Training examples with reproducible and meaningful performance.
- An illustrative mnist example with explanation of the framework
- The same mnist example using tf-slim, Keras, and with weights visualizations
- A boilerplate file to start with, for your own tasks
- A tiny SVHN ConvNet with 97.8% accuracy
- DoReFa-Net: training binary / low-bitwidth CNN on ImageNet
- Train ResNet for ImageNet/Cifar10/SVHN
- Generative Adversarial Network(GAN) variants, including DCGAN, InfoGAN, Conditional GAN, WGAN, BEGAN, DiscoGAN, Image to Image, CycleGAN.
- Inception-BN with 71% accuracy
- InceptionV3 with 74% accuracy (similar to the official code)
- Fully-convolutional Network for Holistically-Nested Edge Detection(HED)
- Spatial Transformer Networks on MNIST addition
- Visualize CNN saliency maps
- Similarity learning on MNIST
- Load a pre-trained AlexNet or VGG16 model.
- Load a pre-trained Convolutional Pose Machines.
- Deep Q-Network(DQN) variants on Atari games, including DQN, DoubleDQN, DuelingDQN.
- Asynchronous Advantage Actor-Critic(A3C) with demos on OpenAI Gym
Note to contributors:
Example needs to satisfy one of the following:
- Reproduce performance of a published or well-known paper.
- Get state-of-the-art performance on some task.
- Illustrate a new way of using the library that is currently not covered.