Aparna Balagopalan (Aparna-B)

Aparna-B

Geek Repo

Location:Cambridge, MA

Github PK Tool:Github PK Tool

Aparna Balagopalan's repositories

pyAudioAnalysis

Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications

Language:PythonLicense:Apache-2.0Stargazers:1Issues:0Issues:0

academic-kickstart

📝 Easily create a beautiful website using Academic, Hugo, and Netlify

Language:ShellLicense:MITStargazers:0Issues:1Issues:0

AVA-dataset-downloader

You may need these scripts to download AVA images from website.

Language:PythonStargazers:0Issues:2Issues:0

bert_score

BERT score for text generation

Language:Jupyter NotebookLicense:MITStargazers:0Issues:1Issues:0
Language:PythonStargazers:0Issues:1Issues:0
Language:PythonStargazers:0Issues:2Issues:0

datasheet-for-dataset-template

Template for datasheet for datasets

License:MITStargazers:0Issues:0Issues:0

illustration2vec

A simple deep learning library for estimating a set of tags and extracting semantic feature vectors from given illustrations.

Language:PythonLicense:MITStargazers:0Issues:2Issues:0

Label-embeddings-in-image-classification

Convolutional Neural Networks (CNNs) are being widely used for various tasks in Computer Vision. We focus on the task of image classification particularly using CNNs with more focus on the relation or similarity between class labels. The similarity between labels is judged using label word embeddings and incorporated into the loss layer. We propose that shallower networks be learnt with more complex and structured losses, in order to gain from shorter training time and equivalent complexity. We train two variants of CNNs with multiple architectures , all limited to a maximum of ten convolution layers to obtain an accuracy of 93.27% on the Fashion-MNIST dataset and 86.40% on the CIFAR 10 dataset. We further probe the adversarial robustness of the model as well the classspecific behavior by visualizing the class confusion matrix.We also show some preliminary results towards extending a trained variant to zero-shot learning.

Language:PythonStargazers:0Issues:2Issues:0

deform_conv_pytorch

PyTorch Implementation of Deformable Convolution

Language:Jupyter NotebookStargazers:0Issues:0Issues:0
Stargazers:0Issues:2Issues:0
Language:PythonStargazers:0Issues:1Issues:0

FairRankingRelevance

An examination of the role of relevance in fair exposure-based ranking

Language:PythonStargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0

HurtfulWords

Quantifying biases in BERT embeddings pretrained on MIMIC-III clinical notes

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

JudgingNorms

An examination of data labeling practices for normative applications.

Language:Jupyter NotebookLicense:MITStargazers:0Issues:1Issues:0

lcifr

Learning Certified Individually Fair Representations

License:MITStargazers:0Issues:0Issues:0

lime-experiments

Code for all experiments.

License:BSD-2-ClauseStargazers:0Issues:0Issues:0

machine-learning-scripts

Collection of scripts and tools related to machine learning

License:MITStargazers:0Issues:0Issues:0

model-card-template

Template for model cards

License:MITStargazers:0Issues:0Issues:0

NeuroNER

Named-entity recognition using neural networks. Easy-to-use and state-of-the-art results.

Language:PythonStargazers:0Issues:0Issues:0

pvd_steganography

Python Implementation of Pixel Value Differencing based Steganography (LSB) - PNG Cover Images

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

pygcn

Graph Convolutional Networks in PyTorch

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

pytorch-CycleGAN-and-pix2pix

Image-to-image translation in PyTorch (e.g. horse2zebra, edges2cats, and more)

Language:PythonLicense:NOASSERTIONStargazers:0Issues:2Issues:0

pytorch-yolo2

Convert https://pjreddie.com/darknet/yolo/ into pytorch

Language:PythonLicense:MITStargazers:0Issues:2Issues:0

researcher

A jekyll based resume template

Language:HTMLLicense:GPL-3.0Stargazers:0Issues:0Issues:0

transformer_rankers

A library to conduct ranking experiments with transformers.

Language:PythonLicense:MITStargazers:0Issues:0Issues:0