hj0711 Goto Github PK

30daysofflutter

adp

Python code for ADP test

bsn-boundary-sensitive-network

Codes of our paper: "BSN: Boundary Sensitive Network for Temporal Action Proposal Generation"

cocoapi

Clone of COCO API - Dataset @ http://cocodataset.org/ - with changes to support Windows build and python3

ctap

ECCV2018 CTAP: Complementary Temporal Action Proposal Generation

darkpose

Distribution-Aware Coordinate Representation for Human Pose Estimation

deep-learning-from-scratch

『밑바닥부터 시작하는 딥러닝』(한빛미디어, 2017)

deep-svdd-pytorch

A PyTorch implementation of the Deep SVDD anomaly detection method

deep_gcns

Tensorflow Repo for "DeepGCNs: Can GCNs Go as Deep as CNNs?" ICCV2019 Oral https://www.deepgcns.org

flutter

flutter_lamp

Lamp plugin for flutter

gan-tts

A pytroch implementation of the GAN-TTS: HIGH FIDELITY SPEECH SYNTHESIS WITH ADVERSARIAL NETWORKS

gtad

The official implementation of G-TAD: Sub-Graph Localization for Temporal Action Detection

handson-ml2

핸즈온 머신러닝 2/E의 주피터 노트북

human-pose-annotation-tool

Human Pose Annotation Tool

instance-segmentation-on-wbc-using-mask-r_cnn

Using Matterport's Mask R-CNN to perform instance segmentation on WBC in blood samples and detect the 5 types of WBC.

janis

kinetics_i3d_pytorch

Inflated i3d network with inception backbone, weights transfered from tensorflow

lmkor

Pretrained Language Models for Korean

mask_rcnn

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

medicaldetectiontoolkit

The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.

mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

motion-sense

MotionSense Dataset for Human Activity and Attribute Recognition ( time-series data generated by smartphone's sensors: accelerometer and gyroscope) (PMC Journal) (IoTDI'19)

naive_bayes

nlp-for-fake-news-detection

We consume news through several mediums throughout the day in our daily routine, but sometimes it becomes difficult to decide which one is fake and which one is authentic. Do you trust all the news you consume from online media? Every news that we consume is not real. If you listen to fake news it means you are collecting the wrong information from the world which can affect society because a person’s views or thoughts can change after consuming fake news which the user perceives to be true. Since all the news we encounter in our day-to-day life is not authentic, how do we categorize if the news is fake or real? In this article, we will focus on text-based news and try to build a model that will help us to identify if a piece of given news is fake or real. Before moving to the practical things let’s get aware of few terminologies. A sort of sensationalist reporting, counterfeit news embodies bits of information that might be lies and is, for the most part, spread through web-based media and other online media. This is regularly done to further or force certain kinds of thoughts or for false promotion of products and is frequently accomplished with political plans. Such news things may contain bogus and additionally misrepresented cases and may wind up being virtualized by calculations, and clients may wind up in a channel bubble.

nsmc

Naver sentiment movie corpus

openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

pgcn

Graph Convolutional Networks for Temporal Action Localization (ICCV2019)

py-denseflow

Extract TVL1 optical flows in python (multi-process && multi-server)

pygcn

Graph Convolutional Networks in PyTorch