Architecture search using unsupervised learning with symmetric auto-encoders and QLearning in PyTorch
-
Updated
Feb 24, 2018 - Python
Architecture search using unsupervised learning with symmetric auto-encoders and QLearning in PyTorch
Implementation of MetaQNN (https://arxiv.org/abs/1611.02167, https://github.com/bowenbaker/metaqnn.git) with Additions and Modifications in PyTorch for Image Classification
Implementation of MetaQNN (https://arxiv.org/abs/1611.02167, https://github.com/bowenbaker/metaqnn.git) with Additions and Modifications in PyTorch for Image Generation with GAN where the Discriminator network is fixed and same as that in the infoGAN paper (https://arxiv.org/abs/1606.03657)
Implementation of MetaQNN (https://arxiv.org/abs/1611.02167, https://github.com/bowenbaker/metaqnn.git) with Additions and Modifications in PyTorch for Image Generation with Asymmetric Variational Autoencoders
A PyTorch implementation of Mnasnet: MnasNet: Platform-Aware Neural Architecture Search for Mobile.
A design space exploration tool for deep neural architectures
Integrating learning and task planning for robots with Keras, including simulation, real robot, and multiple dataset support.
A neural architecture optimizer, targeted at model-size w.r.t. accuracy
A TensorFlow 2.0 implementation of MnasNet: Platform-Aware Neural Architecture Search for Mobile.
DeepArchitect: Automatically Designing and Training Deep Architectures
Distributed Network Architecture Search
AutoDeeplab / auto-deeplab / AutoML for semantic segmentation, implemented in Pytorch
A Tensorflow Keras implementation (Graph and eager execution) of Mnasnet: MnasNet: Platform-Aware Neural Architecture Search for Mobile.
Implementation of Autoslim using Tensorflow2
Code for ''Understanding and Exploring the Network with Stochastic Architectures''
sharpDARTS: Faster and More Accurate Differentiable Architecture Search
A list of high-quality (newest) AutoML works and lightweight models including 1.) Neural Architecture Search, 2.) Lightweight Structures, 3.) Model Compression, Quantization and Acceleration, 4.) Hyperparameter Optimization, 5.) Automated Feature Engineering.
Repository to track the progress in model compression and acceleration
Notes for doing really good software architecting.
EComp: Evolutionary Compression of Neural Networks Using a Novel Similarity Objective
Add a description, image, and links to the architecture-search topic page so that developers can more easily learn about it.
To associate your repository with the architecture-search topic, visit your repo's landing page and select "manage topics."