GhostnetCV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.
Stars: ✭ 1,744 (+2391.43%)
Transformer-in-TransformerAn Implementation of Transformer in Transformer in TensorFlow for image classification, attention inside local patches
Stars: ✭ 40 (-42.86%)
towheeTowhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
Stars: ✭ 821 (+1072.86%)
Labelimg🖍️ LabelImg is a graphical image annotation tool and label object bounding boxes in images
Stars: ✭ 16,088 (+22882.86%)
visualizationa collection of visualization function
Stars: ✭ 189 (+170%)
FishnetImplementation code of the paper: FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction, NeurIPS 2018
Stars: ✭ 533 (+661.43%)
Divide And Co Training[Paper 2020] Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training. Plus, an image classification toolbox includes ResNet, Wide-ResNet, ResNeXt, ResNeSt, ResNeXSt, SENet, Shake-Shake, DenseNet, PyramidNet, and EfficientNet.
Stars: ✭ 54 (-22.86%)
TNCR DatasetDeep learning, Convolutional neural networks, Image processing, Document processing, Table detection, Page object detection, Table classification. https://www.sciencedirect.com/science/article/pii/S0925231221018142
Stars: ✭ 37 (-47.14%)
Alexnetimplement AlexNet with C / convolutional nerual network / machine learning / computer vision
Stars: ✭ 147 (+110%)
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"
Stars: ✭ 27 (-61.43%)
TokenLabelingPytorch implementation of "All Tokens Matter: Token Labeling for Training Better Vision Transformers"
Stars: ✭ 385 (+450%)
super-gradientsEasily train or fine-tune SOTA computer vision models with one open source training library
Stars: ✭ 429 (+512.86%)
Rectlabel SupportRectLabel - An image annotation tool to label images for bounding box object detection and segmentation.
Stars: ✭ 338 (+382.86%)
Computer VisionProgramming Assignments and Lectures for Stanford's CS 231: Convolutional Neural Networks for Visual Recognition
Stars: ✭ 408 (+482.86%)
MmclassificationOpenMMLab Image Classification Toolbox and Benchmark
Stars: ✭ 532 (+660%)
AognetCode for CVPR 2019 paper: " Learning Deep Compositional Grammatical Architectures for Visual Recognition"
Stars: ✭ 132 (+88.57%)
EfficientnetImplementation of EfficientNet model. Keras and TensorFlow Keras.
Stars: ✭ 1,920 (+2642.86%)
TorchdistillPyTorch-based modular, configuration-driven framework for knowledge distillation. 🏆18 methods including SOTA are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy.
Stars: ✭ 177 (+152.86%)
Tf Mobilenet V2Mobilenet V2(Inverted Residual) Implementation & Trained Weights Using Tensorflow
Stars: ✭ 85 (+21.43%)
AITQAresources for the IBM Airlines Table-Question-Answering Benchmark
Stars: ✭ 12 (-82.86%)
VT-UNet[MICCAI2022] This is an official PyTorch implementation for A Robust Volumetric Transformer for Accurate 3D Tumor Segmentation
Stars: ✭ 151 (+115.71%)
libaiLiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training
Stars: ✭ 284 (+305.71%)
pytorch-cifar-model-zooImplementation of Conv-based and Vit-based networks designed for CIFAR.
Stars: ✭ 62 (-11.43%)
YOLOSYou Only Look at One Sequence (NeurIPS 2021)
Stars: ✭ 612 (+774.29%)
ailia-modelsThe collection of pre-trained, state-of-the-art AI models for ailia SDK
Stars: ✭ 1,102 (+1474.29%)
etiketaiEtiketai is an online tool designed to label images, useful for training AI models
Stars: ✭ 63 (-10%)
RexnetOfficial Pytorch implementation of ReXNet (Rank eXpansion Network) with pretrained models
Stars: ✭ 319 (+355.71%)
Assembled CnnTensorflow implementation of "Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network"
Stars: ✭ 319 (+355.71%)
Neural Backed Decision TreesMaking decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet
Stars: ✭ 411 (+487.14%)
Swin-TransformerThis is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Stars: ✭ 8,046 (+11394.29%)
CvatPowerful and efficient Computer Vision Annotation Tool (CVAT)
Stars: ✭ 6,557 (+9267.14%)
ImagenetTrial on kaggle imagenet object localization by yolo v3 in google cloud
Stars: ✭ 56 (-20%)
pigalleryPiGallery: AI-powered Self-hosted Secure Multi-user Image Gallery and Detailed Image analysis using Machine Learning, EXIF Parsing and Geo Tagging
Stars: ✭ 35 (-50%)
RegnetPytorch implementation of network design paradigm described in the paper "Designing Network Design Spaces"
Stars: ✭ 129 (+84.29%)
LabelboxLabelbox is the fastest way to annotate data to build and ship computer vision applications.
Stars: ✭ 1,588 (+2168.57%)
PetridishnnCode for the neural architecture search methods contained in the paper Efficient Forward Neural Architecture Search
Stars: ✭ 112 (+60%)
ImgclsmobSandbox for training deep learning networks
Stars: ✭ 2,405 (+3335.71%)
IresnetImproved Residual Networks (https://arxiv.org/pdf/2004.04989.pdf)
Stars: ✭ 163 (+132.86%)
FNet-pytorchUnofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms
Stars: ✭ 204 (+191.43%)
ModelZoo.pytorchHands on Imagenet training. Unofficial ModelZoo project on Pytorch. MobileNetV3 Top1 75.64🌟 GhostNet1.3x 75.78🌟
Stars: ✭ 42 (-40%)
SwinIRSwinIR: Image Restoration Using Swin Transformer (official repository)
Stars: ✭ 1,260 (+1700%)
nested-transformerNested Hierarchical Transformer https://arxiv.org/pdf/2105.12723.pdf
Stars: ✭ 174 (+148.57%)
fastT5⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
Stars: ✭ 421 (+501.43%)
transformer-lsOfficial PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).
Stars: ✭ 201 (+187.14%)
ICON(TPAMI2022) Salient Object Detection via Integrity Learning.
Stars: ✭ 125 (+78.57%)
BrevitasBrevitas: quantization-aware training in PyTorch
Stars: ✭ 343 (+390%)
PaddleclasA treasure chest for image classification powered by PaddlePaddle
Stars: ✭ 625 (+792.86%)
LaTeX-OCRpix2tex: Using a ViT to convert images of equations into LaTeX code.
Stars: ✭ 1,566 (+2137.14%)
Skin Lesions Classification DCNNsTransfer Learning with DCNNs (DenseNet, Inception V3, Inception-ResNet V2, VGG16) for skin lesions classification
Stars: ✭ 47 (-32.86%)
Evo-ViTOfficial implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer
Stars: ✭ 50 (-28.57%)