Computer Vision : Series
by akshara Updated: May 28, 2022
Solution Kit
𝐂𝐎𝐌𝐏𝐔𝐓𝐄𝐑 𝐕𝐈𝐒𝐈𝐎𝐍 is a field of artificial intelligence that trains computers to interpret and understand the visual world. Using digital images from cameras and videos and deep learning models machines can accurately identify and classify objects and then react to what they "see". It is the field of computer science that focuses on replicating parts of the complexity of the human vision system and enabling computers to identify and process objects in images and videos.
𝑪𝑶𝑴𝑷𝑼𝑻𝑬𝑹 𝑽𝑰𝑺𝑰𝑶𝑵 𝑺𝑬𝑹𝑰𝑬𝑺
𝐈𝐦𝐚𝐠𝐞 𝐜𝐥𝐚𝐬𝐬𝐢𝐟𝐢𝐜𝐚𝐭𝐢𝐨𝐧
Image classification is used to categorize whether an object is present in the likelihood of an image. Feature extraction is a part of the dimensionality reduction process, in which, an initial set of the raw data is divided and reduced into more manageable groups. Image classification is the process of categorizing and labeling groups of pixels or vectors within an image based on specific rules.
mmclassificationby open-mmlab
OpenMMLab Image Classification Toolbox and Benchmark
mmclassificationby open-mmlab
Python
2027
Version:v1.0.0rc5
License: Permissive (Apache-2.0)
pytorch_image_classificationby hysts
PyTorch implementation of image classification models for CIFAR-10/CIFAR-100/MNIST/FashionMNIST/Kuzushiji-MNIST/ImageNet
pytorch_image_classificationby hysts
Python
1204
Version:Current
License: Permissive (MIT)
HRNet-Image-Classificationby HRNet
Train the HRNet model on ImageNet
HRNet-Image-Classificationby HRNet
Python
870
Version:PretrainedWeights
License: Permissive (MIT)
GoogLeNet-Inceptionby conan7882
TensorFlow implementation of GoogLeNet and Inception for image classification.
GoogLeNet-Inceptionby conan7882
Python
268
Version:Current
License: Permissive (MIT)
wildcat.pytorchby durandtibo
PyTorch implementation of "WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation", CVPR 2017
wildcat.pytorchby durandtibo
Python
241
Version:Current
License: Permissive (MIT)
𝐎𝐛𝐣𝐞𝐜𝐭 𝐝𝐞𝐭𝐞𝐜𝐭𝐢𝐨𝐧
Object Detection is used to recognize the object with a bounding box in an image. Object detection is an important computer vision task used to detect instances of visual objects of certain classes (for example, humans, animals, cars, or buildings) in digital images such as photos or video frames. The goal of object detection is to develop computational models that provide the most fundamental information needed by computer vision applications.
Object-Detection-API-Tensorflowby Stick-To
Object Detection API Tensorflow
Object-Detection-API-Tensorflowby Stick-To
Python
274
Version:Current
License: Permissive (MIT)
ssd.pytorchby amdegroot
A PyTorch Implementation of Single Shot MultiBox Detector
ssd.pytorchby amdegroot
Python
4883
Version:Current
License: Permissive (MIT)
flask-object-detectionby AIZOOTech
Frontend and backend separated object detection demo build with Flask, TensorFlow.
flask-object-detectionby AIZOOTech
Python
82
Version:Current
License: Permissive (MIT)
Object-Detection-APIby theAIGuysCode
Yolov3 Object Detection implemented as APIs, using TensorFlow and Flask
Object-Detection-APIby theAIGuysCode
Python
326
Version:Current
License: Permissive (Apache-2.0)
autogluonby awslabs
AutoGluon: AutoML for Image, Text, and Tabular Data
autogluonby awslabs
Python
4341
Version:v0.4.0
License: Permissive (Apache-2.0)
𝐈𝐧𝐬𝐭𝐚𝐧𝐜𝐞 𝐒𝐞𝐠𝐦𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧
Instance Segmentation is identifying each object instance for every known object within an image. Instance segmentation assigns a label to each pixel of the image. Instance segmentation is the task of detecting and delineating each distinct object of interest appearing in an image.
PaddleDetectionby PaddlePaddle
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
PaddleDetectionby PaddlePaddle
Python
10541
Version:v2.6.0
License: Permissive (Apache-2.0)
maskrcnn-benchmarkby facebookresearch
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
maskrcnn-benchmarkby facebookresearch
Python
9098
Version:v0.1
License: Permissive (MIT)
yolactby dbolya
A simple, fully convolutional model for real-time instance segmentation.
yolactby dbolya
Python
4681
Version:Current
License: Permissive (MIT)
yolact_edgeby haotian-liu
The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.
yolact_edgeby haotian-liu
Python
1186
Version:Current
License: Permissive (MIT)
labelImgby tzutalin
🖍️ LabelImg is a graphical image annotation tool and label object bounding boxes in images
labelImgby tzutalin
Python
15699
Version:v1.8.1
License: Permissive (MIT)