examples

tensorpack examples

Training examples with reproducible and meaningful performance.

Vision:

• An illustrative mnist example with explanation of the framework
• A tiny SVHN ConvNet with 97.8% accuracy
• DoReFa-Net: training binary / low-bitwidth CNN on ImageNet
• Train ResNet for ImageNet/Cifar10/SVHN
• 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 Saliency Maps by Guided ReLU
• Similarity Learning on MNIST
• Load a pre-trained AlexNet or VGG16 model.
• Load a pre-trained Convolutional Pose Machines.

Reinforcement Learning:

• Deep Q-Network(DQN) variants on Atari games
• Asynchronous Advantage Actor-Critic(A3C) with demos on OpenAI Gym

Unsupervised Learning:

• Generative Adversarial Network(GAN) variants, including DCGAN, InfoGAN, Conditional GAN, WGAN, Image to Image.

Speech / NLP:

• LSTM-CTC for speech recognition
• char-rnn for fun
• LSTM language model on PennTreebank

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.