Goro: A High-level Machine Learning Library for Go

Last update: Nov 20, 2022

Overview

Goro is a high-level machine learning library for Go built on Gorgonia. It aims to have the same feel as Keras.

Usage

import (
    . "github.com/aunum/goro/pkg/v1/model"
    "github.com/aunum/goro/pkg/v1/layer"
)

// create the 'x' input e.g. mnist image
x := NewInput("x", []int{1, 28, 28})

// create the 'y' or expect output e.g. labels
y := NewInput("y", []int{10})

// create a new sequential model with the name 'mnist'
model, _ := NewSequential("mnist")

// add layers to the model
model.AddLayers(
    layer.Conv2D{Input: 1, Output: 32, Width: 3, Height: 3},
    layer.MaxPooling2D{},
    layer.Conv2D{Input: 32, Output: 64, Width: 3, Height: 3},
    layer.MaxPooling2D{},
    layer.Conv2D{Input: 64, Output: 128, Width: 3, Height: 3},
    layer.MaxPooling2D{},
    layer.Flatten{},
    layer.FC{Input: 128 * 3 * 3, Output: 100},
    layer.FC{Input: 100, Output: 10, Activation: layer.Softmax},
)

// pick an optimizer
optimizer := g.NewRMSPropSolver()

// compile the model with options
model.Compile(xi, yi,
    WithOptimizer(optimizer),
    WithLoss(m.CrossEntropy),
    WithBatchSize(100),
)

// fit the model
model.Fit(xTrain, yTrain)

// use the model to predict an 'x'
prediction, _ := model.Predict(xTest)

// fit the model with a batch
model.FitBatch(xTrainBatch, yTrainBatch)

// use the model to predict a batch of 'x'
prediction, _ = model.PredictBatch(xTestBatch)

Examples

See the examples folder for example implementations.

There are many examples in the reinforcement learning library Gold.

Docs

Each package contains a README explaining the usage, also see GoDoc.

Contributing

Please open an MR for any issues or feature requests.

Feel free to ping @pbarker on Gopher slack.

Roadmap

RNN
LSTM
Summary
Visualization

Skill builders for learning conversational Golang.

goPracticum Skill builders for learning conversational Golang. The Theory I'm stealing...err...borrowing profusely from human language learning and cu

0 Dec 9, 2021

CI/CD Learning

cicd-learning CI/CD Learning /gowebapp Building Here we will cover building the application and docker image Go To build the web app, just run, from t

0 Nov 25, 2021

Collecting and learning common algorithms

中文 Alogrithms Learning alogrithms. Dynamic Programming Fibonacci Grid Traveler Can Sum How Sum TODO Sorting Selection Sort Bubble Sort Insertion Sort

0 Jan 10, 2022

Golang - A collection of small Go programs used as learning exercises

This repo is a collection of small Go programs used as learning exercises Some o

0 Dec 31, 2021

This is a learning poem for golang~

golang-learning This will be a learning Bible ( in developing ... ) for golang~ PS : Currently, all learning content is based on Golang 1.17.5. 主要包含以下

5 Jan 12, 2022

This is a learning poem for golang~

golang-learning-bible This will be a learning Bible ( in developing ... ) for golang~ 中文 | English PS : Currently, all learning content is based on Go

5 Jan 12, 2022

Turtorial - A Hard Fork Of Icexin's Great Gocraft Project Aimed At Learning Basic Programming Tasks Through Turtles

TURTORIAL A voxel sandbox-survival game aimed at teaching the basics of programm

1 Jan 25, 2022

Golang - Learning go aka Flow with the go

golang learning go aka Flow with the go! helpful links tour of go: https://go.de

0 Feb 3, 2022

Learning Hexagonal Pattern with Golang

Marketplace Utility Software yang harus terinstal di komputer Software Versi Golang 1.17+ MariaDB 10.3+ Cara Menjalakan Clone repo ini Buat database d

0 Feb 10, 2022

Comments

Type Error
Hi, I am new to using goro and cnns in general so right now I am trying to run the example mnist go file. However, I am running into the following error with WithOptimizer:

cannot use optimizer (variable of type *gorgonia.RMSPropSolver) as gorgonia.Solver value in argument to m.WithOptimizer: wrong type for method Step (have func(model []gorgonia.org/gorgonia.ValueGrad) (err error), want func([]gorgonia.org/gorgonia.ValueGrad) error)compilerInvalidIfaceAssign

I haven't changed anything in the example main.go file and I can import the following with no errors:

import ( "github.com/aunum/gold/pkg/v1/common/num" "github.com/aunum/gold/pkg/v1/common/require" "github.com/aunum/gold/pkg/v1/dense" "github.com/aunum/goro/pkg/v1/layer" m "github.com/aunum/goro/pkg/v1/model" "github.com/aunum/log" g "gorgonia.org/gorgonia" "gorgonia.org/gorgonia/examples/mnist" "gorgonia.org/tensor" )

I am just confused as to why WithOptimizer is not working for me. Thanks!
opened by emmawuuu 1

Using `Init: gorgonia.Zeroes()` in every layer does not make output always zero

Initializing network with the following code:

qModel, err := m.NewSequential("qLearning")
if err != nil {
	return nil, err
}

xShape := []int{1, 71}
yShape := []int{1, 16}
in := m.NewInput("state", xShape)
out := m.NewInput("actionValue", yShape)

qModel.AddLayers(
	layer.FC{Input: in.Squeeze()[0], Output: 256, Init: gorgonia.Zeroes()},
	layer.FC{Input: 256, Output: 128, Init: gorgonia.Zeroes()},
	layer.FC{Input: 128, Output: 64, Init: gorgonia.Zeroes()},
	layer.FC{Input: 64, Output: 32, Init: gorgonia.Zeroes()},
	layer.FC{Input: 32, Output: out.Squeeze()[0], Activation: layer.Linear, Init: gorgonia.Zeroes()},
)

err = qModel.Compile(in, out,
	m.WithBatchSize(1),
)
if err != nil {
	return nil, err
}

I want the initial output of the network to be zero for any input. What am I doing wrong?

opened by bandreghetti 1

Create SetLearnables

SetLearnables is a slight tweak on CloneLearnablesTo. It receives desired learnables of type gorgonia.Nodes and sets them in the present sequantial model.

opened by samuelvenzi 0

Owner

AUNUM

GitHub

My ML - A machine learning package based on golang

my_ML a machine learning package based on golang 这是一个基于golang的机器学习库和一些机器学习的数据集，可

1 Feb 15, 2022

Labs from MIT's graduate-level Distributed Systems course

Labs from MIT's graduate-level Distributed Systems course Course website here Lab 1: MapReduce Lab 2: Raft Consensus Algorithm Lab 2A: Raft Leader Ele

0 Jun 20, 2022

This project is a collection of many of the basic tools used on Unix-like operating systems implemented in Go as a learning exercize.

GoUnix This project is a collection of many of the basic tools used on Unix-like operating systems implemented in Go as a learning exercize. The idea

65 Jul 21, 2022

Examples of Golang compared to Node.js for learning

This guide full of examples is intended for people learning Go that are coming from Node.js, although the vice versa can work too. This is not meant to be a complete guide and it is assumed that you've gone through the Tour of Go tutorial. This guide is meant to be barely good enough to help you at a high level understand how to do X in Y and doing further learning on your own is of course required.

3.5k Jan 9, 2023

Goro: A High-level Machine Learning Library for Go

Related tags

Overview

Overview

Usage

Examples

Docs

Contributing

Roadmap

You might also like...

Skill builders for learning conversational Golang.

CI/CD Learning

Collecting and learning common algorithms

Golang - A collection of small Go programs used as learning exercises

This is a learning poem for golang~

This is a learning poem for golang~

Turtorial - A Hard Fork Of Icexin's Great Gocraft Project Aimed At Learning Basic Programming Tasks Through Turtles

Golang - Learning go aka Flow with the go

Learning Hexagonal Pattern with Golang

Comments

Type Error

Using `Init: gorgonia.Zeroes()` in every layer does not make output always zero

Create SetLearnables

Owner

AUNUM

My ML - A machine learning package based on golang

Labs from MIT's graduate-level Distributed Systems course

This project is a collection of many of the basic tools used on Unix-like operating systems implemented in Go as a learning exercize.

Examples of Golang compared to Node.js for learning

100 days of Go learning

Golang Learning resources

Contains hundreds of samples for learning Go.

Repository for learning GO lang

Learning GO language by building projects

Learning and Practice - Go Lang