Name: Animesh Karnewar
Type: User
Company: UCL
Bio: PhD @smartgeometry-ucl|Marie Curie Fellow for PRIME-ITN|Research interests: VFX, Movies, Video Games, Generative Modelling, Computer Graphics, PBR, DL, AI.
Twitter: AnimeshKarnewar
Location: London
Blog: https://akanimax.github.io
Animesh Karnewar's Projects
Simple Tensorflow implementation of "Squeeze and Excitation Networks" using Cifar10 (ResNeXt, Inception-v4, Inception-resnet-v2)
A state-preserved multilayered RNN with LSTM cells for performing sentiment-analysis on movie reviews. The implementation is done using the TensorFlow framework in python
basics in depth
More experimentation with the base MSG-GAN architecture. This includes the coord-conv layers in the architecture. For more info about MSG-GAN, head to -> https://github.com/akanimax/msg-stylegan-tf
MSG-GAN with self attention. For MSG-GAN head to -> https://github.com/akanimax/MSG-GAN
Semantic Image Synthesis with SPADE
The spark assignments in the course
StyleGAN2 - Official TensorFlow Implementation
A deep learning based solution for the SVC2004 problem.
T2F: text to face generation using Deep Learning
Computation using data flow graphs for scalable machine learning
TensorFlow Tutorial and Examples for beginners
Tensorflow Notebook Examples and Tutorials
ReLU Fields The Little Non-linearity That Could
Data -> https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge/data
Implementation (with some experimentation) of the paper titled "VARIATIONAL DISCRIMINATOR BOTTLENECK: IMPROVING IMITATION LEARNING, INVERSE RL, AND GANS BY CONSTRAINING INFORMATION FLOW" (arxiv -> https://arxiv.org/pdf/1810.00821.pdf)
Web projects as a part of the Single-Page-Web-Development-using-AngularJS coursera course. This repo contains use of Bootstrap for styling the front-end pages.
A large annotated semantic parsing corpus for developing natural language interfaces.