NVIDIA/NeMo

A New Padding Scheme: Partial Convolution based Padding

A Flow-based Generative Network for Speech Synthesis

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

Style transfer, deep learning, feature transform

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Synthesizing and manipulating 2048x1024 images with conditional GANs

Deep learning for recommender systems

Hunt for security weaknesses in Kubernetes clusters

Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.