eLavin11's repositories
3d-ken-burns
an implementation of 3D Ken Burns Effect from a Single Image using PyTorch
CRAFT-pytorch
Pytorch implementation of CRAFT text detector
Cross-modal-retrieval
Activity image-based video retrieval
cvat
Powerful and efficient Computer Vision Annotation Tool (CVAT)
Cycle-IR
This is a Tensorflow implementation of Cycle-IR approach for content-aware image retargeting.
Decoupled-attention-network
Pytorch implementation for "Decoupled attention network for text recognition".
DeepNude-an-Image-to-Image-technology
DeepNude's algorithm and general image generation theory and practice research, including pix2pix, CycleGAN, UGATIT, DCGAN, SinGAN and VAE models (TensorFlow2 implementation). DeepNude的算法以及通用GAN图像生成的理论与实践研究。
DewarpNet
Code for the paper "DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks" (ICCV '19)
fast-bert
Super easy library for BERT based NLP models
ghostnet
[CVPR2020] Surpassing MobileNetV3: "GhostNet: More Features from Cheap Operations"
Hand-CNN
ICCV 2019, Hand Detection
InGAN
Official code for the paper "InGAN: Capturing and Retargeting the DNA of a Natural Image"
keras-bert
Implementation of BERT that could load official pre-trained models for feature extraction and prediction
lost
Label Objects and Save Time (LOST) - Design your own smart Image Annotation process in a web-based environment.
moco.tensorflow
A TensorFlow re-implementation of Momentum Contrast (MoCo): https://arxiv.org/abs/1911.05722
moviepy
Video editing with Python
ocr_invoice
ocr system of invoice
OIDv4_ToolKit
Download and visualize single or multiple classes from the huge Open Images v4 dataset
OpenSelfSup
Self-Supervised Learning Toolbox and Benchmark
PhotoDemon
A free portable photo editor focused on pro-grade features, high performance, and maximum usability.
pycorrector
pycorrector is a toolkit for text error correction. It was developed to facilitate the designing, comparing, and sharing of deep text error correction models.
retinanet-examples
Fast and accurate object detection with end-to-end GPU optimization
RxFFmpeg
🔥RxFFmpeg 是基于 ( FFmpeg 4.0 + X264 + mp3lame + fdk-aac ) 编译的适用于 Android 平台的音视频编辑、视频剪辑的快速处理框架，包含以下功能（视频拼接，转码，压缩，裁剪，片头片尾，分离音视频，变速，添加静态贴纸和gif动态贴纸，添加字幕，添加滤镜，添加背景音乐，加速减速视频，倒放音视频，音频裁剪，变声，混音，图片合成视频，视频解码图片等主流特色功能
shotcut
cross-platform (Qt), open-source (GPLv3) video editor
sketch-code
Keras model to generate HTML code from hand-drawn website mockups. Implements an image captioning architecture to drawn source images.
SlowFast
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
Video-to-Online-Platform
An intelligent multimodal-learning based system for video, product and ads analysis. Based on the system, people can build a lot of downstream applications such as product recommendation, video retrieval, etc.
video_analyst
A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.
vmaf
Perceptual video quality assessment based on multi-method fusion.