naphjohn Goto Github PK

notable

The Markdown-based note-taking app that doesn't suck.

nvidia-container-runtime

NVIDIA container runtime

observations

on-lstm

Keras implement of ON-LSTM (Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks)

open3d

Open3D: A Modern Library for 3D Data Processing

paddledetection

Object detection and instance segmentation toolkit based on PaddlePaddle.

paddleocr

Awesome multilingual OCR toolkits based on PaddlePaddle （practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices）

piggymetrics

Microservice Architecture with Spring Boot, Spring Cloud and Docker

protmd

python-100-days

Python - 100天从新手到大师

python-api-tesing

python中文库-python人工智能大数据自动化接口测试开发。 书籍下载及python库汇总https://china-testing.github.io/

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch-tutorial

PyTorch Tutorial for Deep Learning Researchers

qtwuziqi

Qt 写的五子棋小游戏，带AI和双人对战

re-balanced-vae

Code for our paper Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation.

recommended-books

计算机经典书籍推荐 部分书籍提供PDF下载

rekcarc-tsc-uht

清华大学计算机系课程攻略 Guidance for courses in Department of Computer Science and Technology, Tsinghua University

scikit-learn

scikit-learn: machine learning in Python

sec-chart

安全思维导图集合

shamecom

收集校招污点公司或组织，帮助学弟学妹避雷。互联网不曾遗忘！

shape-and-action-unit-extraction-of-3d-human-face-meshes-by-multilinear-dimensionality-reduction

This work aims to create a model able to discern the parameters of shape and action units from 3D human face meshes. The adopted dataset was acquired by using Kinect and consist of 360 3D representation of human faces. More precisely, 20 different users performed 6 specific facial expressions (happy, sad, scared, angry, disgusted, surprised) by using 3 emphasis degree (low, medium, high). The collected dataset was labelled and then modelled in a three-dimensional tensor. Then, a multilinear dimensionality reduction technique (Higher-order singular value decomposition - HOSVD) was applied to separately extract the face deformation features related to the shape units and the action units. These specific features are finally exploited to independently rebuild the user human face by using much fewer data with respect to the starting dataset, specifically the 83% less, maintaining approximately 90% of variance.

spring-boot-in-action

Spring Boot 系列实战合集

swin-transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

system-design-primer

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

tensorflow2_tutorials_chinese

tensorflow2中文教程，持续更新(当前版本:tensorflow2.0)，tag: tensorflow 2.0 tutorials

the-art-of-command-line

Master the command line, in one page

thu-cst-cracker

清华大学计算机系课程攻略

tutorials

机器学习相关教程

unet

unet for image segmentation

voxelize-image