The starter repository for submissions to the GeneDisco challenge for optimized experimental design in genetic perturbation experiments

The starter repository for submissions to the GeneDisco challenge for optimized experimental design in genetic perturbation experiments. GeneDisco (to be published at ICLR-22) is a benchmark suite for evaluating activelearning algorithms for experimental design in drug discovery.GeneDisco contains a curated set of multiple publicly available experimental data sets as well as open-sourceimplementations of state-of-the-art active learning policies for experimental design and exploration. Install pip install -r requirements.txt Use Setup Create a cache directory. This will hold any preprocessed and downloaded […]

Read more

Pytorch implementation of MaskGIT: Masked Generative Image Transformer

Pytorch implementation of MaskGIT: Masked Generative Image Transformer (https://arxiv.org/pdf/2202.04200.pdf) Note: this is work in progress MaskGIT is an extension to the VQGAN paper which improves the second stage transformer part (and leaves the first stage untouched). It switches the unidirectional transformer for a bidirectional transformer. The (second stage) training is pretty similar to BERT by randomly masking out tokens and trying to predict these using the bidirectional transformer (the original work used a GPT architecture randomly replaced tokens by other […]

Read more

PLStream: A Framework for Fast Polarity Labelling of Massive Data Streams

Motivation When dataset freshness is critical, the annotating of high speed unlabelled data streams becomes critical but remains an open problem. We propose PLStream, a novel Apache Flink-based framework for fast polarity labelling of massive data streams, like Twitter tweets or online product reviews. Environment Requirements relative python packages are summerized in requirements.txt Flink v1.13 Python 3.7 Java 8 DataSource Tweets Yelp Reviews Amazon Reviews Quick Start quick try PLStream on yelp review dataset Data Prepare cd PLStream weget https://s3.amazonaws.com/fast-ai-nlp/yelp_review_polarity_csv.tgz […]

Read more

Module 2’s katas from Launch X’s python introduction course

Module 2’s katas from Launch X’s python introduction course. Virtual environment creation process (on Windows): Create a folder in any desired direction, I created mine in the documents/ folder and named it test-project. Next, use the Windows command prompt to navigate to the folder’s location, and executed the command py -m venv env. A folder named env should appear in your root directory. Overall directory structure:    

Read more

Implementation of linesearch Optimization Algorithms in Python

During my time as Scientific Assistant at the Karlsruhe Institute of Technology (Germany) I implemented various Optimization Algorithms solving unrestricted nonlinear Problems; Gradient-Descent-Method, Newton-Method, Conjugate-Gradient-Descent-Method, BFGS-Method and a Trust-Region-Method in Python. In addition, I implemented an Armijo linesearch. The code is implemented in an object-oriented manner, whereby each method is implemented in a class (bfgs.py, cg.py, gradv.py, newtonm.py and tr.py) and executed via the ros_test.py script. In the script ros_test.py the Rosenbrock function was implemented, which is minimized to a […]

Read more

Under Water Autonomous Vehicle Research Group

This Respository consists of the projects that I have done as a Part of “Under Water Autonomous Vehicle Research Group” in our college. I was in the AI domain of it and we participate in Under Water Vehicle Competitions at College levels. This Repo consists of variety of object detection codes and color classification codes. HOW TO SETUP THIS CODE???? STEP – 1 – Download the code, it will be a zip file , extractitSTEP -2 – Go to the […]

Read more

Video-quality calculates VMAF and (optionally) other video quality metrics

video-quality calculates VMAF and (optionally) other video quality metrics for a distorted video relative to a reference video before outputting them in a csv file and providing a summary. It utilises FFmpeg, FFprobe and VMAF to achieve this. Features Different quality metrics Support for distorted videos that are clips of the reference video Support for distorted videos that are cropped relative to the reference video Limitations Only supports FHD (1080p) video Has a crop feature deigned for the removal of […]

Read more
1 218 219 220 221 222 915