You have just found TensorLayer! High performance DL and RL library for industry and academic.
Contributions welcome! Read the contribution guidelines first.
TensorLayer can define models in two ways. Static model allows you to build model in a fluent way while dynamic model allows you to fully control the forward process. Please read this DOCS before you start.
- MNIST Simplest Example
- MNIST Static Example
- MNIST Static Example for Reused Model
- MNIST Dynamic Example
- MNIST Dynamic Example for Seperated Models
- MNIST Static Siamese Model Example
- CIFAR10 Static Example with Data Augmentation
- Downloading and Preprocessing PASCAL VOC with TensorLayer VOC data loader. 知乎文章
- Read and Save data in TFRecord Format.
- Read and Save time-series data in TFRecord Format.
- Convert CIFAR10 in TFRecord Format for performance optimization.
- More dataset loader can be found in tl.files.load_xxx
- Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
- OpenPose: Real-time multi-person keypoint detection
- InsignFace - Additive Angular Margin Loss for Deep Face Recognition
- Spatial-Transformer-Nets (STN) trained on MNIST dataset based on the paper by [M. Jaderberg et al, 2015].
- U-Net Brain Tumor Segmentation trained on BRATS 2017 dataset based on the paper by [M. Jaderberg et al, 2015] with some modifications.
- Image2Text: im2txt based on the paper by [O. Vinyals et al, 2016].
- More Computer Vision Application can be found in Adversarial Learning Section
- Binary Networks works on mnist and cifar10.
- Ternary Network works on mnist and cifar10.
- DoReFa-Net works on mnist and cifar10.
- Quantization For Efficient Integer-Arithmetic-Only Inference works on mnist and cifar10.
- DCGAN trained on the CelebA dataset based on the paper by [A. Radford et al, 2015].
- CycleGAN improved with resize-convolution based on the paper by [J. Zhu et al, 2017].
- SRGAN - A Super Resolution GAN based on the paper by [C. Ledig et al, 2016].
- DAGAN: Fast Compressed Sensing MRI Reconstruction based on the paper by [G. Yang et al, 2017].
- GAN-CLS for Text to Image Synthesis based on the paper by [S. Reed et al, 2016]
- Unsupervised Image-to-Image Translation with Generative Adversarial Networks, code
- BEGAN: Boundary Equilibrium Generative Adversarial Networks based on the paper by [D. Berthelot et al, 2017].
- BiGAN Adversarial Feature Learning
- Attention CycleGAN: Unsupervised Attention-guided Image-to-Image Translation
- MoCoGAN Decomposing Motion and Content for Video Generation
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets, 2016
- Lifelong GAN: Continual Learning for Conditional Image Generation, 2019, ICCV
- Seq2Seq Chatbot in 200 lines of code for Seq2Seq.
- Text Generation with LSTMs - Generating Trump Speech.
- Modelling PennTreebank code1 and code2, see blog post.
- FastText Classifier running on the IMDB dataset based on the paper by [A. Joulin et al, 2016].
- Minimalistic Implementation of Word2Vec based on the paper by [T. Mikolov et al, 2013].
- Variational Autoencoder trained on the CelebA dataset.
- Variational Autoencoder trained on the MNIST dataset.
- The guideline of using pretrained models is here.
- Why Database?.
- Put Tasks into Database and Execute on Other Agents, see code.
- TensorDB applied on Pong Game on OpenAI Gym: Trainer File and Generator File based on the following blog post.
- TensorDB applied to classification task on MNIST dataset: Master File and Worker File.
If you find this project useful, we would be grateful if you cite the TensorLayer paper：
@article{tensorlayer2017,
author = {Dong, Hao and Supratak, Akara and Mai, Luo and Liu, Fangde and Oehmichen, Axel and Yu, Simiao and Guo, Yike},
journal = {ACM Multimedia},
title = {{TensorLayer: A Versatile Library for Efficient Deep Learning Development}},
url = {http://tensorlayer.org},
year = {2017}
}