Orbit is an open-source Python framework created by Uber for Bayesian time series forecasting and inference.
Pixel2Style2Pixel (pSp) is an image translation framework that builds upon the representative power of a pre-trained StyleGAN generator and the W+ latent space.
Torch-Points3D is a flexible and powerful framework that aims to make deep learning on 3D data both more accessible and reproducible.
MixNMatch is a conditional generative model that disentangles and encodes background, object pose, shape, and texture from real images with minimal supervision.
TensorFlow, Pytorch, Caffe, Keras, Theano, and many more. There’s already an abundance of deep learning frameworks, so why should you care about Trax? Well, most
KGCNN offers a straightforward and flexible integration of graph operations into the Tensorflow-Keras framework using RaggedTensors.
ClearML is an open-source, zero-integration machine learning/deep learning experiment manager and ML-Ops solution.
RepVGG is a simple ConvNet architecture that combines multibranch topologies’ increased performance and the simplicity of VGG topology.
Open Neural Network Exchange (ONNX) is a powerful and open format built to represent machine learning models. It overcomes the problem of framework lock-in by providing an universal intermediary model format.
Boruta is a Python package designed to take the “all-relevant” approach to feature selection.
Face-to-Face translation is plagued by the novel problem of out-of-sync lips, LipGAN and Wave2Lip aim to solve this lip sync issue.
Stanza is a Python natural language analysis library created by the Stanford NLP group. It is a collection of NLP tools that can be used
© Analytics India Magazine Pvt Ltd & AIM Media House LLC 2023
