sohailahmedkhan Goto Github PK
Name: Sohail Ahmed Khan
Type: User
Company: SFI-MediaFutures, University of Bergen
Bio: PhD Candidate
Location: Bergen, Norway
Name: Sohail Ahmed Khan
Type: User
Company: SFI-MediaFutures, University of Bergen
Bio: PhD Candidate
Location: Bergen, Norway
Implementation of FGSM (Fast Gradient Sign Method) attack on fine-tuned MobileNet architecture trained for flood detection in images.
An awesome README template to jumpstart your projects!
Code and pre-trained models for our paper "CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection".
Notes about usage: This code is to create a custom video dataset to train deeplearning models using PyTorch on consecutive video frames extracted from a video. This code expects the extracted video frames in separate folders. For example, video1's frames will be in a folder named 'video1'. You can use OpenCV to extract video frames and save inside folders.
Deepfake Detection: Analysing Model Generalisation Across Architectures, Datasets, and Pre-Training Paradigms
This script employs Dynamic Programming algorithms such as, Viterbi Search and Beam Search, to accelerate the process of training Multilayer Perceptron
Flood detection from images using deep learning. Deep learning library KERAS was employed and MobileNet architecture was fine-tuned for image classification task.
Deep Learning for humans
A very simple Neural Language Model in PyTorch
Landmark Recurrent Network: An efficient and robust framework for Deepfakes detection
Named Entity Recogniser using Structured Perceptron in Python
OpenCV face detection and extraction from videos.
A detailed comparison of performance scores achieved by Machine Learning and Deep Learning algorithms on 3 different Phishing datasets. 3 different feature selection and 2 different dimensionality reduction techniques are used for comparison.
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
Personal Website
COM6012 Scalable Machine Learning - University of Sheffield
Supervised classification algorithms employed to explore and identify Higgs bosons from particle collisions, like the ones produced in the Large Hadron Collider. HIGGS dataset is used..
The goal of this script is to implement three langauge models to perform sentence completion, i.e. given a sentence with a missing word to choose the correct one from a list of candidate words. The way to use a language model for this problem is to consider a possible candidate word for the sentence at a time and then ask the language model which version of the sentence is the most probable one.
My Resume
Stable Diffusion web UI
This repository contains resources relating to Transformer models including theoretical concepts and code examples.
This is the PyTorch implementation of our ACM Multimedia 2021 paper titled "Video Transformer for Deepfake Detection with Incremental Learning".
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.