ake020675
A computer vision engineer and researcher with 13+ year's experiences. Have 3 academic papers published in areas of eye tracking and visual saliency model.
American
Pinned Repositories
3d-face-models-preprocessing-tool
3d-face-models-preprocessing-tool
3d-face-preprocessing
3d face preprocessing
AI-Basketball-Field-Goal-Tracker
AI Basketball Field Goal Percentage Tracker
ake020675.github.io
A jekyll based resume template
anodet
Anomaly detection on images using features from pretrained neural networks.
anomalib
An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.
CRNN-PyTorch
PyTorch implemnts `An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition` paper.
DeepGaze
pytorch implementation of the different DeepGaze models
FastestDet
:zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 30% compared with yolo-fastest, and the post-processing is simpler
VT-ADL
A Vision Transformer Network for Image Anomaly Detection and Localization
ake020675's Repositories
ake020675/CRNN-PyTorch
PyTorch implemnts `An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition` paper.
ake020675/FastestDet
:zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 30% compared with yolo-fastest, and the post-processing is simpler
ake020675/3d-face-preprocessing
3d face preprocessing
ake020675/AI-Basketball-Field-Goal-Tracker
AI Basketball Field Goal Percentage Tracker
ake020675/ake020675.github.io
A jekyll based resume template
ake020675/anomalib
An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.
ake020675/AntiFraudChatBot
A simple prompt-chatting AI based on wechaty and fintuned NLP model
ake020675/Clash-for-Windows_Chinese
clash for windows汉化版. 提供clash for windows的汉化版, 汉化补丁及汉化版安装程序
ake020675/deep-learning-for-image-processing
deep learning for image processing including classification and object-detection etc.
ake020675/fdsnet
FDSNet: An Accurate Real-Time Surface Defect Segmentation Network (ICASSP 2022)
ake020675/gpt4free
decentralising the Ai Industry, just some language model api's...
ake020675/HowToLiveLonger
程序员延寿指南 | A programmer's guide to live longer
ake020675/iptv
Collection of publicly available IPTV channels from all over the world
ake020675/MHDDoS
Best DDoS Attack Script Python3, (Cyber / DDos) Attack With 56 Methods
ake020675/MMCLS_ColorLine
MMCLS files for train and inference ColorLine model
ake020675/Moondream2-streamlit
ake020675/NiceHashQuickMiner
Super simple & easy Windows 10 cryptocurrency miner made by NiceHash.
ake020675/PaddleDetection
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
ake020675/runner_DeepLearning
A light-weight script for launching a large number of experiments.
ake020675/SMSBoom
awelltoolforbadguy
ake020675/snntorch
Deep and online learning with spiking neural networks in Python
ake020675/SoM
Set-of-Mark Prompting for LMMs
ake020675/SportsLabKit
A python package for turning sports video into csv files
ake020675/SuperGluePretrainedNetwork
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
ake020675/tensorRT_Pro
C++ library based on tensorrt integration
ake020675/the-economist-ebooks
经济学人(含音频)、纽约客、自然、新科学人、卫报、科学美国人、连线、大西洋月刊、国家地理等英语杂志免费下载、订阅(kindle推送),支持epub、mobi、pdf格式, 每周更新. The Economist 、The New Yorker 、Nature、The Atlantic 、New Scientist、The Guardian、Scientific American、Wired magazines, free download and subscription for kindle, mobi、epub、pdf format.
ake020675/torch-cam
Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)
ake020675/uform
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️
ake020675/Utils4DeepLearning
ake020675/YOLOv5-LPRNet-Licence-Recognition
使用YOLOv5和LPRNet进行车牌检测+识别（CCPD数据集）