Ankush Gupta

covid-vaccine-booking. This very basic script can be used to automate COVID-19 vaccination slot booking on India's Co-WIN Platform.

cowin_js_bot. A script to help you book your vaccine slot faster

keypoints. Unsupervised learning of Object Landmarks through Conditional Image Generation

covid19india.github.io. Tracking the impact of COVID-19 in India

deepmind-research. This repository contains implementations and illustrative code to accompany DeepMind publications

3D-CODED. Pytorch Implementation for the project : `3D-CODED` and `Learning Elementary Structure`

deep-text-recognition-benchmark. Text recognition (optical character recognition) with deep learning methods, ICCV 2019

Multiview2Novelview. An official TensorFlow implementation of "Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence" (ECCV 2018) by Shao-Hua Sun, Minyoung Huh, Yuan-Hong Liao, Ning Zhang, and Joseph J. Lim

msdfgen. Multi-channel signed distance field generator

partnet_dataset. PartNet Dataset Official Release Repo

AtlasNet. This repository contains the source codes for the paper "AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation ". The network is able to synthesize a mesh (point cloud + connectivity) from a low-resolution point cloud, or from an image.

GEOMetrics. Repo for the paper "GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects"

unsupervised-learning-intrinsic-images. Implementation of the intrinsic image decomposition algorithm described in "Learning Intrinsic Image Decomposition from Watching the World, Z. Li and N. Snavely, CVPR 2018"

CGIntrinsics. This is the CGIntrinsics implementation described in the paper "CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering, Z. Li and N. Snavely, ECCV 2018".

graphics. TensorFlow Graphics: Differentiable Graphics Layers for TensorFlow

E2E-MLT. E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text

progressive_growing_of_gans. Progressive Growing of GANs for Improved Quality, Stability, and Variation

editdistance. Fast implementation of the edit distance(Levenshtein distance)

joint-vae. Pytorch implementation of JointVAE, a framework for disentangling continuous and discrete factors of variation :star2:

lucid. A collection of infrastructure and tools for research in neural network interpretability.

opendr. Python

adjustText. A small library for automatical adjustment of text position in matplotlib plots to minimize overlaps.

tesseract. Tesseract Open Source OCR Engine (main repository)

python-torchfile. Deserialize Lua torch-serialized objects from Python

improved-gan. Code for the paper "Improved Techniques for Training GANs"

CycleGAN. Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

youtube-dl. Command-line program to download videos from YouTube.com and other video sites

cfnet. [CVPR'17] Training a Correlation Filter end-to-end allows lightweight networks of 2 layers (600 kB) to high performance at fast speed..

drnet. Lua

SynthText. This is a modified version of Ankush's code for generating synthetic text images which support right-to-left languages such as Persian and Arabic.

small_norb. Python wrapper to small NORB dataset

cowc. Cars Overhead With Context related scripts described in Mundhenk et al. 2016 ECCV.

SfMLearner. An unsupervised learning framework for depth and ego-motion estimation from monocular videos

whoswho. Name comparison in python

blocklists. Shared lists of problem domains people may want to block with hosts files

PhotographicImageSynthesis. Photographic Image Synthesis with Cascaded Refinement Networks

fast-LayerNorm-TF. Efficient layer normalization GPU kernel for Tensorflow

CipherGAN. TensorFlow implementation of CipherGAN

deep-image-prior. Image restoration with neural networks but without learning.

mcnFasterRCNN. Training code for the Faster-RCNN detector

convert_matlab73_hdf5. Convert Matlab v7.3 '.mat' files (i.e. HDF5 file format) into Python's pickle or numpy format.

mcnSSD. A matconvnet implementation of the Single Shot Detector

scientists-on-youtube. a small collection of interviews and lectures

freelancer-theme. Jekyll theme based on Freelancer Start Bootstrap theme

tensorflow. An Open Source Machine Learning Framework for Everyone

autonn. A fast and expressive Matlab/MatConvNet deep learning API, with native automatic differentiation

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

Awesome-Scene-Text-Recognition. A curated list of resources dedicated to scene text localization and recognition

FCRN-DepthPrediction. Deeper Depth Prediction with Fully Convolutional Residual Networks (FCRN)

context-encoder. [CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs

matconvnet-ResNet. MatConvNet Implementation for Deep Residual Networks

tensorflow-worklab. This set of files is an example of how to use Tensorflow for importing and retraining an existing model, such as ResNet. The goal of this example is to separate all functionality on several classes, so it is easy to modify the parameters and run the models, while still having all code not too deep inside.

models. Models and examples built with TensorFlow

haupt. Lineage metadata API, artifacts streams, sandbox, API, and spaces for Polyaxon

matconvnet. MatConvNet: CNNs for MATLAB

h5py. HDF5 for Python -- The h5py package is a Pythonic interface to the HDF5 binary data format.

zunavision. Zunavision codebase for embedding content within a video. See http://zunavision.com . Code copyright shared with Prof. Andrew Ng and Prof. Ashutosh Saxena.

Theano. Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.com/pymc-devs/pytensor

caffe. Caffe: a fast open framework for deep learning.

sandbox444. Sandbox at 444