ngmzud's starred repositories
image_classification_sota
Training ImageNet / CIFAR models with sota strategies and fancy techniques such as ViT, KD, Rep, etc.
imagenet-japanese-labels
ImageNet日本語ラベル
keras-image-models
A library that includes Keras3 layers, blocks and models with pretrained weights, providing support for transfer learning, feature extraction, and more.
natural-adv-examples
A Harder ImageNet Test Set (CVPR 2021)
tinygrad-image-models
tinygrad image models, inference, and (soon) training
FoodCalorieEstimation
Food calorie estimation integrated with ImageNet and google generative AI with flask API and Basic Frontend using Tailwind
CarsBrands_Inceptionv3
Project that detects the brand of a car, between 1 and 49 brands, that appears in a photograph, with a success rate of more than 70% (using a test file that has not been involved in the training as a valid or training file, "unseen data") and can be implemented on a personal computer
UniteandConquer
[CVPR '23] Unite and Conquer: Plug & Play Multi-Modal Synthesis using Diffusion Models
event_representation_study
Official PyTorch implementation of the ICCV 2023 paper: From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection.
efficientnet-pytorch
A PyTorch implementation of "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks".
easyrobust
EasyRobust: an Easy-to-use library for state-of-the-art Robust Computer Vision Research with PyTorch.
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
custom_imagenet-1k_models
Models with variable output classes designed for Imagenet-1k.
WhatsThere
Pytorch based Android app, which classifies images using MobileNet-V2 model, takes image using CameraX API
torchdistill
A coding-free framework built on PyTorch for reproducible deep learning studies. 🏆25 knowledge distillation methods presented at CVPR, ICLR, ECCV, NeurIPS, ICCV, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.
equivision
ImageNet1k-pretrained SE(2) Equivariant Vision Models
ImageNetSubmission
This is a simple example of how to prepare an ImageNet submission to the evaluation server.
VGG16-Image-Reverse-Engine
An Image Reverse Engine based on VGG16
one-pixel-attack-keras
Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet
keras_cv_attention_models
Keras beit,caformer,CMT,CoAtNet,convnext,davit,dino,efficientdet,edgenext,efficientformer,efficientnet,eva,fasternet,fastervit,fastvit,flexivit,gcvit,ghostnet,gpvit,hornet,hiera,iformer,inceptionnext,lcnet,levit,maxvit,mobilevit,moganet,nat,nfnets,pvt,swin,tinynet,tinyvit,uniformer,volo,vanillanet,yolor,yolov7,yolov8,yolox,gpt2,llama2, alias kecam
PlantDiseaseDetection
Transforming agriculture with AI: Explore our GitHub for advanced plant disease detection. Utilizing top CNN models, we empower farmers with early diagnosis tools. Access notebooks, datasets, and a user-friendly web app. Join us in revolutionizing farming for a sustainable future
Efficient-AI-Backbones
Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
Rectlabel-support
RectLabel is an offline image annotation tool for object detection and segmentation.