There are 0 repository under cutout topic.
A smart and easy-to-use image masking and cutout SDK for mobile apps.
🛠 Toolbox to extend PyTorch functionalities
Android image background removing library
Unreal Engine 4 Runtimes for Creature, the 2D Skeletal + Mesh Animation Tool
2D Skeletal Animation WebGL Runtimes for Creature ( PixiJS, PhaserJS, ThreeJS, BabylonJS, Cocos Creator )
Cutout / Random Erasing implementation, especially for ImageDataGenerator in Keras
Data Augmentation For Object Detection using Pytorch and PIL
2D Skeletal Animation Unity Runtimes for Creature
Implementation of modern data augmentation techniques in TensorFlow 2.x to be used in your training pipeline.
A handy data augmentation toolkit for image classification put in a single efficient TensorFlow/PyTorch op.
Cocos2d-x Runtimes for Creature
Make cutout effect of your text in an easy way.
AI Image Cutout Maker is a project that uses artificial intelligence to automatically create cutouts from images. This project is designed to simplify the process of creating cutouts, which can be a time-consuming task if done manually. This project utilizes the power of Segment Anything and Grounding Dino AI models to detect subjects in an image
Pytorch Implementation of ALL-CNN in CIFAR10 Dataset
CIRADA cutout SErvice iN PYthon
I followed a tutorial on SUPER Hi to create my own version of the cut-out-effect. The secret is blending.
Tensorflow2(Keras)のImageDataGeneratorのJupyter上での実行例。
Image Enhance CutouPro is an Android application that allows users to enhance their old images or photos using the CutouPro API. The app utilizes Retrofit 2 for network requests, MVVM and Hilt for dependency injection.
This is the front-end webpage for the AI image cutout generator, the BE for this repo can be found here: https://github.com/OriginalByteMe/AI_Image_cutout_maker
This project proposes a neural network architecture Residual Dense Neural Network - ResDen, to dig the optimization ability of neural networks. With enhanced modeling of Resnet and Densenet, this architecture is easier to interpret and less prone to overfitting than traditional fully connected layers or even architectures such as Resnet with higher levels of layers in the network.
To evaluate the performance of each regularization method (cutout, mixup, and self-supervised rotation predictor), we apply it to the CIFAR-10 dataset using a deep residual network with a depth of 20 (ResNet20)
An R script for extracting MODIS data for a list of locations