Parameter-ensemble-differential-evolution - Shows how to do parameter ensembling using differential evolution.

Last update: May 04, 2022

Overview

Ensembling parameters with differential evolution

This repository shows how to ensemble parameters of two trained neural networks using differential evolution. The steps followed are as follows:

Train two networks (architecturally same) on the same dataset (CIFAR-10 used here) but from two different random initializations.
Ensemble their weights using the following formulae:
```
w_t = w_o * ema + (1 - ema) * w_p
```
w_o and w_p represents the learned of a neural network.
Randomly initialize a network (same architecture as above) and populate its parameters w_t using the above formulae.

ema is usually chosen by the developer in an empirical manner. This project uses differential evolution to find it.

Below are the top-1 accuracies (on CIFAR-10 test set) of two individually trained two models along with their ensembled variant:

Model one: 63.23%
Model two: 63.42%
Ensembled: 63.35%

With the more conventional average prediction ensembling, I was able to get to 64.92%. This is way better than what I got by ensembling the parameters. Nevertheless, the purpose of this project was to just try out an idea.

Reproducing the results

Ensure the requirements.txt is satisfied. Then train two models with ensuring your working directory is at the root of this project:

$ git clone https://github.com/sayakpaul/parameter-ensemble-differential-evolution
$ cd parameter-ensemble-differential-evolution
$ pip install -qr requirements.txt
$ for i in `seq 1 2`; python train.py; done

Then just follow the ensemble-parameters.ipynb notebook. You can also use the networks I trained. Instructions are available inside the notebook.

Parameter-ensemble-differential-evolution - Shows how to do parameter ensembling using differential evolution.

Related tags

Overview

Ensembling parameters with differential evolution

Reproducing the results

References

You might also like...

Neural Ensemble Search for Performant and Calibrated Predictions

An Ensemble of CNN (Python 3.5.1 Tensorflow 1.3 numpy 1.13)

zeus is a Python implementation of the Ensemble Slice Sampling method.

Pytorch implementation of SenFormer: Efficient Self-Ensemble Framework for Semantic Segmentation

Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning

This Jupyter notebook shows one way to implement a simple first-order low-pass filter on sampled data in discrete time.

A fast Evolution Strategy implementation in Python

Code for the paper Task Agnostic Morphology Evolution.

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Releases(v0.1.0)

v0.1.0(Jan 2, 2022)

Owner

Sayak Paul

Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)

Control-Robot-Arm-using-PS4-Controller - A Robotic Arm based on Raspberry Pi and Arduino that controlled by PS4 Controller

Aesara is a Python library that allows one to define, optimize, and efficiently evaluate mathematical expressions involving multi-dimensional arrays.

Deep Learning to Improve Breast Cancer Detection on Screening Mammography

Decensoring Hentai with Deep Neural Networks. Formerly named DeepMindBreak.

Generic image compressor for machine learning. Pytorch code for our paper "Lossy compression for lossless prediction".

FrankMocap: A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

NeurIPS 2021 Datasets and Benchmarks Track

TensorFlow implementation of "TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?"

RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition

《LXMERT: Learning Cross-Modality Encoder Representations from Transformers》(EMNLP 2020)

Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth [Paper]

A collection of Jupyter notebooks to play with NVIDIA's StyleGAN3 and OpenAI's CLIP for a text-based guided image generation.

This is the implementation of GGHL (A General Gaussian Heatmap Labeling for Arbitrary-Oriented Object Detection)

Official repository of "BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment"

code for `Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation`

covid question answering datasets and fine tuned models

Pytorch Lightning Distributed Accelerators using Ray

[ICME 2021 Oral] CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning

Monitora la qualità della ricezione dei segnali radio nelle province siciliane.