Attack

A Python framework for adversarial attacks and model training in NLP

TextAttack TextAttack is a Python framework for adversarial attacks, data augmentation, and model training in NLP. If you’re looking for information about TextAttack’s menagerie of pre-trained models, you might want the TextAttack Model Zoo page. Slack Channel For help and realtime updates related to TextAttack, please join the TextAttack Slack! Why TextAttack? There are lots of reasons to use TextAttack: Understand NLP models better by running different adversarial attacks on them and examining the output Research and develop different NLP […]

Read more
Network

Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing

R²SQL The PyTorch implementation of paper Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing. (AAAI 2021) Requirements The model is tested in python 3.6 with following requirements: torch==1.0.0 transformers==2.10.0 sqlparse pymysql progressbar nltk numpy six spacy All experiments on SParC and CoSQL datasets were run on NVIDIA V100 GPU with 32GB GPU memory. Tips: The 16GB GPU memory may appear out-of-memory error. Setup The SParC and CoSQL experiments in two different folders, you need to download different datasets from […]

Read more
Generator

Procedural 3D data generation pipeline for architecture in python

Synthetic Dataset Generator This is a tool that generates a dataset of synthetic buildings of different typologies. The generated data includes: Mesh files of generated buildings, .obj format Rendered images of the mesh, .png format Rendered segmentation masks, .png format Depth annotation, .png and .exr format Surface normals annotation, .png format Point cloud files, .ply format (the number of points by default is 2048, can be changed in dataset_config.py) How To Use Install Blender>=2.90. After installation make sure to add […]

Read more
Tutorial

How to setup a multi-client ethereum Eth1-Eth2 merge testnet with python

Mergenet tutorial How to setup a multi-client ethereum Eth1-Eth2 merge testnet with python Preparing the setup environment In this tutorial, we use a series of scripts to generate configurationfiles, and these scripts have dependencies that we need toinstall. You can either install these dependencies on your host or youcan run those scripts inside a docker container. We call thisenvironment setupenv. Preparing the setup environment on your host: apt-get install python3-dev python3-pip python3-venv golang # Check that you have Go 1.16+ […]

Read more
Command-line Tools

Like the unix tree command but for GCP Org Heirarchy

gcptree Like the unix tree command but for GCP Org Heirarchy. For a note on coloring, the org node is green, folders and blue, and projects that are not ACTIVE are dimmed. These styles won’t show up if you redirect output and Windows is supported by virtue of the colorama package. pip install gcptree First make sure you are authenticated to gcloud and have your application default credentials set using: gcloud auth login –update-adc You just need your org id, […]

Read more
IRC

A bouncer-style Matrix IRC bridge in python

Heisenbridge a bouncer-style Matrix IRC bridge. Heisenbridge brings IRC to Matrix by creating an environment where every user connects to each network individually like they would with a traditional IRC bouncer. Simplicity is achieved by exposing IRC in the most straightforward way as possible where it makes sense so it feels familiar for long time IRC users. Please file an issue when you find something is missing or isn’t working that you’d like to see fixed. Pull requests are more […]

Read more
Tool

A collection of Blender tools Build With Python

A collection of Blender tools I’ve written for myself over the years. I use these daily so they should be bug-free, mostly. Feel free to take and use any parts of this project. gret can be typed with one hand in the search bar. Blender 2.92 or later required. Download the latest release. In Blender, go to Edit → Preferences → Add-ons → Install. Find and select the downloaded zip file, then click Install Add-on. Enable the add-on by clicking […]

Read more
JAX

A Mixed Precision library for JAX in python

Mixed precision training in JAX Mixed precision training [0] is a technique that mixes the use of full andhalf precision floating point numbers during training to reduce the memorybandwidth requirements and improve the computational efficiency of a givenmodel. This library implements support for mixed precision training in JAX by providingtwo key abstractions (mixed precision “policies” and loss scaling). Neuralnetwork libraries (such as Haiku) can integrate with jmp and provide“Automatic Mixed Precision (AMP)” support (automating or simplifying applyingpolicies to modules). All […]

Read more
Network

Attention in Attention Network for Image Super-Resolution

A2N This repository is an PyTorch implementation of the paper “Attention in Attention Network for Image Super-Resolution” [arXiv] Visual results in the paper are availble at Google Drive or Baidu Netdisk (password: 7t74). Unofficial TensorFlow implementation: https://github.com/Anuj040/superres Test Dependecies: PyTorch==0.4.1 (Will be updated to support PyTorch>1.0 in the future) You can download the test sets from Google Drive. Put the test data in ../Data/benchmark/. python main.py –scale 4 –data_test Set5 –pre_train ./experiment/model/aan_x4.pt –chop –test_only If you use CPU, please add […]

Read more
Machine Learning

Unsupervised Pre-training for Person Re-identification

LUPerson The repository is for our CVPR2021 paper Unsupervised Pre-training for Person Re-identification. LUPerson Dataset LUPerson is currently the largest unlabeled dataset for Person Re-identification, which is used for Unsupervised Pre-training. LUPerson consists of 4M images of over 200K identities and covers a much diverse range of capturing environments. Details can be found at ./LUP. Pre-trained Models Finetuned Results For MGN with ResNet50: Dataset mAP cmc1 path MSMT17 66.06/79.93 85.08/87.63 MSMT DukeMTMC 82.27/91.70 90.35/92.82 Duke Market1501 91.12/96.16 96.26/97.12 Market CUHK03-L […]

Read more
1 … 627 628 629 630 631 … 1,024