Source for the paper "Universal Activation Function for machine learning"

Last update: Dec 03, 2022

Overview

Universal Activation Function

Tensorflow and Pytorch source code for the paper

Yuen, Brosnan, Minh Tu Hoang, Xiaodai Dong, and Tao Lu. "Universal activation function for machine learning." Scientific reports 11, no. 1 (2021): 1-11.

Getting the code

Requires Docker

Use git to pull this repo

git clone https://github.com/SensorOrgNet/Universal_Activation_Function.git

Running the Tensorflow 2 version

Install CUDA 11.2 container

docker run --name UAF --gpus all  -v /home/username/UAF/:/workspace  -w /workspace    -it  nvcr.io/nvidia/cuda:11.2.0-cudnn8-devel-ubuntu20.04   bash

Install python

apt update
apt install python3-pip

Install pytorch and pytorch geometric

pip3 install tensorflow==2.7.0

Run the MLP with UAF for MNIST dataset

cd   Universal_Activation_Function/tensorflow/
python3   ./mnist_UAF.py

Running the Pytorch version

Install CUDA 11.3 container

docker run --name UAF --gpus all  -v /home/username/UAF/:/workspace  -w /workspace    -it  nvcr.io/nvidia/cuda:11.3.0-cudnn8-devel-ubuntu20.04   bash

Install python

apt update
apt install python3-pip

Install pytorch and pytorch geometric

pip3 install torch==1.10.0+cu113 torchvision==0.11.1+cu113 torchaudio==0.10.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
pip3 install torch-scatter -f https://data.pyg.org/whl/torch-1.10.0+cu113.html
pip3 install torch-sparse -f https://data.pyg.org/whl/torch-1.10.0+cu113.html
pip3 install torch-cluster -f https://data.pyg.org/whl/torch-1.10.0+cu113.html
pip3 install torch-spline-conv -f https://data.pyg.org/whl/torch-1.10.0+cu113.html
pip3 install torch-geometric

Run the CNN with UAF for MNIST dataset

cd   Universal_Activation_Function/pytorch/
python3   ./mnist_UAF.py

Run the GCN2 with UAF for CORA dataset. The fold number is represented by the number at the end

cd   Universal_Activation_Function/pytorch/
python3   ./gcn2_cora_UAF.py  0

Run the PNA with UAF for ZNC dataset. The fold number is represented by the number at the end

cd   Universal_Activation_Function/pytorch/
python3   ./pna_UAF.py  0

Source for the paper "Universal Activation Function for machine learning"

Related tags

Overview

Universal Activation Function

Getting the code

Running the Tensorflow 2 version

Running the Pytorch version

Owner

Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning (ICLR 2021)

[TIP 2020] Multi-Temporal Scene Classification and Scene Change Detection with Correlation based Fusion

Using multidimensional LSTM neural networks to create a forecast for Bitcoin price

Multi-Agent Reinforcement Learning (MARL) method to learn scalable control polices for multi-agent target tracking.

MultiTaskLearning - Multi Task Learning for 3D segmentation

Implementation of ICCV 2021 oral paper -- A Novel Self-Supervised Learning for Gaussian Mixture Model

A python module for configuration of block devices

El-Gamal on Elliptic Curve (Python)

An implementation on "Curved-Voxel Clustering for Accurate Segmentation of 3D LiDAR Point Clouds with Real-Time Performance"

DuBE: Duple-balanced Ensemble Learning from Skewed Data

Python scripts performing class agnostic object localization using the Object Localization Network model in ONNX.

TagLab: an image segmentation tool oriented to marine data analysis

A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks

XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale

Equivariant Imaging: Learning Beyond the Range Space

FasterAI: A library to make smaller and faster models with FastAI.

[AAAI 2022] Separate Contrastive Learning for Organs-at-Risk and Gross-Tumor-Volume Segmentation with Limited Annotation

Code and Resources for the Transformer Encoder Reasoning Network (TERN)

A fuzzing framework for SMT solvers

Code and results accompanying our paper titled Mixture Proportion Estimation and PU Learning: A Modern Approach at Neurips 2021 (Spotlight)