July 10, 2021 Transformer

Chasing Sparsity in Vision Transformers: An End-to-End Exploration

SViTE [Preprint] “Chasing Sparsity in Vision Transformers: An End-to-End Exploration” by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang Extensive results on ImageNet with diverse ViT backbones validate the effectiveness of our proposals which obtain significantly reduced computational cost and almost unimpaired generalization. Perhaps most surprisingly, we find that the proposed sparse (co-)training can even improve the ViT accuracy rather than compromising it, making sparsity a tantalizing “free lunch”. For example, our sparsified DeiT-Small at (5%, […]

July 10, 2021 Graph

A text-based visual programming language inspired by Unreal Engine blueprint function graphs

Box Box is a text-based visual programming language inspired by Unreal Engine blueprint function graphs. $ cat factorial.box ┌─ƒ(Factorial)───┐ ┌─[Branch]─────┐ ┌─[Set]─┐ │ ►┼─────────────────────┼► True ►┼───────────────────────┼► ►┼─────────┐ ┌─[For Loop]───────────┐ ┌───────┐ │ n ○┼──┐ ┌──┼○ False ►┼──┐ ┌──────────┐ ┌───┼○ │ └─────────┼► Loop body ►┼───────────────────┼► │ └────────────────┘ │ ┌────────┐ │ │ │ │ │ result ○┼──┘ ┌─┼○ │ │ │ ┌──────────┐ ┌────┼○ *= │ ┌────┐ └────┼○ >= ○┼─┘ └──────────────┘ │ └──────────┘ │ └───────┘ ┌────┐ │ │ │ result ○┼─┘ ┌─┼○ │ │ 1 […]

July 10, 2021 Assistant

Dahua Camera and Doorbell Home Assistant Integration

Home Assistant Dahua Integration The Dahua Home Assistant integration allows you to integrate your Dahua cameras and doorbells in Home Assistant. It’s also confirmed to work with some Lorex cameras. Supports motion events, alarm events (and others), enabling/disabling motion detection, switches for infrared, illuminator (white light), security lights (red/blue flashers), sirens, doorbell button press events, and more. Also exposes several services to enable/disable motion detection or set the text overlay on the video. NOTE: Using the switch to turn on/off […]

July 10, 2021 HTTP

An awesome library that records and replays HTTP interactions for unit tests

Cornell: record & replay mock server When your application integrates with multiple web based services, end-to-end testing is crucial before deploying to production. Mocking is often a tedious task, it becomes even more tiresome when working with multiple APIs from multiple vendors. vcrpy is an awesome library that records and replays HTTP interactions for unit tests. Its output is saved to reusable “cassette” files. By wrapping vcrpy with Flask, Cornell provides a lightweight record and replay server that can be […]

July 10, 2021 Data Analysis

Manage your exceptions in Python like a PRO

tryceratops Manage your exceptions in Python like a PRO. Installation and usage Installation pip install tryceratops Usage tryceratops [filename or dir…] You can enable experimental analyzers by running: tryceratops –experimental [filename or dir…] You can ignore specific violations by using: –ignore TCXXX repeatedly: tryceratops –ignore TC201 –ignore TC202 [filename or dir…] You can exclude dirs by using: –exclude dir/path repeatedly: tryceratops –exclude tests –exclude .venv [filename or dir…] Violations All violations and its descriptions can be found in docs. Ignoring […]

July 10, 2021 Images

A suite of image generation models that produce images from simple random processes

Learning to See by Looking at Noise In this work, we investigate a suite of image generation models that produce images from simple random processes. These are then used as training data for a visual representation learner with a contrastive loss. We study two types of noise processes, statistical image models and deep generative models under different random initializations. Requirements This version of code has been tested with Python 3.7.7 and pytorch 1.6.0. Other versions of pytorch are likely to […]

July 10, 2021 GUI

Make NixOS usable for non-technical users through a settings / package management GUI

Nix-Gui Make NixOS usable for non-technical users through a settings / package management GUI. Motives The declarative nature of NixOS provides it the capability of being the most user friendly linux distro. No more editing dotfiles, /etc files, manually writing timers, services, running commands to manage and create users and groups, etc. NixOS integrates all of that into a declarative system, and this project integrates NixOS’ declarative system into a GUI. Serve Users Unfamiliar with or Learning Nix Nix-Gui is […]

July 10, 2021 Machine Learning

Push your spaCy pipelines to the Hugging Face Hub

spacy-huggingface-hub This package provides a CLI command for uploading any trained spaCy pipeline packaged with spacy package to the Hugging Face Hub. It auto-generates all meta information for you, uploads a pretty README (requires spaCy v3.1+) and handles version control under the hood. About the Hugging Face Hub The Hugging Face Hub hosts Git-based repositories which are storage spaces that can contain all your files. These repositories have multiple advantages: versioning (commit history and diffs), branches, useful metadata about their […]

July 10, 2021 Search

A fast and feature-rich CTC beam search decoder for speech recognition with python

pyctcdecode A fast and feature-rich CTC beam search decoder for speech recognition written in Python, providing n-gram (kenlm) language model support similar to PaddlePaddle’s decoder, but incorporating many new features such as byte pair encoding and real-time decoding to support models like Nvidia’s Conformer-CTC or Facebook’s Wav2Vec2. pip install pyctcdecode Main Features: 🔥 hotword boosting 🤖 handling of BPE vocabulary 👥 multi-LM support for 2+ models 🕒 stateful LM for real-time decoding ✨ native frame index annotation of words 💨 fast runtime, comparable to C++ implementation […]

July 10, 2021 Network

Unofficial implementation of Alias-Free Generative Adversarial Networks

alias-free-gan-pytorch Unofficial implementation of Alias-Free Generative Adversarial Networks. (https://arxiv.org/abs/2106.12423) This implementation contains a lot of my guesses, so I think there are many differences to the official implementations Usage First create lmdb datasets: python prepare_data.py –out LMDB_PATH –n_worker N_WORKER –size SIZE1,SIZE2,SIZE3,… DATASET_PATH This will convert images to jpeg and pre-resizes it. This implementation does not use progressive growing, but you can create multiple resolution datasets using size arguments with comma separated lists, for the cases that you want to try […]

« 1 … 556 557 558 559 560 … 912 »