Pinned Repositories
Corona-Drug-Discovery
This is a solution for the Possible Drugs for Covid-19 . Binding scores of leading existing drugs (HIV inhibitors) are around -10 to -11 and around -13 for the drug Remdesivir which recently entered clinical testing. More negative the binding score is, better the drug is. The goal is to create a novel small molecule which can bind with the coronavirus, using deep learning techniques for molecule generation and PyRx to evaluate binding affinities. By combining a Generative RNN model with techniques and principles from transfer learning and genetic algorithms, I was able to create several small molecule candidates which achieved binding scores approaching -18.
Create-own-Jarvis
This jarvis can be like google assistant
Faster-R-CNN
Image-Position-Editing
Image-Position-Editing is a image processing tool for generating segmented masks, changing object positions, and removing objects from images with text prompt
Invo-AI
We propose an extraction system that use knowledge of the types of the target fields to generate extraction candidates, and a neural network architecture that learns a dense representation of each candidate based on neighbouring words in the document. These learned representations are not only useful in solving the extraction task for unseen document templates from two different domains, but are also interpretable in classic document processing.
Protein-Structure-Prediction
In this repository I do rapid prototyping of ideas I have regarding protein structure prediction, some of them building on top of the idea of molecular dynamics simulations, others from the ground up. It may very well be that none of these ideas ever even achieve to fold a simple protein but iterating over different ideas and implementing the basic concept greatly improves my learning experience.
Quora-Ques-Duplicate-or-not
SIIM-Melanoma-Challenge-2019-Solution
SIIM-ISIC Melanoma Classification (6th rank approach). Identify melanoma in lesion images
Speech-To-Text-Wavnet
A tensorflow implementation of speech recognition based on DeepMind's WaveNet: A Generative Model for Raw Audio. (Hereafter the Paper)
Weather_Transformation_Cycle_GaN
Image Translation Using Cycle GAN
Luckygyana's Repositories
Luckygyana/Corona-Drug-Discovery
This is a solution for the Possible Drugs for Covid-19 . Binding scores of leading existing drugs (HIV inhibitors) are around -10 to -11 and around -13 for the drug Remdesivir which recently entered clinical testing. More negative the binding score is, better the drug is. The goal is to create a novel small molecule which can bind with the coronavirus, using deep learning techniques for molecule generation and PyRx to evaluate binding affinities. By combining a Generative RNN model with techniques and principles from transfer learning and genetic algorithms, I was able to create several small molecule candidates which achieved binding scores approaching -18.
Luckygyana/Weather_Transformation_Cycle_GaN
Image Translation Using Cycle GAN
Luckygyana/Create-own-Jarvis
This jarvis can be like google assistant
Luckygyana/Invo-AI
We propose an extraction system that use knowledge of the types of the target fields to generate extraction candidates, and a neural network architecture that learns a dense representation of each candidate based on neighbouring words in the document. These learned representations are not only useful in solving the extraction task for unseen document templates from two different domains, but are also interpretable in classic document processing.
Luckygyana/Faster-R-CNN
Luckygyana/Quora-Ques-Duplicate-or-not
Luckygyana/Awesome-Annotated-Papers
Luckygyana/Bird-Species-Audio-Identification-Ensembling-and-1D-2D-Signals
There are about 10,000 different bird species in the world, and they play an important role in the natural world. They serve as good indicators of declining habitat quality and pollution. It is often easier to hear birds than it is to see them. Bird_CLEF 2021 - Birdcall Identification is a Kaggle competition organized by The Cornell Lab of Ornithology whose challenge is to identify which birds are calling in long recordings, given training data generated in meaningfully different contexts. This paper is structured in a way that it first gives details of the competition and the given data so that there is a clear understanding of the challenges posed by the train and test data. Also, we provide a detailed solution to the approaches we used for this challenge including data preparation, augmentations, model building, training procedure, and post-processing techniques.
Luckygyana/CYCLE_GAN
Transform one image to another on Fashion_mnist Dataset
Luckygyana/Fabric-Defect-Detection
Luckygyana/SIIM-Melanoma-Challenge-2019-Solution
SIIM-ISIC Melanoma Classification (6th rank approach). Identify melanoma in lesion images
Luckygyana/Speech-To-Text-Wavnet
A tensorflow implementation of speech recognition based on DeepMind's WaveNet: A Generative Model for Raw Audio. (Hereafter the Paper)
Luckygyana/torchopenl3-models
torchopenl3 Model weights file
Luckygyana/Cartoonify-GAN
Generate your own cartoon-style images with CartoonifyGAN
Luckygyana/Image-Position-Editing
Image-Position-Editing is a image processing tool for generating segmented masks, changing object positions, and removing objects from images with text prompt
Luckygyana/Protein-Structure-Prediction
In this repository I do rapid prototyping of ideas I have regarding protein structure prediction, some of them building on top of the idea of molecular dynamics simulations, others from the ground up. It may very well be that none of these ideas ever even achieve to fold a simple protein but iterating over different ideas and implementing the basic concept greatly improves my learning experience.
Luckygyana/audiojnd
Audio pair JND
Luckygyana/extreme-image-classification
Luckygyana/G2Net
Luckygyana/hackfest-team-error_404
Submission to Hackfest 2021
Luckygyana/hall-of-fame
:trophy: Show some love to your contributors! A widget for your repo README. Visual and clean. Refreshes every hour.
Luckygyana/hear2021-eval-kit
Evaluation kit for HEAR 2021 NeurIPS competition
Luckygyana/ivy
The Unified Machine Learning Framework
Luckygyana/openl3
OpenL3: Open-source deep audio and image embeddings
Luckygyana/PathFinder
Luckygyana/Portfolio
Luckygyana/seti-kaggle-tezdhar
Repository for solution to https://www.kaggle.com/c/seti-breakthrough-listen/overview
Luckygyana/time-series-notebook
Luckygyana/torchopenl3-1
Luckygyana/yo