rubixml / mnist Goto Github PK

Handwritten digit recognizer using a feed-forward neural network and the MNIST dataset of 70,000 human-labeled handwritten digits.

Home Page: https://rubixml.com

License: MIT License

PHP 100.00%

neural-network computer-vision mnist mnist-dataset mnist-handwriting-recognition image-classification php machine-learning deep-learning deep-neural-networks

mnist's Issues

dont recognize

hello,

after train and validate the model can not recognize a png hand written numeric image.why?
what need i to set yet for fine working?

Regards,
Gabor

Running train.php ends up with PHP Fatal Error

I`m using 0.0.18-beta version of this library with PHP Version 7.3.12 bundled in XAMPP Version: 7.3.12 on Windows 10.
Whenever I try to run train.php, I get the following error:

C:\xampp\php\php.exe D:\Projects\MNIST\train.php
Loading data into memory ...
Training ...
[2020-02-02 12:01:26] MNIST.INFO: Fitted ZScaleStandardizer
PHP Fatal error:  Uncaught InvalidArgumentException: Classifiers require categorical labels, continuous given. in D:\Projects\MNIST\vendor\rubix\ml\src\Other\Specifications\LabelsAreCompatibleWithLearner.php:27
Stack trace:
#0 D:\Projects\MNIST\vendor\rubix\ml\src\Classifiers\MultilayerPerceptron.php(347): Rubix\ML\Other\Specifications\LabelsAreCompatibleWithLearner::check(Object(Rubix\ML\Datasets\Labeled), Object(Rubix\ML\Classifiers\MultilayerPerceptron))
#1 D:\Projects\MNIST\vendor\rubix\ml\src\Classifiers\MultilayerPerceptron.php(324): Rubix\ML\Classifiers\MultilayerPerceptron->partial(Object(Rubix\ML\Datasets\Labeled))
#2 D:\Projects\MNIST\vendor\rubix\ml\src\Pipeline.php(150): Rubix\ML\Classifiers\MultilayerPerceptron->train(Object(Rubix\ML\Datasets\Labeled))
#3 D:\Projects\MNIST\vendor\rubix\ml\src\PersistentModel.php(125): Rubix\ML\Pipeline->train(Object(Rubix\ML\Datasets\Labeled))
#4 D:\Projects\MNIST\train.php(61): Rubix\ML\PersistentModel->train(Object(Rubix\ML\Datasets\Labeled))
#5 {main}
  thrown in D:\Projects\MNIST\vendor\rubix\ml\src\Other\Specifications\LabelsAreCompatibleWithLearner.php on line 27

Fatal error: Uncaught InvalidArgumentException: Classifiers require categorical labels, continuous given. in D:\Projects\MNIST\vendor\rubix\ml\src\Other\Specifications\LabelsAreCompatibleWithLearner.php:27
Stack trace:
#0 D:\Projects\MNIST\vendor\rubix\ml\src\Classifiers\MultilayerPerceptron.php(347): Rubix\ML\Other\Specifications\LabelsAreCompatibleWithLearner::check(Object(Rubix\ML\Datasets\Labeled), Object(Rubix\ML\Classifiers\MultilayerPerceptron))
#1 D:\Projects\MNIST\vendor\rubix\ml\src\Classifiers\MultilayerPerceptron.php(324): Rubix\ML\Classifiers\MultilayerPerceptron->partial(Object(Rubix\ML\Datasets\Labeled))
#2 D:\Projects\MNIST\vendor\rubix\ml\src\Pipeline.php(150): Rubix\ML\Classifiers\MultilayerPerceptron->train(Object(Rubix\ML\Datasets\Labeled))
#3 D:\Projects\MNIST\vendor\rubix\ml\src\PersistentModel.php(125): Rubix\ML\Pipeline->train(Object(Rubix\ML\Datasets\Labeled))
#4 D:\Projects\MNIST\train.php(61): Rubix\ML\PersistentModel->train(Object(Rubix\ML\Datasets\Labeled))
#5 {main}
  thrown in D:\Projects\MNIST\vendor\rubix\ml\src\Other\Specifications\LabelsAreCompatibleWithLearner.php on line 27

UPD: I found out that label type is determined by determine() method in ...\vendor\rubix\ml\src\DataType.php and that only data of type string is corresponding to categorical type. So I tried converting each $label value to string before writing it to $labels array in train.php:

for ($label = 0; $label < 10; $label++) {
    foreach (glob("training/$label/*.png") as $file) {
        $label = strval($label);
        $samples[] = [imagecreatefrompng($file)];
        $labels[] = $label;
    }
}

This did the trick for me and I was able to run the script from PhpStorm 2019.3 built-in terminal. Nevertheless, for some reason the training only completed 1 epoch and finished. This seems to be a really strange behavior. Below is the output for that run (the prompt for saving the model does not appear on screen, but giving 'y' as the input saves the model):

C:\xampp\php\php.exe D:\Projects\MNIST\train.php
Loading data into memory ...
Training ...
[2020-02-02 17:07:40] MNIST.INFO: Fitted ZScaleStandardizer
[2020-02-02 17:07:45] MNIST.INFO: Learner init hidden=[0=Dense 1=Activation 2=Dropout 3=Dense 4=Activation 5=Dropout 6=Dense 7=Activation 8=Dropout] batch_size=200 optimizer=Adam alpha=0.0001 epochs=1000 min_change=0.0001 window=3 hold_out=0.1 cost_fn=CrossEntropy metric=FBeta
[2020-02-02 17:16:39] MNIST.INFO: Epoch 1 score=0.03078281535439 loss=0
[2020-02-02 17:16:39] MNIST.INFO: Training complete
Progress saved to progress.csv
y

Process finished with exit code 0

But when I try to run the script from Windows Command Prompt or PowerShell I get the following error:

C:\xampp\php\php.exe D:\Projects\MNIST\train.php
Loading data into memory ...
Training ...
[2020-02-02 18:04:09] MNIST.INFO: Fitted ZScaleStandardizer
PHP Fatal error:  Uncaught InvalidArgumentException: The number of input nodes must be greater than 0, 0 given. in D:\Projects\MNIST\vendor\rubix\ml\src\NeuralNet\Layers\Placeholder1D.php:34
Stack trace:
#0 D:\Projects\MNIST\vendor\rubix\ml\src\Classifiers\MultilayerPerceptron.php(316): Rubix\ML\NeuralNet\Layers\Placeholder1D->__construct(0)
#1 D:\Projects\MNIST\vendor\rubix\ml\src\Pipeline.php(150): Rubix\ML\Classifiers\MultilayerPerceptron->train(Object(Rubix\ML\Datasets\Labeled))
#2 D:\Projects\MNIST\vendor\rubix\ml\src\PersistentModel.php(125): Rubix\ML\Pipeline->train(Object(Rubix\ML\Datasets\Labeled))
#3 D:\Projects\MNIST\train.php(71): Rubix\ML\PersistentModel->train(Object(Rubix\ML\Datasets\Labeled))
#4 {main}
  thrown in D:\Projects\MNIST\vendor\rubix\ml\src\NeuralNet\Layers\Placeholder1D.php on line 34

Fatal error: Uncaught InvalidArgumentException: The number of input nodes must be greater than 0, 0 given. in D:\Projects\MNIST\vendor\rubix\ml\src\NeuralNet\Layers\Placeholder1D.php:34
Stack trace:
#0 D:\Projects\MNIST\vendor\rubix\ml\src\Classifiers\MultilayerPerceptron.php(316): Rubix\ML\NeuralNet\Layers\Placeholder1D->__construct(0)
#1 D:\Projects\MNIST\vendor\rubix\ml\src\Pipeline.php(150): Rubix\ML\Classifiers\MultilayerPerceptron->train(Object(Rubix\ML\Datasets\Labeled))
#2 D:\Projects\MNIST\vendor\rubix\ml\src\PersistentModel.php(125): Rubix\ML\Pipeline->train(Object(Rubix\ML\Datasets\Labeled))
#3 D:\Projects\MNIST\train.php(71): Rubix\ML\PersistentModel->train(Object(Rubix\ML\Datasets\Labeled))
#4 {main}
  thrown in D:\Projects\MNIST\vendor\rubix\ml\src\NeuralNet\Layers\Placeholder1D.php on line 34

PHP Fatal Error while I try to run train.php

PHP Fatal Error while I try to run train.php using 0.0.18-beta version of this library, XAMPP and PHP 7.3.8 on Windows 10

C:\xampp\php\php.exe D:\[projects]\PhpStorm\MNIST\train.php
Loading data into memory ...
Training ...
[2020-02-02 16:47:36] MNIST.INFO: Fitted ZScaleStandardizer

Fatal error: Uncaught InvalidArgumentException: The number of input nodes must be greater than 0, 0 given. in D:\[projects]\PhpStorm\MNIST\vendor\rubix\ml\src\NeuralNet\Layers\Placeholder1D.php:34
Stack trace:
#0 D:\[projects]\PhpStorm\MNIST\vendor\rubix\ml\src\Classifiers\MultilayerPerceptron.php(316): Rubix\ML\NeuralNet\Layers\Placeholder1D->__construct(0)
#1 D:\[projects]\PhpStorm\MNIST\vendor\rubix\ml\src\Pipeline.php(150): Rubix\ML\Classifiers\MultilayerPerceptron->train(Object(Rubix\ML\Datasets\Labeled))
#2 D:\[projects]\PhpStorm\MNIST\vendor\rubix\ml\src\PersistentModel.php(125): Rubix\ML\Pipeline->train(Object(Rubix\ML\Datasets\Labeled))
#3 D:\[projects]\PhpStorm\MNIST\train.php(61): Rubix\ML\PersistentModel->train(Object(Rubix\ML\Datasets\Labeled))
#4 {main}
  thrown in D:\[projects]\PhpStorm\MNIST\vendor\rubix\ml\src\NeuralNet\Layers\Placeholder1D.php on line 34
PHP Fatal error:  Uncaught InvalidArgumentException: The number of input nodes must be greater than 0, 0 given. in D:\[projects]\PhpStorm\MNIST\vendor\rubix\ml\src\NeuralNet\Layers\Placeholder1D.php:34
Stack trace:
#0 D:\[projects]\PhpStorm\MNIST\vendor\rubix\ml\src\Classifiers\MultilayerPerceptron.php(316): Rubix\ML\NeuralNet\Layers\Placeholder1D->__construct(0)
#1 D:\[projects]\PhpStorm\MNIST\vendor\rubix\ml\src\Pipeline.php(150): Rubix\ML\Classifiers\MultilayerPerceptron->train(Object(Rubix\ML\Datasets\Labeled))
#2 D:\[projects]\PhpStorm\MNIST\vendor\rubix\ml\src\PersistentModel.php(125): Rubix\ML\Pipeline->train(Object(Rubix\ML\Datasets\Labeled))
#3 D:\[projects]\PhpStorm\MNIST\train.php(61): Rubix\ML\PersistentModel->train(Object(Rubix\ML\Datasets\Labeled))
#4 {main}
  thrown in D:\[projects]\PhpStorm\MNIST\vendor\rubix\ml\src\NeuralNet\Layers\Placeholder1D.php on line 34

Process finished with exit code 255

getcomposer link in readme leads to phishing site

the correct link to get composer is

https://getcomposer.org/

and not

getcomposer com

training is very slow (>8h already) and has no sensible progress indicator

In the README.md it says that training takes less than 3 hours. I let the pc work overnight for over 8 hours and it reached only epoch 6. Is there any way to reduce the training time (in exchange for worse accuracy)? Is there any chance you could provide the pre-trained mnist.model data?

installation error

Hello!
I am trying to install but pecl gives me the following error:
libtool: compile: cc -I. -I/tmp/pear/temp/tensor/ext -I/tmp/pear/temp/pear-build-rootgoI8i3/tensor-3.0.00/include -I/tmp/pear/temp/pear-build-rootgoI8i3/tensor-3.0.00/main -I/tmp/pear/temp/tensor/ext -I/usr/include/php/20210902 -I/usr/include/php/20210902/main -I/usr/include/php/20210902/TSRM -I/usr/include/php/20210902/Zend -I/usr/include/php/20210902/ext -I/usr/include/php/20210902/ext/date/lib -DHAVE_CONFIG_H -g -O2 -O3 -ffast-math -c /tmp/pear/temp/tensor/ext/kernel/main.c -MMD -MF kernel/main.dep -MT kernel/main.lo -fPIC -DPIC -o kernel/.libs/main.o /tmp/pear/temp/tensor/ext/kernel/main.c: In function ‘zephir_fast_count’: /tmp/pear/temp/tensor/ext/kernel/main.c:154:45: error: ‘spl_ce_Countable’ undeclared (first use in this function); did you mean ‘zend_ce_countable’? 154 | if (instanceof_function(Z_OBJCE_P(value), spl_ce_Countable)) { | ^~~~~~~~~~~~~~~~ | zend_ce_countable /tmp/pear/temp/tensor/ext/kernel/main.c:154:45: note: each undeclared identifier is reported only once for each function it appears in /tmp/pear/temp/tensor/ext/kernel/main.c: In function ‘zephir_fast_count_ev’: /tmp/pear/temp/tensor/ext/kernel/main.c:204:45: error: ‘spl_ce_Countable’ undeclared (first use in this function); did you mean ‘zend_ce_countable’? 204 | if (instanceof_function(Z_OBJCE_P(value), spl_ce_Countable)) { | ^~~~~~~~~~~~~~~~ | zend_ce_countable /tmp/pear/temp/tensor/ext/kernel/main.c: In function ‘zephir_fast_count_int’: /tmp/pear/temp/tensor/ext/kernel/main.c:252:45: error: ‘spl_ce_Countable’ undeclared (first use in this function); did you mean ‘zend_ce_countable’? 252 | if (instanceof_function(Z_OBJCE_P(value), spl_ce_Countable)) { | ^~~~~~~~~~~~~~~~ | zend_ce_countable /tmp/pear/temp/tensor/ext/kernel/main.c: In function ‘zephir_function_exists’: /tmp/pear/temp/tensor/ext/kernel/main.c:285:101: warning: comparison between pointer and integer 285 | if (zend_hash_str_exists(CG(function_table), Z_STRVAL_P(function_name), Z_STRLEN_P(function_name)) != NULL) { | ^~ /tmp/pear/temp/tensor/ext/kernel/main.c: In function ‘zephir_function_exists_ex’: /tmp/pear/temp/tensor/ext/kernel/main.c:301:76: warning: comparison between pointer and integer 301 | if (zend_hash_str_exists(CG(function_table), function_name, function_len) != NULL) { | ^~ make: *** [Makefile:205: kernel/main.lo] Error 1 ERROR: make' failed
`

my system is ubuntu server 20.04 with php 8.0.14
Thanks!

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.