junfeng tu's Projects
超轻量级中文ocr,支持竖排文字识别, 支持ncnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M
This project summarizes the CLIP-based cross-modal hashing methods. Including DCMHT, MITH, DSPH, DNPH, TwDH (Two-Step Discrete Hashing for Cross-Modal Retrieval).
This is the official code of the paper "Differentiable Cross Modal Hashing via Multimodal Transformers"
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
Describes the full end to end smart parking application that is available with DeepStream 4.0
A project demonstrating use of Python for DeepStream sample apps given as a part of SDK (that are currently in C,C++).
Detectron2 is FAIR's next-generation platform for object detection and segmentation.
使用keras库写的MobileNet网络实现猫狗分类,使用kaggle的Dog-vs-Cat数据集训练
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
This repository contains the source code for the paper First Order Motion Model for Image Animation
Google Research
这是我用python写的一个用来分割hadoop里面的log,可以将他的错误信息之际划开,详细内容见内
Config files for my GitHub profile.
Chinese keyword spotting model using LSTM RNN
Train a 4-layer Convolutional Neural Network to detect trigger word
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
本项目是基于python、pytorch开发的一个关于video人物(face)、内容(nsfw)、文字(OCR)的多模态检索项目,支持docker便携式移植。This is a python project which use multimodal to analyze a video, it can detect face, ocr, nsfw and other informations in videos.
ONNX-TensorRT: TensorRT backend for ONNX
Open Source Computer Vision Library
Oscar and VinVL
Object detection and instance segmentation toolkit based on PaddlePaddle.
Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications
This program use python-opencv to get video and transmit the video from WiFi .It can work on any machine that can use python-opencv.
Image-to-Image Translation in PyTorch
这个项目是基于python3的mxnet框架实现的实时视频人脸识别,其中包括视频传输,人脸识别等部分,用户可根据需要调整使用。整个项目建立在ubuntu18.04系统下。
DNN based hotword and wake word detection toolkit