All Projects → DrChainsaw → NaiveNASflux.jl

DrChainsaw / NaiveNASflux.jl

Licence: MIT license
Your local Flux surgeon

Programming Languages

julia
2034 projects

Projects that are alternatives of or similar to NaiveNASflux.jl

SIGIR2021 Conure
One Person, One Model, One World: Learning Continual User Representation without Forgetting
Stars: ✭ 23 (+15%)
Mutual labels:  pruning, transfer-learning
Autogluon
AutoGluon: AutoML for Text, Image, and Tabular Data
Stars: ✭ 3,920 (+19500%)
Mutual labels:  hyperparameter-optimization, transfer-learning
sparsezoo
Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes
Stars: ✭ 264 (+1220%)
Mutual labels:  pruning, transfer-learning
Keras-MultiClass-Image-Classification
Multiclass image classification using Convolutional Neural Network
Stars: ✭ 48 (+140%)
Mutual labels:  transfer-learning
aml-keras-image-recognition
A sample Azure Machine Learning project for Transfer Learning-based custom image recognition by utilizing Keras.
Stars: ✭ 14 (-30%)
Mutual labels:  transfer-learning
mutable
State containers with dirty checking and more
Stars: ✭ 32 (+60%)
Mutual labels:  flux
Open set domain adaptation
Tensorflow Implementation of open set domain adaptation by backpropagation
Stars: ✭ 27 (+35%)
Mutual labels:  transfer-learning
ATMC
[NeurIPS'2019] Shupeng Gui, Haotao Wang, Haichuan Yang, Chen Yu, Zhangyang Wang, Ji Liu, “Model Compression with Adversarial Robustness: A Unified Optimization Framework”
Stars: ✭ 41 (+105%)
Mutual labels:  pruning
textlearnR
A simple collection of well working NLP models (Keras, H2O, StarSpace) tuned and benchmarked on a variety of datasets.
Stars: ✭ 16 (-20%)
Mutual labels:  hyperparameter-optimization
LegoBrickClassification
Repository to identify Lego bricks automatically only using images
Stars: ✭ 57 (+185%)
Mutual labels:  transfer-learning
Pruning filters for efficient convnets
PyTorch implementation of "Pruning Filters For Efficient ConvNets"
Stars: ✭ 96 (+380%)
Mutual labels:  pruning
MoeFlow
Repository for anime characters recognition website, powered by TensorFlow
Stars: ✭ 113 (+465%)
Mutual labels:  transfer-learning
bert-squeeze
🛠️ Tools for Transformers compression using PyTorch Lightning ⚡
Stars: ✭ 56 (+180%)
Mutual labels:  pruning
TransTQA
Author: Wenhao Yu ([email protected]). EMNLP'20. Transfer Learning for Technical Question Answering.
Stars: ✭ 12 (-40%)
Mutual labels:  transfer-learning
EntityTargetedActiveLearning
No description or website provided.
Stars: ✭ 17 (-15%)
Mutual labels:  transfer-learning
ml-pipeline
Using Kafka-Python to illustrate a ML production pipeline
Stars: ✭ 90 (+350%)
Mutual labels:  hyperparameter-optimization
k8s-gitops
Homelab GitOps repository. Cluster definition state via code.
Stars: ✭ 47 (+135%)
Mutual labels:  flux
paper annotations
A place to keep track of all the annotated papers.
Stars: ✭ 96 (+380%)
Mutual labels:  transfer-learning
ProxGradPytorch
PyTorch implementation of Proximal Gradient Algorithms a la Parikh and Boyd (2014). Useful for Auto-Sizing (Murray and Chiang 2015, Murray et al. 2019).
Stars: ✭ 28 (+40%)
Mutual labels:  hyperparameter-optimization
task-transferability
Data and code for our paper "Exploring and Predicting Transferability across NLP Tasks", to appear at EMNLP 2020.
Stars: ✭ 35 (+75%)
Mutual labels:  transfer-learning

NaiveNASflux

Build status Build Status Codecov

NaiveNASflux uses NaiveNASlib to enable mutation operations of arbitrary Flux computation graphs. It is designed with Neural Architecture Search (NAS) in mind, but can be used for any purpose where doing changes to a model is desired.

Note that NaiveNASflux does not have any functionality to search for a model architecture. Check out NaiveGAflux for a simple proof of concept.

Basic Usage

]add NaiveNASflux

See documentation for usage instructions.

Contributing

All contributions are welcome. Please file an issue before creating a PR.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].