Abhilash Awasthi's repositories
DataScience
Some data science projects that I have worked on.
AttentionXML
Implementation for "AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification"
AwasthiMaddy.github.io
My website
competition-winners
The code for the prize winners in DrivenData competitions.
trading_models
Some ML and DL model/solutions for investing in stock market.
DHS2019_HackSession_NLP
Codes used for the hack session in DHS 2019
handson-ml2
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.
Humpback-Whale-Identification-Challenge-2019_2nd_palce_solution
Kaggle Humpback Whale Identification Challenge 2019 2nd place code
imet-6th-soltuion
Code for iMet Collection 2019 - FGVC6
kaggle-competition-solutions
Kaggle competition solutions
kaggle-HPA
Kaggle Human Protein Atlas Image Classification 73th solution
kaggle-hpa-1
Code for 3rd place solution in Kaggle Human Protein Atlas Image Classification Challenge.
kaggle-humpback
Code for 3rd place solution in Kaggle Humpback Whale Identification Challenge.
kaggle-imaterialist
The First Place Solution of Kaggle iMaterialist (Fashion) 2019 at FGVC6
kaggle-pneumothorax-segmentation
https://www.kaggle.com/c/siim-acr-pneumothorax-segmentation
keras-retinanet
Keras implementation of RetinaNet object detection.
kuma_utils
My toolbox for data analysis. :)
micrograd
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
nlp_course
YSDA course in Natural Language Processing
pytorch-saltnet
Kaggle | 9th place solution for TGS Salt Identification Challenge
tf2_course
Notebooks for my "Deep Learning with TensorFlow 2 and Keras" course
TGS-Salt-Identification-Challenge-2018-_4th_place_solution
Kaggle TGS Salt Identification Challenge 2018 4th place code
TGS-SaltNet
Kaggle | 22nd place solution for TGS Salt Identification Challenge
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.