Code & Data
Here I list some useful code and datasets in machine learning and deep learning.
- Dataset for Multi-Label Learning This website contains some commonly used extreme multi-label datasets.
- Crowdhuman CrowdHuman is a benchmark dataset to better evaluate detectors in crowd scenarios.
- Fashion-MNIST Fashion-MNIST is a dataset of Zalando's article images — consisting of a training set of 60,000 examples and a test set of 10,000 examples.
- BDD100K BDD100K: A Diverse Driving Video Database with Scalable Annotation Tooling.
- MURA MURA (musculoskeletal radiographs) is a large dataset of bone X-rays. Algorithms are tasked with determining whether an X-ray study is normal or abnormal.
- A.I.WIKI A good collection of commonly used open datasets.
- Graph Convolutional Network This is a TensorFlow implementation of Graph Convolutional Networks for the task of (semi-supervised) classification of nodes in a graph, as described in the paper: Thomas N. Kipf, Max Welling, Semi-Supervised Classification with Graph Convolutional Networks. (ICLR 2017).
- Info GAN This repository contains a straightforward implementation of Generative Adversarial Networks trained to fool a discriminator that sees real MNIST images, along with Mutual Information Generative Adversarial Networks (InfoGAN).
- Pytorch_Image_Classification Following papers are implemented using PyTorch: ResNet, ResNet-preact, WRN, DenseNet, PyramidNet, ResNeXt, shake-shake, Cutout, Random Erasing, SENet, Mixup.
- Safe Multi-Label Learning The package includes the MATLAB code of the safe multi-label algorithm SAFEML which towards avoiding performance deterioration using weakly labeled data, or Learning safe multi-label prediction for weakly labeled data. For more detail, you can see the paper Learning Safe Multi-Label Prediction for Weakly Labeled Data.