Machine Learning

NeRF Meta-Learning with PyTorch

nerf-meta is a PyTorch re-implementation of NeRF experiments from the paper “Learned Initializations for Optimizing Coordinate-Based Neural Representations”. Simply by initializing NeRF with meta-learned weights, we can achieve: Environment Python 3.8 PyTorch 1.8 NumPy, imageio, imageio-ffmpeg Photo Tourism Starting from a meta-initialized NeRF, we can interpolate between camera pose, focal length, aspect ratio and scene appearance. The videos below are generated with a 5 layer only NeRF, trained for ~100k iterations. Your browser does not support the video tag.Your browser […]

Read more
Testing

Visual, reactive testing library for Julia

PlutoTest.jl (alpha release) A macro @test that you can use to verify your code’s correctness. But instead of just saying “Pass” or “Fail”, let’s try to show you why a test failed. ✨ time travel ✨ to replay the execution step-by-step ⭐️ multimedia display ⭐️ to make results easy to read Try this demo in your browser First, update Pluto to at least 0.14.5! Next, add this package like so: julia> import Pkg; Pkg.add(Pkg.PackageSpec(url=”https://github.com/JuliaPluto/PlutoTest.jl”)) julia> using PlutoTest julia> @test 1 […]

Read more
Download

Download videos from Youtube and other platforms through a Telegram Bot

ytdl-bot Download videos from YouTube and other platforms through a Telegram Bot. Usage: https://t.me/benny_ytdlbot Send link from YouTube directly to the bot. Any platform supported by youtube-dl will also work. fast download and upload. Many thanks to FastTelethon andJasonKhew96‘s contribution on this! ads free – I’ll never send ads to you, also I don’t even print logs that will identify you.So feel free to download any type of video from any website. support progress bar Normal clone code and update […]

Read more
Machine Learning

Use AI to generate a optimized stock portfolio

AIPortfolio Logo Use AI, Modern Portfolio Theory, and Monte Carlo simulation’s to generate a optimized stock portfolio that minimizes risk while maximizing returns. How does it work? The app works by pulling the stock close data from the yahoo finance api. We then calculate the log returns and the volitility of the data to see what the overall trend for the stocks look like. We then generate random portfolio weights and use scipy to maximize a function that calculates the […]

Read more
Machine Learning

A Neural Algorithm of Artistic Style implementation – Neural Style Transfer

ArtiStyle To quote authors Leon A. Gatys, Alexander S. Ecker, Matthias Bethge, “in light of the striking similarities between performance-optimised artificial neural networks and biological vision, our work offers a path forward to an algorithmic understanding of how humans create and perceive artistic imagery. The idea of Neural Style Transfer is taking a white noise as an input image, changing the input in such a way that it resembles the content of the content image and the texture/artistic style of […]

Read more
WebAssembly

Python with the scientific stack compiled to WebAssembly

Pyodide Pyodide may be used in any context where you want to run Python inside a web browser. Pyodide brings the Python 3.8 runtime to the browser via WebAssembly, along with the Python scientific stack including NumPy, Pandas, Matplotlib, SciPy, and scikit-learn. The packages directory lists over 75 packages which are currently available. In addition it’s possible to install pure Python wheels from PyPi. Pyodide provides transparent conversion of objects between Javascript and Python. When used inside a browser, Python […]

Read more
NLP

What they do when in doubt: a study of inductive biases in seq2seq learners

Abstract Sequence-to-sequence (seq2seq) learners are widely used, but we still have only limited knowledge about what inductive biases shape the way they generalize. We address that by investigating how popular seq2seq learners generalize in tasks that have high ambiguity in the training data. We use four new tasks to study learners’ preferences for memorization, arithmetic, hierarchical, and compositional reasoning. Further, we connect to Solomonoff’s theory of induction and propose to use description length as a principled and sensitive measure of […]

Read more
Advanced, NLP, Python, Text

AIML – A Language for Chatbots

This article was published as a part of the Data Science Blogathon. What is a Chatbot? Chatbots are intelligent digital assistants which may address customer’s basic and predictable queries. They offer numerous services via chatting and perform basic customer service operations. Chatbots work 24/7 and hence they provide assistance when offices are closed on holidays. There are a variety of synonyms for chatbot, including “talkbot,” “bot,” “IM bot,” “interactive agent” or “artificial conversation entity.“ Most organizations have already started implementing […]

Read more
Images

Turn xarray timestacks into GIFs with python

GeoGIF Make GIFs from time-stacked xarray.DataArrays (time, [optional band], y, x), dead-simple. from geogif import gif, dgif gif(data_array) dgif(dask_data_array).compute() The “geo” part is a lie, actually. The arrays don’t have to be geospatial in nature. But I called it GeoGIF because: Wanting to animate a time-stack of imagery (like you’d get from stackstac) is a common task in the earth-observation/geospatial world. I think GeoGIF is a hilarious idea1. 1: To ruin the joke, it sounds like GeoTIFF, a ubiquitous geospatial […]

Read more
1 … 655 656 657 658 659 … 935