YOLOv12-Comparison-With-YOLOv11-And-YOLOv7-Based-Darknet](https:\u002F\u002Flearnopencv.com\u002Ffine-tuning-yolov12\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-Tuning-YOLOv12-Comparison-With-YOLOv11-And-YOLOv7-Based-Darknet) |\n| [FineTuning RetinaNet for Wildlife Detection with PyTorch: A Step-by-Step Tutorial](https:\u002F\u002Flearnopencv.com\u002Ffinetuning-retinanet) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Ffinetuning-retinanet) |\n| [DUSt3R: Geometric 3D Vision Made Easy :  Explanation and Results](https:\u002F\u002Flearnopencv.com\u002Fdust3r-geometric-3d-vision\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDUSt3R-Dense-3D-Reconstruction) |\n| [YOLOv12: Attention Meets Speed](https:\u002F\u002Flearnopencv.com\u002Fyolov12) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLOv12) |\n| [Video Generation: A Diffusion based approach](https:\u002F\u002Flearnopencv.com\u002Fvideo-generation-models\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FVideo-Generation-A-Diffusion-based-approach) |\n| [Agentic AI: A Comprehensive Introduction](https:\u002F\u002Flearnopencv.com\u002Fagentic-ai\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FAgentic-AI-A-Comprehensive-Introduction) |\n| [Finetuning SAM2 for Leaf Disease Segmentation](https:\u002F\u002Flearnopencv.com\u002Ffinetuning-sam2\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Ffinetuning-sam2) |\n| [Object Insertion in Gaussian Splatting: Paper Explained and Training Code for MCMC and Bilateral Grid](https:\u002F\u002Flearnopencv.com\u002Fobject-insertion-in-gaussian-splatting\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FObject-Insertion-in-Gaussian-Splatting) |\n| [Depth Pro: Sharp Monocular Metric Depth](https:\u002F\u002Flearnopencv.com\u002Fdepth-pro-monocular-metric-depth) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDepthPro-Monocular-Metric-Depth) |\n| [Fine-tuning-Stable-Diffusion-3_5-UI-images](https:\u002F\u002Flearnopencv.com\u002Ffine-tuning-stable-diffusion-3-5m\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-tuning-Stable-Diffusion-3_5-UI-images) |\n| [SimSiam: Streamlining SSL with Stop-Gradient Mechanism](https:\u002F\u002Flearnopencv.com\u002Fsimsiam\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FSimSiam-Streamlining-SSL-with-Stop-Gradient-Mechanism) |\n| [Image Captioning using ResNet and LSTM](https:\u002F\u002Flearnopencv.com\u002Fimage-captioning\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FImage-Captioning-using-ResNet-and-LSTM) |\n| [Molmo VLM: Paper Explanation and Demo](https:\u002F\u002Flearnopencv.com\u002Fmolmo-vlm) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FMolmo-VLM-SAM2) |\n| [3D Gaussian Splatting Paper Explanation: Training Custom Datasets with NeRF-Studio Gsplats](https:\u002F\u002Flearnopencv.com\u002F3d-gaussian-splatting\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002F3D-Gaussian-Splatting-Code) |\n| [FLUX Image Generation: Experimenting with the Parameters](https:\u002F\u002Flearnopencv.com\u002Fflux-ai-image-generator\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFlux-Image-Generation) |\n| [Contrastive-Learning-SimCLR-and-BYOL(With Code Example)](https:\u002F\u002Flearnopencv.com\u002Fcontrastive-learning-simclr-and-byol-with-code-example\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FContrastive-Learning-SimCLR-and-BYOL) |\n| [The Annotated NeRF : Training on Custom Dataset from Scratch in Pytorch](https:\u002F\u002Flearnopencv.com\u002Fannotated-nerf-pytorch\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FAnnotated-NeRF) |\n| [Stable Diffusion 3 and 3.5: Paper Explanation and Inference](https:\u002F\u002Flearnopencv.com\u002Fstable-diffusion-3\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FStable-Diffusion-3) |\n| [LightRAG - Legal Document Analysis](https:\u002F\u002Flearnopencv.com\u002Flightrag\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FLightRAG-Legal) |\n| [NVIDIA AI Summit 2024 – India Overview](https:\u002F\u002Flearnopencv.com\u002Fnvidia-ai-summit-2024-india-overview\u002F) | |\n| [Introduction to Speech to Speech: Most Efficient Form of NLP](https:\u002F\u002Flearnopencv.com\u002Fspeech-to-speech\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fspeech-to-speech) |\n| [Training 3D U-Net for Brain Tumor Segmentation (BraTS-GLI)](https:\u002F\u002Flearnopencv.com\u002F3d-u-net-brats\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FTraining_3D_U-Net_Brain_Tumor_Seg) |\n| [DETR: Overview and Inference](https:\u002F\u002Flearnopencv.com\u002Fdetr-overview-and-inference\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDETR-Overview_and_Inference) |\n| [YOLO11: Faster Than You Can Imagine!](https:\u002F\u002Flearnopencv.com\u002Fyolo11\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLO11) |\n| [Exploring DINO: Self-Supervised Transformers for Road Segmentation with ResNet50 and U-Net](https:\u002F\u002Flearnopencv.com\u002Ffine-tune-dino-self-supervised-learning-segmentation\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FExploring-DINO-dino-road-segmentation) |\n| [Sapiens: Foundation for Human Vision Models by Meta](https:\u002F\u002Flearnopencv.com\u002Fsapiens-human-vision-models) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FSapiens-Human-Vision-Model-Meta) |\n| [Multimodal RAG with ColPali and Gemini](https:\u002F\u002Flearnopencv.com\u002Fmultimodal-rag-with-colpali) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FMultimodal-RAG-with-ColPali-Gemini) |\n| [Building Autonomous Vehicle in Carla: Path Following with PID Control & ROS 2](https:\u002F\u002Flearnopencv.com\u002Fpid-controller-ros-2-carla\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FBuilding_Autonomous_Vehicle_in_Carla_Path_Following_with_PID_Control_ROS2) |\n| [Handwritten Text Recognition using OCR](https:\u002F\u002Flearnopencv.com\u002Fhandwritten-text-recognition-using-ocr\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FHandwritten_Text_Recognition_using_OCR) |\n| [Training CLIP from Sratch for Image Retrieval](https:\u002F\u002Flearnopencv.com\u002Fclip-model) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FTraining-CLIP-from-Scratch-for-Image-Retrieval) |\n| [Introduction to LiDAR SLAM: LOAM and LeGO-LOAM Paper and Code Explanation with ROS 2 Implementation](https:\u002F\u002Flearnopencv.com\u002Flidar-slam-with-ros2) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FLeGO-LOAM-ROS2) |\n| [Recommendation System using Vector Search](https:\u002F\u002Flearnopencv.com\u002Frecommendation-system-using-vector-search) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FRecommendation-System-using-Vector-Search) |\n| [Fine Tuning Whisper on Custom Dataset](https:\u002F\u002Flearnopencv.com\u002Ffine-tuning-whisper-on-custom-dataset\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-Tuning-Whisper-on-Custom-Dataset) |\n| [SAM 2 – Promptable Segmentation for Images and Videos](https:\u002F\u002Flearnopencv.com\u002Fsam-2\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FSAM_2_Segment_Anything_Model_2) |\n| [Introduction to Feature Matching Using Neural Networks](https:\u002F\u002Flearnopencv.com\u002Ffeature-matching\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFeature-Matching-Using-Neural-Networks) |\n| [Introduction to ROS2 (Robot Operating System 2): Tutorial on ROS2 Working, DDS, ROS1 RMW, Topics, Nodes, Publisher, Subscriber in Python](https:\u002F\u002Flearnopencv.com\u002Frobot-operating-system-introduction) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FIntroduction-to-ROS2-in-python) |\n| [CVPR 2024 Research Papers - Part- 2](https:\u002F\u002Flearnopencv.com\u002Fcvpr-2024-research-papers) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fcvpr-2024-research-papers-part2) |\n| [CVPR 2024: An Overview and Key Papers](https:\u002F\u002Flearnopencv.com\u002Fcvpr2024\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FCVPR-2024) |\n| [Object Detection on Edge Device - OAK-D-Lite](https:\u002F\u002Flearnopencv.com\u002Fobject-detection-on-edge-device) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FObject-Detection-on-Edge-Devices) |\n| [Fine-Tuning YOLOv10 Models on Custom Dataset](https:\u002F\u002Flearnopencv.com\u002Ffine-tuning-yolov10\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-Tuning-YOLOv10-Models-Custom-Dataset) |\n| [ROS2 and Carla Setup Guide for Ubuntu 22.04](https:\u002F\u002Flearnopencv.com\u002Fros2-and-carla-setup-guide\u002F) |  |\n| [Understanding Visual SLAM for Robotics Perception: Building Monocular SLAM from Scratch in Python](https:\u002F\u002Flearnopencv.com\u002Fmonocular-slam-in-python\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FMonocular%20SLAM%20for%20Robotics%20implementation%20in%20python) |\n| [Enhancing Image Segmentation using U2-Net: An Approach to Efficient Background Removal](https:\u002F\u002Flearnopencv.com\u002Fu2-net-image-segmentation\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FEfficient-Background-Removal-using-U2-Net) |\n| [YOLOv10: The Dual-Head OG of YOLO Series](https:\u002F\u002Flearnopencv.com\u002Fyolov10\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLOv10) |\n| [Fine-tuning Faster R-CNN on Sea Rescue Dataset](https:\u002F\u002Flearnopencv.com\u002Ffine-tuning-faster-r-cnn\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-tuning-Faster-R-CNN-on-SeaRescue-Dataset) |\n| [Mastering Recommendation System: A Complete Guide](https:\u002F\u002Flearnopencv.com\u002Frecommendation-system\u002F) | |\n| [Automatic Speech Recognition with Diarization : Speech-to-Text](https:\u002F\u002Flearnopencv.com\u002Fautomatic-speech-recognition\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FAutomatic-Speech-Recognition-with-Diarization-Speech-to-Text) |\n| [Building MobileViT Image Classification Model from Scratch In Keras 3](https:\u002F\u002Flearnopencv.com\u002Fmobilevit-keras-3\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FBuilding%20MobileViT%20from%20Scratch%20in%20Keras%203) |\n| [SDXL Inpainting: Fusing Image Inpainting with Stable Diffusion](https:\u002F\u002Flearnopencv.com\u002Fsdxl-inpainting\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FSDXL-inpainting) |\n| [YOLOv9 Instance Segmentation on Medical Dataset](https:\u002F\u002Flearnopencv.com\u002Fyolov9-instance-segmentation-on-medical-dataset\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLOv9-Instance-Segmentation-on-Medical-Dataset) |\n| [A Comprehensive Guide to Robotics](https:\u002F\u002Flearnopencv.com\u002Fa-comprehensive-guide-to-robotics\u002F) | |\n| [Integrating Gradio with OpenCV DNN](https:\u002F\u002Flearnopencv.com\u002Fintegrating-gradio-with-opencv-dnn\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FIntegrating-Gradio-with-OpenCV-DNN) |\n| [Fine-Tuning YOLOv9 on Custom Dataset](https:\u002F\u002Flearnopencv.com\u002Ffine-tuning-yolov9\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-Tuning-YOLOv9-Models-Custom-Dataset) |\n| [Dreambooth using Diffusers](https:\u002F\u002Flearnopencv.com\u002Fdreambooth-using-diffusers\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDreambooth_using_Diffusers) |\n| [Introduction to Hugging Face Diffusers](https:\u002F\u002Flearnopencv.com\u002Fhugging-face-diffusers\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FIntroduction_to_Diffusers) |\n| [Introduction to Ultralytics Explorer API](https:\u002F\u002Flearnopencv.com\u002Fultralytics-explorer-api\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FIntroduction-to-Ultralytics-Explorer-API) |\n| [YOLOv9: Advancing the YOLO Legacy](https:\u002F\u002Flearnopencv.com\u002Fyolov9-advancing-the-yolo-legacy\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLOv9-Advancing-the-YOLO-Legacy) |\n| [Fine-Tuning LLMs using PEFT](https:\u002F\u002Flearnopencv.com\u002Ffine-tuning-llms-using-peft\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-Tuning-LLMs-using-PEFT) |\n| [Depth Anything: Accelerating Monocular Depth Perception](https:\u002F\u002Flearnopencv.com\u002Fdeciphering-llms\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDepth-Anything) |\n| [Deciphering LLMs: From Transformers to Quantization](https:\u002F\u002Flearnopencv.com\u002Fdeciphering-llms\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDeciphering-LLMs) |\n| [YOLO Loss Function Part 2: GFL and VFL Loss](https:\u002F\u002Flearnopencv.com\u002Fyolo-loss-function-gfl-vfl-loss\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLO-Loss-Functions-Part2) |\n| [YOLOv8-Object-Tracking-and-Counting-with-OpenCV](https:\u002F\u002Flearnopencv.com\u002Fyolov8-object-tracking-and-counting-with-opencv\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLOv8-Object-Tracking-and-Counting-with-OpenCV) |\n| [Stereo Vision in ADAS: Pioneering Depth Perception Beyond LiDAR](https:\u002F\u002Flearnopencv.com\u002Fadas-stereo-vision\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FADAS-Stereo-Vision) |\n| [YOLO Loss Function Part 1: SIoU and Focal Loss](https:\u002F\u002Flearnopencv.com\u002Fyolo-loss-function-siou-focal-loss\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLO-Loss-Functions-Part1) |\n| [Moving Object Detection with OpenCV](https:\u002F\u002Flearnopencv.com\u002Fmoving-object-detection-with-opencv\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FMoving-Object-Detection-with-OpenCV) |\n| [Integrating ADAS with Keypoint Feature Pyramid Network for 3D LiDAR Object Detection](https:\u002F\u002Flearnopencv.com\u002F3d-lidar-object-detection\u002F) | [Code](https:\u002F\u002Fwww.dropbox.com\u002Fscl\u002Ffi\u002F3n1s68jtfkjmw2f5e5ctv\u002F3D-LiDAR-Object-Detection.zip?rlkey=d8q6xvlxis4oxso4qki87omvc&dl=1) |\n| [Mastering All YOLO Models from YOLOv1 to YOLO-NAS: Papers Explained (2024)](https:\u002F\u002Flearnopencv.com\u002Fmastering-all-yolo-models) | |\n| [GradCAM: Enhancing Neural Network Interpretability in the Realm of Explainable AI](https:\u002F\u002Flearnopencv.com\u002Fintro-to-gradcam\u002F) | [Code](https:\u002F\u002Fwww.dropbox.com\u002Fscl\u002Ffo\u002F3p3sg5fnvhrvi9vp00i0w\u002Fh?rlkey=1x01uz5o7esex7p6c8r534iyn&dl=1) |\n| [Text Summarization using T5: Fine-Tuning and Building Gradio App](https:\u002F\u002Flearnopencv.com\u002Ftext-summarization-using-t5\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FText-Summarization-using-T5-Fine-Tuning-and-Building-Gradio-App) |\n| [3D LiDAR Visualization using Open3D: A Case Study on 2D KITTI Depth Frames for Autonomous Driving](https:\u002F\u002Flearnopencv.com\u002F3d-lidar-visualization\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002F3D-LiDAR-Perception) |\n| [Fine Tuning T5: Text2Text Transfer Transformer for Building a Stack Overflow Tag Generator](https:\u002F\u002Flearnopencv.com\u002Ffine-tuning-t5\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-Tuning-T5-Text2Text-Transformer-for-Strack-Overflow-Tag-Generation) |\n| [SegFormer 🤗 : Fine-Tuning for Improved Lane Detection in Autonomous Vehicles](https:\u002F\u002Flearnopencv.com\u002Fsegformer-fine-tuning-for-lane-detection) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-Tuning-SegFormer-For-Lane-Detection) |\n| [Fine-Tuning BERT using Hugging Face Transformers](https:\u002F\u002Flearnopencv.com\u002Ffine-tuning-bert) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-Tuning-BERT-using-Hugging-Face-Transformers) |\n| [YOLO-NAS Pose](https:\u002F\u002Flearnopencv.com\u002Fyolo-nas-pose) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLO-NAS-Pose) |\n| [BERT: Bidirectional Encoder Representations from Transformers](https:\u002F\u002Flearnopencv.com\u002Fbert-bidirectional-encoder-representations-from-transformers\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FBERT-Bidirectional-Encoder-Representations-from-Transformers) |\n| [Comparing KerasCV YOLOv8 Models on the Global Wheat Data 2020](https:\u002F\u002Flearnopencv.com\u002Fcomparing-kerascv-yolov8-models\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FComparing-KerasCV-YOLOv8-Models-on-the-Global-Wheat-Data-2020) |\n| [Top 5 AI papers of September 2023](https:\u002F\u002Flearnopencv.com\u002Ftop-5-ai-papers-of-september-2023\u002F) | |\n| [Empowering Drivers: The Rise and Role of Advanced Driver Assistance Systems](https:\u002F\u002Flearnopencv.com\u002Fadvanced-driver-assistance-systems\u002F) | |\n| [Semantic Segmentation using KerasCV DeepLabv3+](https:\u002F\u002Flearnopencv.com\u002Fkerascv-deeplabv3-plus-semantic-segmentation\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FSemantic-Segmentation-using-KerasCV-with-DeepLabv3-Plus) |\n| [Object Detection using KerasCV YOLOv8](https:\u002F\u002Flearnopencv.com\u002Fobject-detection-using-kerascv-yolov8\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FObject-Detection-using-KerasCV-YOLOv8) |\n| [Fine-tuning YOLOv8 Pose Models for Animal Pose Estimation](https:\u002F\u002Flearnopencv.com\u002Fanimal-pose-estimation\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-tuning-YOLOv8-Pose-Models-for-Animal-Pose-Estimation) |\n| [Top 5 AI papers of August 2023](https:\u002F\u002Flearnopencv.com\u002Ftop-5-ai-papers-of-august-2023\u002F) | |\n| [Fine Tuning TrOCR - Training TrOCR to Recognize Curved Text](https:\u002F\u002Flearnopencv.com\u002Ffine-tuning-trocr-training-trocr-to-recognize-curved-text\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-Tuning-TrOCR) |\n| [TrOCR - Getting Started with Transformer Based OCR](https:\u002F\u002Flearnopencv.com\u002Ftrocr-getting-started-with-transformer-based-ocr\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FTrOCR-Getting-Started-with-Transformer-Based-OCR) |\n| [Facial Emotion Recognition](https:\u002F\u002Flearnopencv.com\u002Ffacial-emotion-recognition\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFacial-Emotion-Recognition) |\n| [Object Keypoint Similarity in Keypoint Detection](https:\u002F\u002Flearnopencv.com\u002Fobject-keypoint-similarity\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FObject-Keypoint-Similarity-in-Keypoint-Detection) |\n| [Real Time Deep SORT with Torchvision Detectors](https:\u002F\u002Flearnopencv.com\u002Freal-time-deep-sort-with-torchvision-detectors\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FReal_Time_Deep_SORT_using_Torchvision_Detectors) |\n| [Top 5 AI papers of July 2023](https:\u002F\u002Flearnopencv.com\u002Ftop-5-ai-papers-of-july-2023\u002F) | |\n| [Medical Image Segmentation](https:\u002F\u002Flearnopencv.com\u002Fmedical-image-segmentation\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FMedical-Image-Segmentation-Using-HuggingFace-&-PyTorch) |\n| [Weighted Boxes Fusion in Object Detection: A Comparison with Non-Maximum Suppression](https:\u002F\u002Flearnopencv.com\u002Fweighted-boxes-fusion\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FWeighted-Boxes-Fusion-in-Object-Detection) |\n| [Medical Multi-label Classification with PyTorch & Lightning](https:\u002F\u002Flearnopencv.com\u002Fmedical-multi-label\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FMedical_Multi-label_Classification_with_PyTorch_&_Lightning) |\n| [Getting Started with PaddlePaddle: Exploring Object Detection, Segmentation, and Keypoints](https:\u002F\u002Flearnopencv.com\u002Fpaddlepaddle\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FIntroduction-to-PaddlePaddle) |\n| [Drone Programming With Computer Vision A Beginners Guide](https:\u002F\u002Flearnopencv.com\u002Fdrone-programming-with-computer-vision\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDrone-Programming-With-Computer-Vision-A-Beginners-Guide) |\n| [How to Build a Pip Installable Package & Upload to PyPi](https:\u002F\u002Flearnopencv.com\u002Fbuilding-pip-installable-package-pypi\u002F) | |\n| [IoU Loss Functions for Faster & More Accurate Object Detection](https:\u002F\u002Flearnopencv.com\u002Fiou-loss-functions-object-detection\u002F) | |\n| [Exploring Slicing Aided Hyper Inference for Small Object Detection](https:\u002F\u002Flearnopencv.com\u002Fslicing-aided-hyper-inference\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FExploring-Slicing-Aided-Hyper-Inference) |\n| [Advancements in Face Recognition Models, Toolkit and Datasets](https:\u002F\u002Flearnopencv.com\u002Fface-recognition-models\u002F) | |\n| [Train YOLO NAS on Custom Dataset](https:\u002F\u002Flearnopencv.com\u002Ftrain-yolo-nas-on-custom-dataset\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FTrain-YOLO-NAS-on-Custom-Dataset) |\n| [Train YOLOv8 Instance Segmentation on Custom Data](https:\u002F\u002Flearnopencv.com\u002Ftrain-yolov8-instance-segmentation\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FTrain-YOLOv8-Instance-Segmentation-on-Custom-Data) |\n| [YOLO-NAS: New Object Detection Model Beats YOLOv6 & YOLOv8](https:\u002F\u002Flearnopencv.com\u002Fyolo-nas\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLO-NAS_Introduction) |\n| [Segment Anything – A Foundation Model for Image Segmentation](https:\u002F\u002Flearnopencv.com\u002Fsegment-anything\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FSegment-Anything-A-Foundation-Model-for-Image-Segmentation) |\n|[Build a Video to Slides Converter Application using the Power of Background Estimation and Frame Differencing in OpenCV](https:\u002F\u002Flearnopencv.com\u002Fvideo-to-slides-converter-using-background-subtraction\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FBuild-a-Video-to-Slides-Converter-Application-using-the-Power-of-Background-Estimation-and-Frame-Differencing-in-OpenCV)|\n|[A Closer Look at CVAT: Perfecting Your Annotations](https:\u002F\u002Flearnopencv.com\u002Fa-closer-look-at-cvat-perfecting-your-annotations\u002F)|[YouTube](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=yxX_0-zr-2U&list=PLfYPZalDvZDLvFhjuflhrxk_lLplXUqqB)|\n| [ControlNet - Achieving Superior Image Generation Results](https:\u002F\u002Flearnopencv.com\u002Fcontrolnet\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FControlNet-Achieving-Superior-Image-Generation-Results) |\n| [InstructPix2Pix - Edit Images With Prompts](https:\u002F\u002Flearnopencv.com\u002Finstructpix2pix\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FInstructPix2Pix-Edit-Images-With-Prompts) |\n| [NVIDIA Spring GTC 2023 Day 4: Ending on a High Note with Top Moments from the Finale!](https:\u002F\u002Flearnopencv.com\u002Fnvidia-spring-gtc-2023-day-4\u002F) | |\n| [NVIDIA Spring GTC 2023 Day 3: Digging deeper into Deep Learning, Semiconductors & more!](https:\u002F\u002Flearnopencv.com\u002Fnvidia-spring-gtc-2023-day-3-digging-deeper-into-deep-learning-semiconductors-more\u002F) | |\n| [NVIDIA Spring GTC 2023 Day 2: Jensen’s keynote & the iPhone moment of AI is here!](https:\u002F\u002Flearnopencv.com\u002Fnvidia-spring-gtc-2023-day-2-jensens-keynote-the-iphone-moment-of-ai-is-here\u002F) | |\n| [NVIDIA Spring GTC 2023 Day 1: Welcome to the future!](https:\u002F\u002Flearnopencv.com\u002Fnvidia-spring-gtc-2023-day-1-highlights-welcome-to-the-future\u002F) | |\n| [NVIDIA GTC Spring 2023 Curtain Raiser](https:\u002F\u002Flearnopencv.com\u002Fnvidia-gtc-spring-2023-curtain-raiser\u002F) | |\n| [Stable Diffusion - A New Paradigm in Generative AI](https:\u002F\u002Flearnopencv.com\u002Fstable-diffusion-generative-ai\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FStable-Diffusion-A-New-Paradigm-in-Generative-AI) |\n| [OpenCV Face Recognition – Does Face Recognition Work on AI-Generated Images?](https:\u002F\u002Flearnopencv.com\u002Fopencv-face-recognition-api\u002F) | |\n|[An In-Depth Guide to Denoising Diffusion Probabilistic Models – From Theory to Implementation](https:\u002F\u002Flearnopencv.com\u002Fdenoising-diffusion-probabilistic-models\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FGuide-to-training-DDPMs-from-Scratch)|\n|[From Pixels to Paintings: The Rise of Midjourney AI Art](https:\u002F\u002Flearnopencv.com\u002Frise-of-midjourney-ai-art\u002F)| |\n|[Mastering DALL·E 2: A Breakthrough in AI Art Generation](https:\u002F\u002Flearnopencv.com\u002Fmastering-dall-e-2\u002F)| |\n|[Top 10 AI Art Generation Tools using Diffusion Models](https:\u002F\u002Flearnopencv.com\u002Fai-art-generation-tools\u002F)| |\n|[The Future of Image Recognition is Here: PyTorch Vision Transformer](https:\u002F\u002Flearnopencv.com\u002Fthe-future-of-image-recognition-is-here-pytorch-vision-transformer\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FVision_Transformer_PyTorch)|\n|[Understanding Attention Mechanism in Transformer Neural Networks](https:\u002F\u002Flearnopencv.com\u002Fattention-mechanism-in-transformer-neural-networks\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FAttention_Mechanism_Introduction)|\n| [Deploying a Deep Learning Model using Hugging Face Spaces and Gradio](https:\u002F\u002Flearnopencv.com\u002Fdeploy-deep-learning-model-huggingface-spaces\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDeploying-a-Deep-Learning-Model-using-Hugging-Face-Spaces-and-Gradio) |\n| [Train YOLOv8 on Custom Dataset – A Complete Tutorial](https:\u002F\u002Flearnopencv.com\u002Ftrain-yolov8-on-custom-dataset\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FTrain-YOLOv8-on-Custom-Dataset-A-Complete-Tutorial) |\n| [Introduction to Diffusion Models for Image Generation](https:\u002F\u002Flearnopencv.com\u002Fimage-generation-using-diffusion-models\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FIntroduction-to-Diffusion-Models-for-Image-Generation) |\n| [Building An Automated Image Annotation Tool: PyOpenAnnotate](https:\u002F\u002Flearnopencv.com\u002Fbuilding-automated-image-annotation-tool-pyopenannotate\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FBuilding-An-Automated-Image-Annotation-Tool-PyOpenAnnotate\u002F) |\n| [Ultralytics YOLOv8: State-of-the-Art YOLO Models](https:\u002F\u002Flearnopencv.com\u002Fultralytics-yolov8\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FUltralytics-YOLOv8-State-of-the-Art-YOLO-Models) |\n| [Getting Started with YOLOv5 Instance Segmentation](https:\u002F\u002Flearnopencv.com\u002Fgetting-started-with-yolov5-instance-segmentation\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FGetting-Started-with-YOLOv5-Instance-Segmentation) |\n|[The Ultimate Guide To DeepLabv3 - With PyTorch Inference](https:\u002F\u002Flearnopencv.com\u002Fdeeplabv3-ultimate-guide\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FThe-ultimate-guide-to-deeplabv3)|\n|[AI Fitness Trainer using MediaPipe: Squats Analysis](https:\u002F\u002Flearnopencv.com\u002Fai-fitness-trainer-using-mediapipe\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FAI-Fitness-Trainer-Using-MediaPipe-Analyzing-Squats)|\n|[YoloR - Paper Explanation & Inference -An In-Depth Analysis](https:\u002F\u002Flearnopencv.com\u002Fyolor-paper-explanation-inference-an-in-depth-analysis\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYoloR-paper-explanation-analysis)|\n|[Roadmap To an Automated Image Annotation Tool Using Python](https:\u002F\u002Flearnopencv.com\u002Fautomated-image-annotation-tool-using-opencv-python\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FRoadmap-To-an-Automated-Image-Annotation-Tool-Using-Python)|\n|[Performance Comparison of YOLO Object Detection Models – An Intensive Study](https:\u002F\u002Flearnopencv.com\u002Fperformance-comparison-of-yolo-models\u002F)||\n|[FCOS - Anchor Free Object Detection Explained](https:\u002F\u002Flearnopencv.com\u002Ffcos-anchor-free-object-detection-explained\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFCOS-Inference-using-PyTorch)|\n| [YOLOv6 Custom Dataset Training – Underwater Trash Detection](https:\u002F\u002Flearnopencv.com\u002Fyolov6-custom-dataset-training\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLOv6-Custom-Dataset-Training-Underwater-Trash-Detection) |\n|[What is EXIF Data in Images?](https:\u002F\u002Fwww.learnopencv.com\u002Fwhat-is-exif-data-in-images\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FWhat-is-EXIF-Data-in-Images)|\n|[t-SNE: T-Distributed Stochastic Neighbor Embedding Explained](https:\u002F\u002Flearnopencv.com\u002Ft-sne-t-distributed-stochastic-neighbor-embedding-explained\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Ft-SNE-with-Tensorboard)|\n|[CenterNet: Objects as Points – Anchor-free Object Detection Explained](https:\u002F\u002Flearnopencv.com\u002Fcenternet-anchor-free-object-detection-explained\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fcenternet-with-tf-hub)|\n|[YOLOv7 Pose vs MediaPipe in Human Pose Estimation](https:\u002F\u002Flearnopencv.com\u002Fyolov7-pose-vs-mediapipe-in-human-pose-estimation\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLOv7-Pose-vs-MediaPipe-in-Human-Pose-Estimation)|\n|[YOLOv6 Object Detection – Paper Explanation and Inference](https:\u002F\u002Flearnopencv.com\u002Fyolov6-object-detection\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLOv6-Object-Detection-Paper-Explanation-and-Inference)|\n|[YOLOX Object Detector Paper Explanation and Custom Training](https:\u002F\u002Flearnopencv.com\u002Fyolox-object-detector-paper-explanation-and-custom-training\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLOX-Object-Detection-Paper-Explanation-and-Custom-Training)|\n|[Driver Drowsiness Detection Using Mediapipe In Python](https:\u002F\u002Flearnopencv.com\u002Fdriver-drowsiness-detection-using-mediapipe-in-python\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDriver-Drowsiness-detection-using-Mediapipe-in-Python)|\n|[GTC 2022 Big Bang AI announcements: Everything you need to know](https:\u002F\u002Flearnopencv.com\u002Fgtc-2022-big-bang-ai-announcements-everything-you-need-to-know\u002F)||\n|[NVIDIA GTC 2022 : The most important AI event this Fall](https:\u002F\u002Flearnopencv.com\u002Fnvidia-gtc-2022-the-most-important-ai-event-this-fall\u002F)||\n|[Object Tracking and Reidentification with FairMOT](https:\u002F\u002Flearnopencv.com\u002Fobject-tracking-and-reidentification-with-fairmot\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FObject-Tracking-and-Reidentification-with-FairMOT) |\n|[What is Face Detection? – The Ultimate Guide for 2022](https:\u002F\u002Flearnopencv.com\u002Fwhat-is-face-detection-the-ultimate-guide\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFace-Detection-Ultimate-Guide) |\n|[Document Scanner: Custom Semantic Segmentation using PyTorch-DeepLabV3](https:\u002F\u002Flearnopencv.com\u002Fcustom-document-segmentation-using-deep-learning\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDocument-Scanner-Custom-Semantic-Segmentation-using-PyTorch-DeepLabV3)|\n|[Fine Tuning YOLOv7 on Custom Dataset](https:\u002F\u002Flearnopencv.com\u002Ffine-tuning-yolov7-on-custom-dataset\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFine-Tuning-YOLOv7)|\n|[Center Stage for Zoom Calls using MediaPipe](https:\u002F\u002Flearnopencv.com\u002FCenter-Stage-for-zoom-call-using-mediapipe\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FCenterStage)|\n|[Mean Average Precision (mAP) in Object Detection](https:\u002F\u002Flearnopencv.com\u002Fmean-average-precision-map-object-detection-model-evaluation-metric\u002F)||\n|[YOLOv7 Object Detection Paper Explanation and Inference](https:\u002F\u002Flearnopencv.com\u002Fyolov7-object-detection-paper-explanation-and-inference\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FYOLOv7-Object-Detection-Paper-Explanation-and-Inference)|\n|[Pothole Detection using YOLOv4 and Darknet](https:\u002F\u002Flearnopencv.com\u002Fpothole-detection-using-yolov4-and-darknet\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FPothole-Detection-using-YOLOv4-and-Darknet)|\n|[Automatic Document Scanner using OpenCV](https:\u002F\u002Flearnopencv.com\u002Fautomatic-document-scanner-using-opencv\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FAutomatic-Document-Scanner)|\n|[Demystifying GPU architectures for deep learning: Part 2](https:\u002F\u002Flearnopencv.com\u002Fdemystifying-gpu-architectures-for-deep-learning-part-2\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fgpu_arch_and_CUDA)|\n|[Demystifying GPU Architectures For Deep Learning](https:\u002F\u002Flearnopencv.com\u002Fdemystifying-gpu-architectures-for-deep-learning\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fgpu_arch_and_CUDA)|\n|[Intersection-over-Union(IoU)-in-Object-Detection-and-Segmentation](https:\u002F\u002Flearnopencv.com\u002Fintersection-over-unioniou-in-object-detection-and-segmentation\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FIntersection-over-Union-IoU-in-Object-Detection-and-Segmentation)|\n|[Understanding Multiple Object Tracking using DeepSORT](https:\u002F\u002Flearnopencv.com\u002Funderstanding-multiple-object-tracking-using-deepsort\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FUnderstanding-Multiple-Object-Tracking-using-DeepSORT)|\n|[Optical Character Recognition using PaddleOCR](https:\u002F\u002Flearnopencv.com\u002Foptical-character-recognition-using-paddleocr\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FOptical-Character-Recognition-using-PaddleOCR)|\n|[Gesture Control in Zoom Call using Mediapipe](https:\u002F\u002Flearnopencv.com\u002Fgesture-control-in-zoom-call-using-mediapipe\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fzoom-gestures)|\n|[A Deep Dive into Tensorflow Model Optimization](https:\u002F\u002Flearnopencv.com\u002Fdeep-dive-into-tensorflow-model-optimization-toolkit\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FA-Deep-Dive-into-Tensorflow-Model-Optimization)|\n|[DepthAI Pipeline Overview: Creating a Complex Pipeline](https:\u002F\u002Flearnopencv.com\u002Fdepthai-pipeline-overview-creating-a-complex-pipeline\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FOAK-DepthAi-Pipeline-Overview)|\n|[TensorFlow Lite Model Maker: Create Models for On-Device Machine Learning](https:\u002F\u002Flearnopencv.com\u002Ftensorflow-lite-model-maker-create-models-for-on-device-machine-learning\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FTensorflow-Lite-Model-Maker-Create-Models-for-On-Device-ML)|\n|[TensorFlow Lite: Model Optimization for On Device Machine Learning](https:\u002F\u002Flearnopencv.com\u002Ftensorflow-lite-model-optimization-for-on-device-machine-learning)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FTensorFlow-Lite-Model-Optimization-for-On-Device-MachineLearning)|\n|[Object detection with depth measurement using pre-trained models with OAK-D](https:\u002F\u002Flearnopencv.com\u002Fobject-detection-with-depth-measurement-with-oak-d\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FOAK-Object-Detection-with-Depth)|\n|[Custom Object Detection Training using YOLOv5](https:\u002F\u002Flearnopencv.com\u002Fcustom-object-detection-training-using-yolov5\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FCustom-Object-Detection-Training-using-YOLOv5)|\n|[Object Detection using Yolov5 and OpenCV DNN (C++\u002FPython)](https:\u002F\u002Flearnopencv.com\u002Fobject-detection-using-yolov5-and-opencv-dnn-in-c-and-python\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FObject-Detection-using-YOLOv5-and-OpenCV-DNN-in-CPP-and-Python)|\n|[Create Snapchat\u002FInstagram filters using Mediapipe](https:\u002F\u002Flearnopencv.com\u002Fcreate-snapchat-instagram-filters-using-mediapipe\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FCreate-AR-filters-using-Mediapipe)|\n|[AUTOSAR C++ compliant deep learning inference with TensorRT](https:\u002F\u002Flearnopencv.com\u002Fautosar-c-compliant-deep-learning-inference-with-tensorrt\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Findustrial_cv_TensorRT_cpp)|\n|[NVIDIA GTC 2022 Day 4 Highlights: Meet the new Jetson Orin](https:\u002F\u002Flearnopencv.com\u002Fnvidia-gtc-2022-day-4-highlights-meet-the-new-jetson-orin\u002F)||\n|[NVIDIA GTC 2022 Day 3 Highlights: Deep Dive into Hopper architecture](https:\u002F\u002Flearnopencv.com\u002Fnvidia-gtc-2022-day-3-highlights-deep-dive-into-hopper-architecture\u002F)||\n|[NVIDIA GTC 2022 Day 2 Highlights: Jensen’s Keynote](https:\u002F\u002Flearnopencv.com\u002Fnvidia-gtc-2022-day-2-highlights\u002F)||\n|[NVIDIA GTC 2022 Day 1 Highlights: Brilliant Start](https:\u002F\u002Flearnopencv.com\u002Fgtc-day-1-highlights\u002F)||\n|[Automatic License Plate Recognition using Python](https:\u002F\u002Flearnopencv.com\u002Fautomatic-license-plate-recognition-using-deep-learning\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FALPR)|\n|[Building a Poor Body Posture Detection and Alert System using MediaPipe](https:\u002F\u002Flearnopencv.com\u002Fbuilding-a-body-posture-analysis-system-using-mediapipe\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FPosture-analysis-system-using-MediaPipe-Pose)|\n|[Introduction to MediaPipe](https:\u002F\u002Flearnopencv.com\u002Fintroduction-to-mediapipe\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FIntroduction-to-MediaPipe)|\n|[Disparity Estimation using Deep Learning](https:\u002F\u002Flearnopencv.com\u002Fdisparity-estimation-using-deep-learning\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDisparity-Estimation-Using-Deep-Learning)|\n|[How to build Chrome Dino game bot using OpenCV Feature Matching](https:\u002F\u002Flearnopencv.com\u002Fhow-to-build-chrome-dino-game-bot-using-opencv-feature-matching\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FChrome-Dino-Bot-using-OpenCV-feature-matching)|\n|[Top 10 Sources to Find Computer Vision and AI Models](https:\u002F\u002Flearnopencv.com\u002Ftop-10-sources-to-find-computer-vision-and-ai-models\u002F)||\n|[Multi-Attribute and Graph-based Object Detection](https:\u002F\u002Flearnopencv.com\u002Fmulti-attribute-and-graph-based-object-detection\u002F)||\n|[Plastic Waste Detection with Deep Learning](https:\u002F\u002Flearnopencv.com\u002Fplastic-waste-detection-with-deep-learning\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FPlastic-Waste-Detection-with-Deep-Learning)|\n|[Ensemble Deep Learning-based Defect Classification and Detection in SEM Images](https:\u002F\u002Flearnopencv.com\u002Fensemble-deep-learning-based-defect-classification-and-detection-in-sem-images\u002F)||\n|[Building Industrial embedded deep learning inference pipelines with TensorRT](https:\u002F\u002Flearnopencv.com\u002Fbuilding-industrial-embedded-deep-learning-inference-pipelines-with-tensorrt\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Findustrial_cv_TensorRT_python)|\n|[Transfer Learning for Medical Images](https:\u002F\u002Flearnopencv.com\u002Ftransfer-learning-for-medical-images\u002F)||\n|[Stereo Vision and Depth Estimation using OpenCV AI Kit](https:\u002F\u002Flearnopencv.com\u002Fstereo-vision-and-depth-estimation-using-opencv-ai-kit\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Foak-getting-started)|\n|[Introduction to OpenCV AI Kit and DepthAI](https:\u002F\u002Flearnopencv.com\u002Fintroduction-to-opencv-ai-kit-and-depthai\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Foak-getting-started)|\n|[WeChat QR Code Scanner in OpenCV](https:\u002F\u002Flearnopencv.com\u002Fwechat-qr-code-scanner-in-opencv)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FWeChat-QRCode-Scanner-OpenCV)|\n|[AI behind the Diwali 2021 ‘Not just a Cadbury ad’](https:\u002F\u002Flearnopencv.com\u002Fai-behind-the-diwali-2021-not-just-a-cadbury-ad\u002F)| |\n|[Model Selection and Benchmarking with Modelplace.AI](https:\u002F\u002Flearnopencv.com\u002Fmodel-selection-and-benchmarking-with-modelplace-ai\u002F)|[Model Zoo](https:\u002F\u002Fmodelplace.ai\u002F)|\n|[Real-time style transfer in a zoom meeting](https:\u002F\u002Flearnopencv.com\u002Freal-time-style-transfer-in-a-zoom-meeting\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fstyle-transfer-zoom)|\n| [Introduction to OpenVino Deep Learning Workbench](https:\u002F\u002Flearnopencv.com\u002Fintroduction-to-openvino-deep-learning-workbench\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FIntroduction-to-OpenVino-Deep-Learning-Workbench) |\n| [Running OpenVino Models on Intel Integrated GPU](https:\u002F\u002Flearnopencv.com\u002Frunning-openvino-models-on-intel-integrated-gpu\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FRunning-OpenVino-Models-on-Intel-Integrated-GPU) |\n|[Post Training Quantization with OpenVino Toolkit](https:\u002F\u002Flearnopencv.com\u002Fpost-training-quantization-with-openvino-toolkit\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FPost-Training-Quantization-with-OpenVino-Toolkit)|\n|[Introduction to Intel OpenVINO Toolkit](https:\u002F\u002Flearnopencv.com\u002Fintroduction-to-intel-openvino-toolkit\u002F)||\n|[Human Action Recognition using Detectron2 and LSTM](https:\u002F\u002Flearnopencv.com\u002Fhuman-action-recognition-using-detectron2-and-lstm\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FHuman-Action-Recognition-Using-Detectron2-And-Lstm)|\n|[Pix2Pix:Image-to-Image Translation in PyTorch & TensorFlow](https:\u002F\u002Flearnopencv.com\u002Fpaired-image-to-image-translation-pix2pix\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FImage-to-Image-Translation-with-GAN)|\n|[Conditional GAN (cGAN) in PyTorch and TensorFlow](https:\u002F\u002Flearnopencv.com\u002Fconditional-gan-cgan-in-pytorch-and-tensorflow\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FConditional-GAN-PyTorch-TensorFlow)|\n|[Deep Convolutional GAN in PyTorch and TensorFlow](https:\u002F\u002Flearnopencv.com\u002Fdeep-convolutional-gan-in-pytorch-and-tensorflow\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDeep-Convolutional-GAN)|\n|[Introduction to Generative Adversarial Networks (GANs)](https:\u002F\u002Flearnopencv.com\u002Fintroduction-to-generative-adversarial-networks\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FIntro-to-Generative-Adversarial-Network)|\n|[Human Pose Estimation using Keypoint RCNN in PyTorch](https:\u002F\u002Flearnopencv.com\u002Fhuman-pose-estimation-using-keypoint-rcnn-in-pytorch\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FPyTorch-Keypoint-RCNN)|\n|[Non Maximum Suppression: Theory and Implementation in PyTorch](https:\u002F\u002Flearnopencv.com\u002Fnon-maximum-suppression-theory-and-implementation-in-pytorch)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FNon-Maximum-Suppression)|\n|[MRNet – The Multi-Task Approach](https:\u002F\u002Flearnopencv.com\u002Fmrnet-multitask-approach\u002F)| [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FMRnet-MultiTask-Approach) |\n|[Generative and Discriminative Models](https:\u002F\u002Flearnopencv.com\u002Fgenerative-and-discriminative-models\u002F)| |\n|[Playing Chrome's T-Rex Game with Facial Gestures](https:\u002F\u002Flearnopencv.com\u002Fplaying-chromes-t-rex-game-with-facial-gestures\u002F)| [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FPlaying-Chrome-TRex-Game-with-Facial-Gestures) |\n|[Variational Autoencoder in TensorFlow](https:\u002F\u002Flearnopencv.com\u002Fvariational-autoencoder-in-tensorflow\u002F)| [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FVariational-Autoencoder-TensorFlow) |\n|[Autoencoder in TensorFlow 2: Beginner’s Guide](https:\u002F\u002Flearnopencv.com\u002Fautoencoder-in-tensorflow-2-beginners-guide\u002F)| [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FAutoencoder-in-TensorFlow) |\n|[Deep Learning with OpenCV DNN Module: A Definitive Guide](https:\u002F\u002Flearnopencv.com\u002Fdeep-learning-with-opencvs-dnn-module-a-definitive-guide\u002F)| [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDeep-Learning-with-OpenCV-DNN-Module) |\n|[Depth perception using stereo camera (Python\u002FC++)](https:\u002F\u002Flearnopencv.com\u002Fdepth-perception-using-stereo-camera-python-c\u002F)| [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDepth-Perception-Using-Stereo-Camera) |\n|[Contour Detection using OpenCV (Python\u002FC++)](https:\u002F\u002Flearnopencv.com\u002Fcontour-detection-using-opencv-python-c\u002F)| [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FContour-Detection-using-OpenCV) |\n|[Super Resolution in OpenCV](https:\u002F\u002Flearnopencv.com\u002Fsuper-resolution-in-opencv\u002F)| [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Fblob\u002Fmaster\u002FSuper-Resolution-in-OpenCV) |\n|[Improving Illumination in Night Time Images](https:\u002F\u002Flearnopencv.com\u002Fimproving-illumination-in-night-time-images\u002F)| [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FImproving-Illumination-in-Night-Time-Images) |\n|[Video Classification and Human Activity Recognition](https:\u002F\u002Flearnopencv.com\u002Fintroduction-to-video-classification-and-human-activity-recognition\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fvideo-classification-and-human-activity-recognition) |\n|[How to use OpenCV DNN Module with Nvidia GPU on Windows](https:\u002F\u002Flearnopencv.com\u002Fhow-to-use-opencv-dnn-module-with-nvidia-gpu-on-windows) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FOpenCV-dnn-gpu-support-Windows) |\n|[How to use OpenCV DNN Module with NVIDIA GPUs](https:\u002F\u002Flearnopencv.com\u002Fopencv-dnn-with-gpu-support\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FOpenCV-dnn-gpu-support-Linux) |\n|[Code OpenCV in Visual Studio](https:\u002F\u002Flearnopencv.com\u002Fcode-opencv-in-visual-studio\u002F) | |\n|[Install OpenCV on Windows – C++ \u002F Python](https:\u002F\u002Flearnopencv.com\u002Finstall-opencv-on-windows\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FInstall-OpenCV-Windows-exe) |\n|[Face Recognition with ArcFace](https:\u002F\u002Fwww.learnopencv.com\u002Fface-recognition-with-arcface\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFace-Recognition-with-ArcFace)|\n|[Background Subtraction with OpenCV and BGS Libraries](https:\u002F\u002Fwww.learnopencv.com\u002Fbackground-subtraction-with-opencv-and-bgs-libraries\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FBackground-Subtraction) |\n|[RAFT: Optical Flow estimation using Deep Learning](https:\u002F\u002Flearnopencv.com\u002Foptical-flow-using-deep-learning-raft\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FOptical-Flow-Estimation-using-Deep-Learning-RAFT)|\n|[Making A Low-Cost Stereo Camera Using OpenCV](https:\u002F\u002Fwww.learnopencv.com\u002Fmaking-a-low-cost-stereo-camera-using-opencv\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fstereo-camera)|\n|[Optical Flow in OpenCV (C++\u002FPython)](https:\u002F\u002Fwww.learnopencv.com\u002Foptical-flow-in-opencv)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FOptical-Flow-in-OpenCV)|\n|[Introduction to Epipolar Geometry and Stereo Vision](https:\u002F\u002Fwww.learnopencv.com\u002Fintroduction-to-epipolar-geometry-and-stereo-vision\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FEpipolarGeometryAndStereoVision)|\n|[Classification With Localization: Convert any keras Classifier to a Detector](https:\u002F\u002Fwww.learnopencv.com\u002Fclassification-with-localization\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FClassification-with-localization-convert-any-keras-classifier-into-a-detector\u002FREADME.md) |\n|[Photoshop Filters in OpenCV](https:\u002F\u002Fwww.learnopencv.com\u002Fphotoshop-filters-in-opencv\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FPhotoshop-Filters-in-OpenCV)|\n|[Tetris Game using OpenCV Python](https:\u002F\u002Fwww.learnopencv.com\u002Ftetris-with-opencv-python)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FTetris)|\n|[Image Classification with OpenCV for Android](https:\u002F\u002Fwww.learnopencv.com\u002Fimage-classification-with-opencv-for-android\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDNN-OpenCV-Classification-Android) |\n|[Image Classification with OpenCV Java](https:\u002F\u002Fwww.learnopencv.com\u002Fimage-classification-with-opencv-java)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FDNN-OpenCV-Classification-with-Java) |\n|[PyTorch to Tensorflow Model Conversion](https:\u002F\u002Fwww.learnopencv.com\u002Fpytorch-to-tensorflow-model-conversion\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FPyTorch-to-TensorFlow-Model-Conversion) |\n|[Snake Game with OpenCV Python](https:\u002F\u002Fwww.learnopencv.com\u002Fsnake-game-with-opencv-python\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FSnakeGame) |\n|[Stanford MRNet Challenge: Classifying Knee MRIs](https:\u002F\u002Fwww.learnopencv.com\u002Fstanford-mrnet-challenge-classifying-knee-mris\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FMRNet-Single-Model) |\n|[Experiment Logging with TensorBoard and wandb](https:\u002F\u002Fwww.learnopencv.com\u002Fexperiment-logging-with-tensorboard-and-wandb)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FPyTorch-Vision-Experiment-Logging) |\n|[Understanding Lens Distortion](https:\u002F\u002Fwww.learnopencv.com\u002Funderstanding-lens-distortion\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FUnderstandingLensDistortion) |\n|[Image Matting with state-of-the-art Method “F, B, Alpha Matting”](https:\u002F\u002Fwww.learnopencv.com\u002Fimage-matting-with-state-of-the-art-method-f-b-alpha-matting\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFBAMatting) |\n|[Bag Of Tricks For Image Classification - Let's check if it is working or not](https:\u002F\u002Fwww.learnopencv.com\u002Fbag-of-tricks-for-image-classification-lets-check-if-it-is-working-or-not\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FBag-Of-Tricks-For-Image-Classification) |\n|[Getting Started with OpenCV CUDA Module](https:\u002F\u002Fwww.learnopencv.com\u002Fgetting-started-opencv-cuda-module\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FGetting-Started-OpenCV-CUDA-Module) |\n|[Training a Custom Object Detector with DLIB & Making Gesture Controlled Applications](https:\u002F\u002Fwww.learnopencv.com\u002Ftraining-a-custom-object-detector-with-dlib-making-gesture-controlled-applications\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FTraining_a_custom_hand_detector_with_dlib) |\n|[How To Run Inference Using TensorRT C++ API](https:\u002F\u002Fwww.learnopencv.com\u002Fhow-to-run-inference-using-tensorrt-c-api\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FPyTorch-ONNX-TensorRT-CPP) |\n|[Using Facial Landmarks for Overlaying Faces with Medical Masks](https:\u002F\u002Fwww.learnopencv.com\u002Fusing-facial-landmarks-for-overlaying-faces-with-masks\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FFaceMaskOverlay) |\n|[Tensorboard with PyTorch Lightning](https:\u002F\u002Fwww.learnopencv.com\u002Ftensorboard-with-pytorch-lightning)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FTensorBoard-With-Pytorch-Lightning) |\n|[Otsu's Thresholding with OpenCV](https:\u002F\u002Fwww.learnopencv.com\u002Fotsu-thresholding-with-opencv\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002Fotsu-method) |\n|[PyTorch-to-CoreML-model-conversion](https:\u002F\u002Fwww.learnopencv.com\u002Fpytorch-to-coreml-model-conversion\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FPyTorch-to-CoreML-model-conversion) |\n|[Playing Rock, Paper, Scissors with AI](https:\u002F\u002Fwww.learnopencv.com\u002Fplaying-rock-paper-scissors-with-ai\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FPlaying-rock-paper-scissors-with-AI) |\n|[CNN Receptive Field Computation Using Backprop with TensorFlow](https:\u002F\u002Fwww.learnopencv.com\u002Fcnn-receptive-field-computation-using-backprop-with-tensorflow\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FTensorFlow-Receptive-Field-With-Backprop)|\n|[CNN Fully Convolutional Image Classification with TensorFlow](https:\u002F\u002Fwww.learnopencv.com\u002Fcnn-fully-convolutional-image-classification-with-tensorflow) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FTensorFlow-Fully-Convolutional-Image-Classification) |\n|[How to convert a model from PyTorch to TensorRT and speed up inference](https:\u002F\u002Fwww.learnopencv.com\u002Fhow-to-convert-a-model-from-pytorch-to-tensorrt-and-speed-up-inference\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FPyTorch-ONNX-TensorRT) |\n|[Efficient image loading](https:\u002F\u002Fwww.learnopencv.com\u002Fefficient-image-loading\u002F)|[Code](https:\u002F\u002Fgithub.com\u002Fspmallick\u002Flearnopencv\u002Ftree\u002Fmaster\u002FEfficient-image-loading) |\n|[Gra","LearnOpenCV 是一个专注于计算机视觉、深度学习和人工智能研究的文章及代码示例库。该项目通过 C++ 和 Python 语言提供了一系列基于 OpenCV 的实用教程与代码示例，涵盖了从基础的图像处理到高级的物体检测、实例分割等技术。其核心功能包括 YOLO 系列的目标检测与姿态估计、实时多目标跟踪以及面部模糊处理等。此外，还涉及了边缘计算环境下的模型部署等内容。非常适合希望深入了解并实践 OpenCV 应用的开发者、研究人员以及对计算机视觉感兴趣的初学者使用。",2,"2026-06-11 03:23:33","top_topic"]