Stars
Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2), MobileSAM!!
Keras Attention Layer (Luong and Bahdanau scores).
[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
EVA Series: Visual Representation Fantasies from BAAI
[IEEE TMI] Official Implementation for UNet++
A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error ＝ 0.34%.
特征提取/数据降维:PCA、LDA、MDS、LLE、TSNE等降维算法的python实现
Machine learning metrics for distributed, scalable PyTorch applications.
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
Implementation of different kinds of Unet Models for Image Segmentation - Unet , RCNN-Unet, Attention Unet, RCNN-Attention Unet, Nested Unet
Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and rela…
Read, modify and write DICOM files with python code
A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch
Pytorch implementation of cnn network
Use of Attention Gates in a Convolutional Neural Network / Medical Image Classification and Segmentation
MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.
PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models
a generalist algorithm for cellular segmentation with human-in-the-loop capabilities
[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
CVNets: A library for training computer vision networks
Integrate deep learning models for image classification | Backbone learning/comparison/magic modification project
Nvidia Semantic Segmentation monorepo
This is a collection of our NAS and Vision Transformer work.
这是一个faster-rcnn的pytorch实现的库，可以利用voc数据集格式的数据进行训练。
Pytorch implementation of various Knowledge Distillation (KD) methods.