Pinned Repositories
ArtiViz
A tool to automatically generate dynamic graphics as webm files using themes provided as natural language queries. Built using p5.js, powered by ChatGPT.
AutoFFmpeg
A tool to automatically generate and debug ffmpeg commands using natural language queries. Powered by ChatGPT.
DeepSemiNMF
This repository contains the pytorch code for the paper: A Deep Semi-NMF Model for Learning Hidden Representations (Trigeorgis2014)
HyperspecAE
Code for the experiments on the Samson Dataset as presented in the paper: Hyperspectral Unmixing Using a Neural Network Autoencoder (Palsson et al. 2018)
NNVisualizer
A web app made using Flask and Streamlit to visualise the workings of a Neural Network
ReinforcementLearning
Implementing some RL algorithms (using PyTorch) on the CartPole environment by OpenAI.
sdc
A scaled down version of the self-driving system using OpenCV. The system comprises of - • Raspberry Pi with a webcam and an ultrasonic sensor as inputs, ◦ Steering using move in sdcar.py ◦ Stop sign detection using houghcircles and colour intensities ◦ Front collision avoidance using an ultrasonic sensor • l298N motor controller • project structure: *sdcar.py is a combination of all the following *lane_lines.py: step1.take the webcam feed and apply the canny edge algorithm to detect the edges step2. detect the lines in an edged image using houghlines step3. average the lines according to the slope step4.making points using slope step5. return right, left, camera and central line *sensor.py: distance measurement using input and output pins *sign.py: *detection of circles in image using hough circles *if the dominant colour in a square region around the circle is red then it is stop sign. *if the dominant colour in a square region around the circle is blue then there are 5 cases left, right, forward, forward and right or forward and left for this: • make the 3 zones of square regions the right , left, upper(for forward) • if the right zone is white and the other two are blue then the sum of RGB colour intensities in the right zone will be obviously greater than the other two zones then the sign is right similarly for others. Note : sign.py will work on following type of sign:
SemiNMF-Autoencoders
Official implementation of our NCC'24 paper titled "Semi‑NMF Regularization‑Based Autoencoder Training for Hyperspectral Unmixing".
SentimentClassification
Fine-tuning a BERT model for Sentiment Classification on the SMILE: Twitter Emotion Dataset
NL-Code-Adapter
dv-fenix's Repositories
dv-fenix/HyperspecAE
Code for the experiments on the Samson Dataset as presented in the paper: Hyperspectral Unmixing Using a Neural Network Autoencoder (Palsson et al. 2018)
dv-fenix/DeepSemiNMF
This repository contains the pytorch code for the paper: A Deep Semi-NMF Model for Learning Hidden Representations (Trigeorgis2014)
dv-fenix/NNVisualizer
A web app made using Flask and Streamlit to visualise the workings of a Neural Network
dv-fenix/SentimentClassification
Fine-tuning a BERT model for Sentiment Classification on the SMILE: Twitter Emotion Dataset
dv-fenix/SemiNMF-Autoencoders
Official implementation of our NCC'24 paper titled "Semi‑NMF Regularization‑Based Autoencoder Training for Hyperspectral Unmixing".
dv-fenix/AutoFFmpeg
A tool to automatically generate and debug ffmpeg commands using natural language queries. Powered by ChatGPT.
dv-fenix/ReinforcementLearning
Implementing some RL algorithms (using PyTorch) on the CartPole environment by OpenAI.
dv-fenix/sdc
A scaled down version of the self-driving system using OpenCV. The system comprises of - • Raspberry Pi with a webcam and an ultrasonic sensor as inputs, ◦ Steering using move in sdcar.py ◦ Stop sign detection using houghcircles and colour intensities ◦ Front collision avoidance using an ultrasonic sensor • l298N motor controller • project structure: *sdcar.py is a combination of all the following *lane_lines.py: step1.take the webcam feed and apply the canny edge algorithm to detect the edges step2. detect the lines in an edged image using houghlines step3. average the lines according to the slope step4.making points using slope step5. return right, left, camera and central line *sensor.py: distance measurement using input and output pins *sign.py: *detection of circles in image using hough circles *if the dominant colour in a square region around the circle is red then it is stop sign. *if the dominant colour in a square region around the circle is blue then there are 5 cases left, right, forward, forward and right or forward and left for this: • make the 3 zones of square regions the right , left, upper(for forward) • if the right zone is white and the other two are blue then the sum of RGB colour intensities in the right zone will be obviously greater than the other two zones then the sign is right similarly for others. Note : sign.py will work on following type of sign:
dv-fenix/ArtiViz
A tool to automatically generate dynamic graphics as webm files using themes provided as natural language queries. Built using p5.js, powered by ChatGPT.
dv-fenix/Convolutions-as-Matrix-Multiplication
Understanding how CNNs can be implemented on a TPU
dv-fenix/NeRF
A simple 2D toy example to play around with NeRFs, implemented in pytorch-lightning. Repository can be used as a template to speed up further research on nerfs.
dv-fenix/NL-Code-Adapter
Official implementation and data for our ICPC '22 paper "On The Cross-Modal Transfer from Natural Language to Code through Adapter Modules"
dv-fenix/SyLSTM
Official implementation for the paper "Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks" published at SocialNLP @ NAACL-HLT 2022.
dv-fenix/clean-fid
PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]
dv-fenix/Domain-Adaptation
PyTorch implementations of some papers on Domain Adaptation
dv-fenix/dv-fenix.github.io
dv-fenix/generative-models
Generative Models by Stability AI
dv-fenix/hifi-gan
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
dv-fenix/ieee-iitr.github.io
Website for IEEE Student Chapter IITR
dv-fenix/ITR
Machine Translation
dv-fenix/LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
dv-fenix/pygcn
Graph Convolutional Networks in PyTorch
dv-fenix/seq2seq-con
Implementation of "Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs"
dv-fenix/Snake
I wanted a project which would accommodate whatever I've learned in C++. This came close.
dv-fenix/tutorials
PyTorch tutorials.
dv-fenix/wona.github.com
Blog of Watch Out News Agency, IIT Roorkee