chitraA multi-functional library for full-stack Deep Learning. Simplifies Model Building, API development, and Model Deployment.
CV本仓库将使用Pytorch框架实现经典的图像分类网络、目标检测网络、图像分割网络,图像生成网络等,并会持续更新!!!
Maix-LogoClassifierA simple logo classifier developed using Maixduino framework and PlatfomIO, to run on K210 MCU on Sipeed's Maix dev board.
catacombThe simplest machine learning library for launching UIs, running evaluations, and comparing model performance.
tensorflow-classificationA unified program to check predictions of different convolutional neural networks for image classification.
Tensorflow-Dog-Breed-ClassifierTensorflow Image classifier that can predict the breed of a dog from it photo. Trained on image dataset of 5 different breed of dogs (rottweiler, bulldog, pug, german shepherds, labrador). Interestingly the classifier was able to predict the breed of the dogs even from images of their toys.
Paper-NotesPaper notes in deep learning/machine learning and computer vision
sinkhorn-label-allocationSinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms. The SLA algorithm is described in full in this ICML 2021 paper: https://arxiv.org/abs/2102.08622.
UniFormer[ICLR2022] official implementation of UniFormer
MixNet-PyTorchConcise, Modular, Human-friendly PyTorch implementation of MixNet with Pre-trained Weights.
imannotateImage annotation tool to make Machine Learning or others stuffs
KerasUIUI for Keras to implement image classification written in python and django
subwAIScripts for training an AI to play the endless runner Subway Surfers using a supervised machine learning approach by imitation and a convolutional neural network (CNN) for image classification
mybabeMyBB CAPTCHA Solver using Convolutional Neural Network in Keras
aitlasAiTLAS implements state-of-the-art AI methods for exploratory and predictive analysis of satellite images.
head-network-distillation[IEEE Access] "Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-constrained Edge Computing Systems" and [ACM MobiCom HotEdgeVideo 2019] "Distilled Split Deep Neural Networks for Edge-assisted Real-time Systems"
LibFewShotLibFewShot: A Comprehensive Library for Few-shot Learning.
SimMIMThis is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".
SCL📄 Spatial Contrastive Learning for Few-Shot Classification (ECML/PKDD 2021).