Name: Takeru Miyato
Type: User
Company: Autonomous vision group, University of Tübingen
Bio: Ph.D. student @ Autonomous Vision Group, University of Tübingen. Part-time researcher for Preferred Networks, Inc.
Twitter: takeru_miyato
Blog: takerum.github.io
Takeru Miyato's Projects
Implementation of Adversarial Autoencoder with Theano
Certifying Some Distributional Robustness with Principled Adversarial Training (https://arxiv.org/abs/1710.10571)
A flexible framework of neural networks for deep learning
Chainer implementation of recent GAN variants
Deep Residual Network implementation by Chainer
NumPy-like API accelerated with CUDA
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
EscherNet: A Generative Model for Scalable View Synthesis
Chainer implementation of Least Squares GAN (LSGAN)
Generate mini-ImageNet with ImageNet for fewshot learning
Models built with TensorFlow
Implementation of Prototypical Networks for Few Shot Learning (https://arxiv.org/abs/1703.05175) in Pytorch
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
Sprites video data used in the ICML 2018 paper
Independent PyTorch implementation of Scene Representation Transformer
ResNet model in TensorFlow
Implementation of Variational Auto Encoder with Chainer
Code for reproducing the results on the MNIST dataset in the paper "Distributional Smoothing with Virtual Adversarial Training"
Implementation of Virtual adversarial training with chainer
Virtual adversarial training with Tensorflow
Datasets, Transforms and Models specific to Computer Vision