Deep Learning

The project for the most brutal and effective language learning technique

– “The project for the most brutal and effective language learning technique” (c) Alex Kay The langflow project was created especially for language learning by using the most direct way. A method demands to work passionately and regularly. The main idea of the method is constant recall by students writing sentences in language which he would like to improve! The natural way of learning by this technique reminds supervised learning which became one the most effective ways in ML. Just […]

Read more
Tool

Additional useful operations for Python

Additional useful operations for Python Available Operations MulDiv64: calculate m1*m2/d with no overflow on multiplication (TEAL 3+) Min, Max: calculate minimum/maximum of 2 expressions, without using slots or evaluating arguments more than once (TEAL 4+) LazyAnd, LazyOr: lazily evaluate arguments in And/Or operation State manipulation GlobalState and LocalState allow for manipulating global and local state respectively. They both have the same interface. from pyteal import App, Bytes, Int, Seq, TealType from pytealext import LocalState user_counter = LocalState(“UC”, TealType.uint64) program

Read more
Webhooks

An API endpoint for stock, forex and cryptocurrency exchanges that accept REST webhooks

Jackrabbit Relay is an API endpoint for stock, forex and cryptocurrency exchanges that accept REST webhooks. Disclaimer Please note RAPMD Crypto, LLC (“the Company”), does not provide financial advice. The Company, and any associated companies, owners, employees, agents or volunteers, do not hold themselves out as Commodity Trading Advisors (“CTAs”) or Authorized Financial Advisors (“AFAs”). The owners, publishers, employees and agents are not licensed under securities laws to address particular investment situations. No information presented constitutes a recommendation to buy, […]

Read more
Email

Send email notification when receiving Facebook message

This repository has a small Python application which will allow you to receive an email notification when somebody sends you a Facebook message. Why? I don’t like Facebook as a company, and I don’t want to support them by using their products, including Messenger. However, when I came around to this point of view, I already had a number of existing contacts on Messenger. I migrated everyone I talked to regularly onto other platforms, but in case someone messaged me […]

Read more
Semantic

An efficient 3D semantic segmentation framework for Urban-scale point clouds like SensatUrban, Campus3D, etc

This is the official implementation of our BEV-Seg3D-Net, an efficient 3D semantic segmentation framework for Urban-scale point clouds like SensatUrban, Campus3D, etc. Features of our framework/model: leveraging various proven methods in 2D segmentation for 3D tasks achieve competitive performance in the SensatUrban benchmark fast inference process, about 1km^2 area per minute with RTX 3090. To be done: add more complex/efficient fusion models add more backbone like ResNeXt, HRNet, DenseNet, etc. add more novel projection methods like pointpillars For technical details, […]

Read more
Attention

Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation

This repo hosts the code to accompany the camera-ready version of “Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation” in EMNLP 2021. Setup We provide our scripts and modifications to Fairseq. In this section, we describe how to go about running the code and, for instance, reproduce Table 2 in the paper. Data To view the data as we prepared and used it, switch to the main branch. But we recommend cloning code from this branch to […]

Read more
Deep Learning

GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition

This paper is the code release of the paper GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition, which is accepted at EACL-2021. This work aims at improving weakly supervised named entity reconigtion systems by automatically finding new rules that are helpful at identifying entities from data. The idea is, as shown in the following figure, if we know rule1: associated with->Disease is an accurate rule and it is semantically related to rule2: cause of->Disease, we should be […]

Read more
ffmpeg

Run an FFmpeg command and see the percentage progress and ETA

A command line program that runs an FFmpeg command and shows the following in addition to the FFmpeg output: Percentage Progress Speed ETA (minutes and seconds) Example: Progress: 25% | Speed: 22.3x | ETA: 1m 33s python3 better_ffmpeg_progress.py -c “ffmpeg -i input.mp4 -c:a libmp3lame output.mp3” I have also included a function, which can be imported and used in your own Python program or script: run_ffmpeg_show_progress(“ffmpeg -i input.mp4 -c:a libmp3lame output.mp3”) GitHub https://github.com/CrypticSignal/better-ffmpeg-progress    

Read more
Real Time

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation

This repository contains the implementation of the following paper: Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation Yuanxun Lu, Jinxiang Chai, Xun Cao (SIGGRAPH Asia 2021) Abstract: To the best of our knowledge, we first present a live system that generates personalized photorealistic talking-head animation only driven by audio signals at over 30 fps. Our system contains three stages. The first stage is a deep neural network that extracts deep audio features along with a manifold projection to project the features […]

Read more
1 … 544 545 546 547 548 … 1,025