sudabai666 Goto Github PK

focuscut

The official PyTorch implementation of oral paper "FocusCut: Diving into a Focus View in Interactive Segmentation" in CVPR 2022.

gcpanet

Global Context-Aware Progressive Aggregation Network for Salient Object Detection

high-fidelity-generative-compression

Pytorch implementation of High-Fidelity Generative Image Compression + Routines for neural image compression

iphonemocapios

mead

MEAD: A Large-scale Audio-visual Dataset for Emotional Talking-face Generation [ECCV2020]

mediapipe-demo-hand-detection

This project is written in Kotlin which makes it easier for android developers to implement hand detection feature.

mmdetection

OpenMMLab Detection Toolbox and Benchmark

mnn_pc_demo

mnnkitdemo

MNN Kit Demo

model-compression

model compression based on pytorch (1、quantization: 16/8/4/2 bits(dorefa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular and group convolutional channel pruning；3、 group convolution structure；4、batch-normalization folding for quantization)

modnet

A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]

openpose

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

openseeface

Robust realtime face and facial landmark tracking with Unity integration

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)

paper_list

peppa_pig_face_engine

A simple face detect and alignment method, which is easy and stable.

pfld-pytorch

PFLD pytorch Implementation

recipe

reconstructing_faces_from_voices

Implementation of the "Reconstructing Faces from Voices" paper.

resnet-protofiles

Caffe Protofiles for MSRA ResNet: train prototxt

salt

Segment Anything Labelling Tool

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

simple-faster-rcnn-pytorch

A simplified implemention of Faster R-CNN that replicate performance from origin paper

sophie_test

sppnet-pytorch

A simple Spatial Pyramid Pooling layer which could be added in CNN

stanet

sudabai.github.io

BY Blog ->

thin-object-selection

Deep Interactive Thin Object Selection

to-learn

tuta_table_understanding

TUTA and ForTaP for Structure-Aware and Numerical-Reasoning-Aware Table Pre-Training