Author Archives: Jayita Bhattacharyya - Page 2
Exploring ArtLine – To Create Line Art Portraits, Movie Posters & Cartoonize Images in Python
ArtLine uses deep learning algorithms to achieve fine quality line art portraits, movie posters and cartoonize images.
The post Exploring ArtLine – To Create Line Art Portraits, Movie Posters & Cartoonize Images in Python appeared first on Analytics India Magazine.
Apple’s Hypersim – A Photorealistic Synthetic Indoor Scene Dataset for Per-Pixel Ground Truth Labels
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding containing annotations for per pixel ground truth labels and corresponding ground truth geometry, material information, and lighting information for every scene.
The post Apple’s Hypersim – A Photorealistic Synthetic Indoor Scene Dataset for Per-Pixel Ground Truth Labels appeared first on Analytics India Magazine.
VIBE - Video Inference for 3D Human Body Pose and Shape Estimation. It uses CNNs, RNNs(GRU) and GANs along with a self-attention layer to achieve its state-of-the-art results.
The post Guide To VIBE: Video Inference for 3D Human Body Pose and Shape Estimation appeared first on Analytics India Magazine.
VIBE - Video Inference for 3D Human Body Pose and Shape Estimation. It uses CNNs, RNNs(GRU) and GANs along with a self-attention layer to achieve its state-of-the-art results.
The post Guide To VIBE: Video Inference for 3D Human Body Pose and Shape Estimation appeared first on Analytics India Magazine.
TorchIO is a PyTorch based deep learning library written in Python for medical imaging. It is used for 3D medical image loading, preprocessing, augmenting, and sampling.
The post TorchIO – A PyTorch Library Using Patch-based Learning For Medical Imaging appeared first on Analytics India Magazine.
MODNet is a matting decomposition network for sub-objective consistency(SOC) from a single input image in real-time under varying scene changes. It is designed on neural networks to be along with a self-supervised strategy and one-frame delay(OFD) to smooth portrait sequence. It is easy to implement as it's a trimap-free method and runs at 63fps.
The post MODNet – A Trimap & Green Screen free Solution For Real-time Portrait Matting appeared first on Analytics India Magazine.
Microsoft Qlib is an AI-oriented quantitative investment platform containing the full ML pipeline of data processing, model training, back-testing; and covers the entire auto workflow of quant investment.
The post Guide To Qlib: Microsoft’s AI Investment Platform appeared first on Analytics India Magazine.
TabPy(Tableau Python Server) is an API which allows python scripts to be run on a Tableau server. Thereby enabling EDA and visualization more effectively. This helps in building better dashboards and advanced analytics to draw insights out of it. TabPy handles the data exploration and visualization part when data developers can focus more on the data science logic to better handle business use cases.
The post TabPy – Guide To Integrating Tableau With Python appeared first on Analytics India Magazine.
Codist is a platform as a service(PaaS), built for MLonCode and Programming Language Theory to automatically interpret source code and then help developers understand and maintain source code faster.
The post Generating Automatic Documentation and Comments to Source Codes using Codist AI appeared first on Analytics India Magazine.
In this article, we have implemented time series forecasting over the National Stock Exchange India Nifty 50 index dataset using Facebook’s NeuralProphet library to show the seasonality and trends over time.
The post Time Series Forecasting On NSE Of India Using Facebook’s NeuralProphet appeared first on Analytics India Magazine.