6f482b1fa7
|
||
|---|---|---|
| .. | ||
| README.md | ||
README.md
Computer Vision
Computer Vision Recipies
Image Classification
A form of inference in which an object in an image is determined to be of a particular class, such as a cat vs. a dog.
Object Detection
A form of inference in which objects within an image are detected, and a bounding box is output based on where in the image the object was detected. Usually, this is combined with some form of classification to also output which class the detected object belongs to.
Semantic Segmentation
A form of inference in which objects within an image are detected and classified on a pixel-by-pixel basis, with all objects of a given class given the same label.
Instance Segmentation
Similar to semantic segmentation, this form of inference is done on a pixel-by-pixel basis, but different objects of the same class are separately identified.
SSD
Single Shot MultiBox Detector. A neural network combining object detection and classification, with different feature extraction layers directly feeding to the detection layer, using default bounding box sizes and shapes.
YOLO
One of the original neural networks to only take a single look at an input image, whereas earlier networks ran a classifier multiple times across a single image at different locations and scales.
- YOLOv4 in the CLOUD: Build and Train Custom Object Detector (FREE GPU)
- YOLOv4-Cloud-Tutorial - Code
- The AI Guy
Faster R-CNN
A network, expanding on R-CNN and Fast R-CNN, that integrates advances made in the earlier models by adding a Region Proposal Network on top of the Fast R-CNN model for an integrated object detection model.
MobileNet
A neural network architecture optimized for speed and size with minimal loss of inference accuracy through the use of techniques like 1x1 convolutions. As such, MobileNet is more useful in mobile applications that substantially larger and slower networks.
ResNet
A very deep neural network that made use of residual, or “skip” layers that pass information forward by a couple of layers. This helped deal with the vanishing gradient problem experienced by deeper neural networks.
Inception
A neural network making use of multiple different convolutions at each “layer” of the network, such as 1x1, 3x3 and 5x5 convolutions. The top architecture from the original paper is also known as GoogLeNet, an homage to LeNet, an early neural network used for character recognition.
Cool CVProjects
DeOldify
A Deep Learning based project for colorizing and restoring old images (and video!)