chitwansaharia

HACAModel

Implementation of "Watch, Listen, and Describe: Globally and Locally Aligned Cross-Modal Attentions for Video Captioning" (https://arxiv.org/abs/1804.05448)

Adversarial-Examples

Tutorial for generating adversarial examples

ASR-Project

Course Project on Speaker Identification using CNNs

categorical-dqn

A working implementation of the Categorical DQN (Distributional RL).

all-conv-pytorch

Pytorch implementation of "Striving for Simplicity: The All Convolutional Net" (https://arxiv.org/abs/1412.6806)

AMLProject

Image-Captioning

Analysis of Image Captioning Models

aws-efa-eks

Deploying EFA in EKS utilizing GPUDirectRDMA where supported

aws-efa-nccl-baseami-pipeline

EFA/NCCL base AMI build Packer and CodeBuild/Pipeline files. Also base Docker build files to enable EFA/NCCL in containers

clean-fid

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

dotfiles

My personal collection of various dotfiles

examples

TensorFlow examples

EyeInTheSky

Inter IIT Tech Meet 2018 (Eye in the Sky)

flax

Flax is a neural network library for JAX that is designed for flexibility.

guided-diffusion

gym-minigrid

Minimalistic gridworld environment for OpenAI Gym

minima

Minima is a one-size-fits-all Jekyll theme for writers.

nccl-tests

NVIDIA NCCL Tests for Distributed Training

NFGEC

Neural Architectures for Fine Grained Entity Type Classification

opencv

Open Source Computer Vision Library

OpenNMT-tf

Neural machine translation and sequence learning using TensorFlow

pyannote-audio

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, speaker embedding

pytorch-cifar

95.16% on CIFAR10 with PyTorch

pytorch-fid

Compute FID scores with PyTorch.

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

SincNet

SincNet is a neural architecture for efficiently processing raw audio samples.

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

vsepp

PyTorch Code for the paper "VSE++: Improving Visual-Semantic Embeddings with Hard Negatives"

website

youtube-8m-videos-frames

Youtube-8m Videos, Frames and Ids Generator. Extract videos from youtube-8m. Extract frames from youtube-8m.