Month: July 2021

Machine Learning

A PyTorch implementation of Capsule Graph Neural Network

CapsGNN A PyTorch implementation of Capsule Graph Neural Network (ICLR 2019). Abstract The high-quality node embeddings learned from the Graph Neural Networks (GNNs) have been applied to a wide range of node-based applications and some of them have achieved state-of-the-art (SOTA) performance. However, when applying node embeddings learned from GNNs to generate graph embeddings, the scalar node representation may not suffice to preserve the node/graph properties efficiently, resulting in sub-optimal graph embeddings. Inspired by the Capsule Neural Network (CapsNet), we […]

Read more
Machine Learning

Watch Your Step: Learning Node Embeddings via Graph Attention

Attention Walk A PyTorch Implementation of Watch Your Step: Learning Node Embeddings via Graph Attention (NIPS 2018). Abstract Graph embedding methods represent nodes in a continuous vector space, preserving different types of relational information from the graph. There are many hyper-parameters to these methods (e.g. the length of a random walk) which have to be manually tuned for every graph. In this paper, we replace previously fixed hyper-parameters with trainable ones that we automatically learn via backpropagation. In particular, we […]

Read more
Algorithms

An implementation of the proximal policy optimization algorithm

PPO Pytorch C++ This is an implementation of the proximal policy optimization algorithm for the C++ API of Pytorch. It uses a simple TestEnvironment to test the algorithm. Below is a small visualization of the environment, the algorithm is tested in. Build You first need to install PyTorch. For a clean installation from Anaconda, checkout this short tutorial, or this tutorial, to only install the binaries. Do mkdir build cd build cmake -DCMAKE_PREFIX_PATH=/absolut/path/to/libtorch .. make Run Run the executable with […]

Read more
Python

Your First Steps With Django: Set Up a Django Project

Django is a high-level Python Web framework that encourages rapid development and clean, pragmatic design. In this tutorial we’ll be answering the question “How do I setup a Django (1.5, 1.6, 1.7, or 1.8) project from scratch?” In other words, you’ll learn how to install Django and how to set up your Django project structure. Here’s how you can make the most of this tutorial: Read over the Introduction and Setup sections. Then choose your poison – Django 1.5, 1.6, […]

Read more
Deep Learning

Pre-trained models for high-performance deep learning applications in python

Hailo Model Zoo The Hailo Model Zoo provides pre-trained models for high-performance deep learning applications. Using the Hailo Model Zoo you can measure the full precision accuracy of each model, the quantized accuracy using the Hailo Emulator and measure the accuracy on the Hailo-8 device. Finally, you will be able to generate the Hailo Executable Format (HEF) binary file to speed-up development and generate high quality applications accelerated with Hailo-8. The models are optimized for high accuracy on public datasets […]

Read more
PDF

A Python tool to generate a static HTML file that represents the internal structure of a PDF file

A Python tool to generate a static HTML file that represents the internal structure of a PDF file At some point the low-level functions developed for this CLI will be exposed as an API for programmatic use. WORK IN PROGRESS! CLI Features The generated HTML looks like the raw PDF file with the following additions: Pretty-print dictionary object Extract an object contained in an object stream and insert it in the flow like a regular object Decompress stream and display […]

Read more
Twitter

Quickly and efficiently delete your entire tweet history with the help of your Twitter archive

Twitter Nuke Quickly and efficiently delete your entire tweet history with the help of your Twitter archive without worrying about the puny and pointless 3200 tweet limit imposed by Twitter. About The script uses multithreading to speed up the deletion process by simultaneously running multiple instances of the Twitter API. By utilising this modification the speed can be improved upto ~50-60 times the single threaded performance (~1 tweet per sec). Features Set the number of likes and retweets as threshold […]

Read more
Models

Bonsai: Gradient Boosted Trees + Bayesian Optimization

Bonsai Bonsai is a wrapper for the XGBoost and Catboost model training pipelines that leverages Bayesian optimization for computationally efficient hyperparameter tuning. Despite being a very small package, it has access to nearly all of the configurable parameters in XGBoost and CatBoost as well as the BayesianOptimization package allowing users to specify unique objectives, metrics, parameter search ranges, and search policies. This is made possible thanks to the strong similarities between both libraries. $ pip install bonsai-tree References/Dependencies: Why use […]

Read more
Transformer

AST: Audio Spectrogram Transformer

AST This repository contains the official implementation (in PyTorch) of the Audio Spectrogram Transformer (AST) proposed in the Interspeech 2021 paper AST: Audio Spectrogram Transformer (Yuan Gong, Yu-An Chung, James Glass). AST is the first convolution-free, purely attention-based model for audio classification which supports variable length input and can be applied to various tasks. We evaluate AST on various audio classification benchmarks, where it achieves new state-of-the-art results of 0.485 mAP on AudioSet, 95.6% accuracy on ESC-50, and 98.1% accuracy […]

Read more
1 … 15 16 17 18 19 … 52