Author: Deep Learner

Uncategorized Leave a comment

µTransfer: A technique for hyperparameter tuning of enormous neural networks

Great scientific achievements cannot be made by trial and error alone. Every launch in the space program is underpinned by centuries of fundamental research in aerodynamics, propulsion, and celestial bodies. In the same way, when it comes to building large-scale AI systems, fundamental research forms the theoretical insights that drastically reduce the amount of trial and error necessary and can prove very cost-effective.  In this post, we relay how our fundamental research enabled us, for the first time, to tune […]

Read more
Message

Small VK userbot to substitute some message parts with other message parts, cross or underline text, and add images to a message

WARNING: “substitutions” are just text substitutions, while “attachments” are being added to the current message as attachments Also don’t forget to put your token in token.txt, you know… attachments.json SHOULD NOT BE FILLED MANUALLY!substitutions.json SHOULD BE FILLED MANUALLY! (format: {“pattern”: “substitution”, “pattern”: “substitution”, …}) uline and cross do not depend on any of the configs.If you surround some text with the uline macro, the text surrounded will be underlined,if you surround some text with the cross macro, the text surrounded […]

Read more
Converter

Convert scikit-learn models to PyTorch modules

sk2torch converts scikit-learn models into PyTorch modules that can be tuned with backpropagation and even compiled as TorchScript. Problems solved by this project: scikit-learn cannot perform inference on a GPU. Models like SVMs have a lot to gain from fast GPU primitives, and converting the models to PyTorch gives immediate access to these primitives. While scikit-learn supports serialization through pickle, saved models are not reproducible across versions of the library. On the other hand, TorchScript provides a convenient, safe way […]

Read more
Images

Self-Distilled Internet Photos (SDIP) Dataset

Self-Distilled Internet Photos (SDIP) is a multi-domain image dataset. The dataset consists of Self-Distilled Flickr (SD-Flickr) and Self-Distilled LSUN (SD-LSUN) that were crawled from Flickr and LSUN dataset, respectively, and then curated using the method described in our Self-Distilled StyleGAN paper: Self-Distilled StyleGAN: Towards Generation from Internet PhotosRon Mokady, Michal Yarom, Omer Tov, Oran Lang, Daniel Cohen-Or, Tali Dekel, Michal Irani, Inbar Mosserihttps://arxiv.org/abs/2202.12211 Overview StyleGAN’s fascinating generative and editing abilities are limited to structurally aligned and well-curated datasets. It does […]

Read more
Telegram

Go live easily and stream videos in Telegram channels

A bot for streaming in Telegram RTMP streams. Get Started Use a Cloud Platform Manually Prerequisites Configure In order to configure the bot, you have to set the following environmental variables: APP_HASH APP_ID BOT_TOKEN RTMP_KEY RTMP_URL Or put them in a .env in the root. Install Run poetry run python -m trtmp Commands Currently, TRTMP has 2 commands. To request more features and commands, talk to usin @CallsMusicChat. Note: Commands are triggered with the “/” prefix. stream As you may […]

Read more
Raspberry Pi

A simple speech jammer using auditory delayed feedback for raspberry pi

A simple speech jammer using auditory delayed feedback for raspberry pi This script is intended to work on a Raspberry Pi device running Raspberry Pi OS.You’ll also need a usb sound card with a microphone, headset and any type of bluetooth gamepad/controller to make it work. -Install EVDEV and find your bluetooth controller name and button codes using this tutorial: https://raspberry-valley.azurewebsites.net/Map-Bluetooth-Controller-using-Python/ -Disable HDMI and default audio output on Raspberry Pi OS so the script can correctly find your USB sound […]

Read more
Backdoor

AV evading OSX Backdoor and Crypter Framework

OSripper is a fully undetectable Backdoor generator and Crypter which specialises in OSX M1 malware. Even though it specialises in OSX malware it also works well for generating windows malware. It now not only generates normal unix executables but also .apps. Description OSripper not only generates backdoors but also obfuscates and compiles them. This also includes apple M1 backdoors. Take a closer look at the Roadmap to see how close we are to achieving our goal of total evasion but […]

Read more
Uncategorized

Official Pytorch implementation of 6DRepNet: 6D Rotation representation for unconstrained head pose estimation

Paper Thorsten Hempel and Ahmed A. Abdelrahman and Ayoub Al-Hamadi, “6D Rotation Representation for Unconstrained Head Pose Estimation”, submitted to ICIP 2022. [ResearchGate][Arxiv] Abstract In this paper, we present a method for unconstrained end-to-end head pose estimation. We address the problem of ambiguous rotation labels by introducing the rotation matrix formalism for our ground truth data and propose a continuous 6D rotation matrix representation for efficient and robust direct regression. This way, our method can learn the full rotation appearance […]

Read more
1 … 245 246 247 248 249 … 978