Referecnce
- Convert PascalVOC Annotations to YOLO
- Object Detection Algorithm — YOLO v5 Architecture
- Explaining-Yolov4-a-One-Stage-Detector
- YOLOv4
- Reading: UNet 3+ — A Full-Scale Connected UNet (Medical Image Segmentation)
- No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objects
- Find the best Reinforcement Learning jobs
- Practical_RL
- Best DL Tutorial and refreshment
- Full Stack Deep Learning - Course 2022
- YOLOV-updated releases classification
- An improved millisecond mobile backbone
- introducing-the-playtorch-app rapidly create mobile AI experiences
- Deep Clustering for Mars Rover image datasets
- Mars-Search-Robot
- cuda-error-out-of-memory
- Top-10-Computer-Vision-papers-2020
- Computer Vision Foundations Open Access
- Instance Embedding: Segmentation Without Proposals
- The Why and the How of Deep Metric Learning
- Flashlight: Fast and flexible machine learning in C++
- Weekly ML papers
- The Why and the How of Deep Metric Learning.
- Global Context Networks (GCNet) Explained
- FCOS: Fully Convolutional One Stage Detector
- Global Context Vision Transformers
- Reading: ShuffleNet V2 — Practical Guidelines for E�fficient CNN Architecture Design (Image Classification)
- Squeezenet Module
- Image Segmentation Loss: IoU vs Dice Coefficient
- How I mastered Data Structures and Algorithms
- Docker Tutorial ML
- Docker Tutorial for Beginners [FULL COURSE in 3 Hours]
- 1st Two Lessons of From Deep Learning Foundations to Stable Diffusion
- Walk with fastai
- Lesson 9 (part 2) preview Satble Diffusion
- Diffusion Models | Paper Explanation | Math Explained
- Practical Deep Learning FasiAI
- 58 Dr. Ben Goertzel - Artificial General Intelligence
- Visual Guide to Transformer Neural Networks - (Episode 1) Position Embeddings
- Deep Learning Course by Yann Lecuun
- Full Stack Deep Learning 2021
- Swin Transformer paper animated and explained
- ConvNext paper
- Learning to learn: An Introduction to Meta Learning
- How to Use "memory_profiler" to Profile Memory Usage by Python Code?
- Matlab RObotics Series
- Exploring the Limits of Synthetic Creation of Solar EUV Images via Image-to-image Translation
- Transformer Architecture: The Positional Encoding
- Sub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web Faces
- Global Context Networks (GCNet) Explained
- How can one quickly look up people from a large database?
- 10 INSTAGRAM TIPS for Photographers in 2021
- SegFormer
- Segmenter: Transformer for Semantic Segmentation
- Application of Hybrid Network of UNet and Feature Pyramid Network in Spine Segmentation
- The Matrix Calculus You Need For Deep Learning
- Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [BCNet, CVPR 2021]
- COCO Semantic Segmentation
- Effect of batch size on training dynamics
- Create virtual environments for python with conda
- COAT Net
- This is a game changer! (AlphaTensor by DeepMind explained)
- CoAtNet: Marrying Convolution and Attention for All Data Sizes - Paper Explained
- CoAtNet: Marrying Convolution and Attention for All Data Sizes
- NanoDet-Plus
- AAAI 2021: Meta-Learning
- Learning to learn: An Introduction to Meta Learning
- A Tutorial on Attention in Deep Learning (Monday, June 10 - Hall A - 13
- Roger Penrose | Gravity, Hawking Points and Twistor Theory
- AI for Robotics
- OneFormer: An Universal Image Segmentation Framework That Unifies Segmentation With A Multi-Task Train-Once Design
- Class-agnostic Object Detection
- Heatmap-based Explanation of YOLOv5 Object Detection with Layer-wise Relevance Propagation
- COCO to YOLOV5 conversion
- Object Detection Annotation Conversion PyLabel
- An Overview of Robotics Perception
- How Robots See: Computer Vision and Robot Perception with Miguel Valencia
- #82 - Dr. JOSCHA BACH - Digital Physics, DL and Consciousness
- Tips for Best Training Results YOLOV5
- Different IoU Losses for Faster and Accurate Object Detection
- focal_loss.binary_focal_loss
- Focal-loss-a-better-alternative-for-cross-entropy
- IoU Metrics | IOU, Generalised IoU ( GIOU ), Distance IOU ( DIOU ) and Complete IoU (CIOU) Explained
- Different IoU Losses for Faster and Accurate Object Detection
- Everything You Want to Know About ONNX
- Data Science Gems Deep Learning Podcast Queries
- OpenCV Course - Full Tutorial with Python
- Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Sele...
- FCOS - Fully Convolutional One Stage Detector
- VoltaMl is an open-source lightweight library to accelerate your machine learning and deep learning models. VoltaML can optimize, compile and deploy your models to your target CPU and GPU devices, with just one line of code.
- Google doc supporting ML algorithms plugin tutorial
- Install Git and Github in VSCode
- Binary Quantizer
- BiDet: An Efficient Binarized Object Detector
- Momentum Contrast Self supervised learning paper
- NCNN lightweight - ncnn is a high-performance neural network inference computing framework optimized for mobile platforms
- CutMix: A new strategy for Data Augmentation
- Transfer Learning for Fundus Image Quality Assessment Using Discriminating Patches
- Data Augmentation for Object Detection Cutmix, Cutout albumentations
- Data Augmentation Tutorial: Basic, Cutout, Mixup albumentations
- SSD object detection
- YOLOX is an anchor-free version of YOLO
- You Only Learn One Representation: Unified Network for Multiple Tasks
- Centernet Objects as Points
- Detectron2 is Facebook AI Research's next generation library that provides state-of-the-art detection and segmentation algorithms. It is the successor of Detectron and maskrcnn-benchmark
- Lightweight fastest segmentation catalyst large seg hub
- Pytorch Segmentation Library
- Icevision Tutorial github
- Icevision doc -- IceVision is the first agnostic computer vision framework to offer a curated collection with hundreds of high-quality pre-trained models from Torchvision, Open MMLab's MMDetection, Ultralytic's YOLOv5, Ross Wightman's EfficientDet and soon PyTorch Image Models. It orchestrates the end-to-end deep learning workflow allowing to train networks with easy-to-use robust high-performance libraries such as PyTorch-Lightning and Fastai.
- A faster way to ship your models to production
- SEResNeXt paper
- GhostNetV2: Enhance Cheap Operation with Long-Range Attention
- How to create a new branch on GitHub // Commit & Push
- BBAug: A Package for Bounding Box Augmentation in PyTorch
- get-a-list-of-files-sorted-by-modified-date-in-python
- CV3DST - Object tracking
- CV3DST - Multi-object tracking
- Understanding Kalman Filters MATLAB
- DeepSort Explanation
- LIDAR Technology, Principles
- Demystifying Attention in Computer Vision with Convolutional Neural Networks
- Vision Transformer Explained
- IOU Loss
- Image Segmentation Using Deep Learning
- Get Visual Studio Code terminal history
- YOLOX Explanation — Mosaic and Mixup For Data Augmentation
- Pytorch Segmentation Models Resources
- FPN Segmentation Doc
- Python: logging program state into multiple files for analysis
- MaxViT: Multi-Axis Vision Transformer
- Exploiting Multiprocessing and Multithreading in Python as a Data Scientist
- Monarch II - Mobile Multispectral Camera