Semi-supervised

Semi-supervised Semantic Segmentation with Directional Context-aware Consistency

Semi-supervised Semantic Segmentation with Directional Context-aware Consistency (CAC) Xin Lai*, Zhuotao Tian*, Li Jiang, Shu Liu, Hengshuang Zhao, Liwei Wang, Jiaya Jia This is the official PyTorch implementation of our paper Semi-supervised Semantic Segmentation with Directional Context-aware Consistency that has been accepted to 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021). [Paper] Our method achives the state-of-the-art performance on semi-supervised semantic segmentation. Based on CCT, this Repository also supports efficient distributed training with multiple GPUs. Environment The […]

Read more
Scripts

Generate direct m3u playlist for all the channels subscribed in the Tata Sky portal

A script to generate the m3u playlist containing direct streamable file (.mpd or MPEG-DASH or DASH) based on the channels that the user has subscribed on the Tata Sky portal. You just have to login using your password or otp that’s it A working brain Knowledge of basic python A working Tata Sky account Channels that you want to watch, already subscribed (I’m sorry, no freebies) You can simply use the android app in your mobile phone or TV, login […]

Read more
JAX

A Gaussian process (GP) library built in JAX (with objax)

Newt Newt is a Gaussian process (GP) library built in JAX (with objax), built and actively maintained by Will Wilkinson. Newt provides a unifying view of approximate Bayesian inference for GPs, and allows for the combination of many models (e.g. GPs, sparse GPs, Markov GPs, sparse Markov GPs) with the inference method of your choice (VI, EP, Laplace, Linearisation). For a full list of the methods implemented scroll down to the bottom of this page. Installation In the top directory […]

Read more
Transformer

A fast and easy implementation of Transformer with PyTorch

FasySeq FasySeq is a shorthand as a Fast and easy sequential modeling toolkit. It aims to provide a seq2seq model to researchers and developers, which can be trained efficiently and modified easily. This toolkit is based on Transformer(Vaswani et al.), and will add more seq2seq models in the future. Dependency PyTorch >= 1.4 NLTK Result … Structure … To Be Updated top-k and top-p sampling multi-GPU inference length penalty in beam search … Preprocess Build Vocabulary createVocab.py NamedArguments Description -f/–file […]

Read more
Detection

Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection

QueryDet-PyTorch This repository is the official implementation of our paper: QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection Requirement a. Install Pytorch 1.4 b. Install APEX for mixed precision training c. Install our Pytorch based sparse convolution toolkit d. Install the detectron2 toolkit. Note we build our approach based on version 0.2.1, you may follow the instructions to set environment configs e. Install the Detectron2_Backbone for usage of MobileNet and ShuffleNet f. Clone our repository and have fun […]

Read more
Telegram

A Telegram bot for remotely managing Binance Trade Bot

Binance Trade Bot Manager Telegram A Telegram bot for remotely managing Binance Trade Bot. About I wanted to develop an easy way of managing [Binance Trade Bot] so that I wouldn’t have to constantly ssh into my VPS, and my non-techy friends could enjoy the benefits of automated trading. As of now the bot is able to perform the following actions: [x] 🔍 Check bot status (running / not running) [x] ▶ Start Binance Trade Bot [x] ⏹ Stop Binance […]

Read more
Detection

Multi-Scale Aligned Distillation for Low-Resolution Detection

Multi-Scale Aligned Distillation for Low-Resolution Detection Lu Qi*, Jason Kuen*, Jiuxiang Gu, Zhe Lin, Yi Wang, Yukang Chen, Yanwei Li, Jiaya Jia This project provides an implementation for the CVPR 2021 paper “Multi-Scale Aligned Distillation for Low-Resolution Detection” based on Detectron2. MSAD targets to detect objects using low-resolution instead of high-resolution image. MSAD could obtain comparable performance in high-resolution image size. Our paper use Slimmable Neural Networks as our pretrained weight. Installation This project is based on Detectron2, which can […]

Read more
Deep Learning

A gym style toolkit for building lightweight NAS systems

gymnastics A “gym” style toolkit for building lightweight Neural Architecture Search systems. I know, the name is awful. Installation Preferred option: Install from source: git clone [email protected]:jack-willturner/gymnastics.git cd gymnastics python setup.py install To install the latest release version: pip install gymnastics If you want to use NAS-Bench-101, follow the instructions here to get it set up. Overview Over the course of the final year of my PhD I worked a lot on Neural Architecture Search (NAS) and built a bunch […]

Read more
Transformer

The “tl;dr” on a few notable transformer papers

# tldr-transformers The tl;dr on a few notable transformer/language model papers + other papers (alignment, memorization, etc). Models: GPT- *, * BERT *, Adapter- *, * T5, etc. Each set of notes includes links to the paper, the original code implementation (if available) and the Huggingface :hugs: implementation. Here is an example: t5. The transformers papers are presented somewhat chronologically below. Go to the “:point_right: Notes :point_left:” column below to find the notes for each paper. This repo also includes […]

Read more
Neural Network

A PyTorch library to analyze representation of neural networks

anatome Ἀνατομή is a PyTorch library to analyze internal representation of neural networks This project is under active development and the codebase is subject to change. Installation anatome requires Python>=3.9.0 PyTorch>=1.9.0 torchvision>=0.10.0 After the installation of PyTorch, install anatome as follows: pip install -U git+https://github.com/moskomule/anatome Representation Similarity To measure the similarity of learned representation, anatome.SimilarityHook is a useful tool. Currently, the followingmethods are implemented. from anatome import SimilarityHook model = resnet18() hook1 = SimilarityHook(model, “layer3.0.conv1”) hook2 = SimilarityHook(model, “layer3.0.conv2”) model.eval() […]

Read more
1 … 533 534 535 536 537 … 947