ajbrock / SMASHLinks
An experimental technique for efficiently exploring neural architectures.
☆492Updated 8 years ago
Alternatives and similar repositories for SMASH
Users that are interested in SMASH are comparing it to the libraries listed below
Sorting:
- Spatially Adaptive Computation Time for Residual Networks☆248Updated 2 years ago
- 2.86% and 15.85% on CIFAR-10 and CIFAR-100☆297Updated 7 years ago
- Training Very Deep Neural Networks Without Skip-Connections☆588Updated 7 years ago
- Decoupled Neural Interfaces using Synthetic Gradients for PyTorch☆239Updated 6 years ago
- auto-tuning momentum SGD optimizer☆288Updated 6 years ago
- ☆219Updated 7 years ago
- ☆137Updated 8 years ago
- PyTorch and Tensorflow functional model definitions☆587Updated 7 years ago
- PyTorch implementation of "Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning"☆348Updated 4 years ago
- Accelerate Neural Net Training by Progressively Freezing Layers☆212Updated 7 years ago
- Complementary code for the Targeted Dropout paper☆256Updated 6 years ago
- Example code for Weight Normalization, from "Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Netw…☆367Updated 7 years ago
- Efficient Architecture Search by Network Transformation, in AAAI 2018☆168Updated 6 years ago
- Log TensorBoard events without touching TensorFlow☆628Updated 2 years ago
- ☆255Updated 4 years ago
- ☆306Updated 4 years ago
- Compare SELUs (scaled exponential linear units) with other activations on MNIST, CIFAR10, etc.☆375Updated 8 years ago
- ☆253Updated 9 years ago
- Deep Learning Projects that Build Themselves☆359Updated 6 years ago
- The first public PyTorch implementation of Attentive Recurrent Comparators☆146Updated 8 years ago
- Tensorflow Implementation of Adversarial Attack to Capsule Networks☆173Updated 8 years ago
- Files to create the figures in the paper "Super-Convergence: Very Fast Training of Residual Networks Using Large Learning Rates"☆191Updated 8 years ago
- Speed up PixelCNN++ image generation by up to a 183 times☆482Updated 8 years ago
- Implementation of Progressive Neural Architecture Search in Keras and Tensorflow☆118Updated 6 years ago
- Code release for paper "Random Search and Reproducibility for NAS"☆167Updated 6 years ago
- Fast Scattering Transform with CuPy/PyTorch☆295Updated 5 years ago
- PyTorch implementation of the CortexNet predictive model☆368Updated 7 years ago
- 📈 TensorFlow + Matplotlib as TF ops☆299Updated 6 years ago
- PyTorch based Deep Learning Toolbox☆206Updated 7 years ago
- DeepArchitect: Automatically Designing and Training Deep Architectures☆145Updated 6 years ago