Handwritten digit OCR
Project · study · 2024
Handwritten digit OCR is a set of Jupyter notebooks notebooks that train convolutional neural networks to recognise handwritten digits. It is written in Python with TensorFlow and Keras, and each notebook opens in Google Colab.
Experiments
The notebooks compare training set-ups on the same task:
- a CNN trained for 50 and for 200 epochs;
- the same with early stopping, which ends training when validation stops improving;
- transfer learning from VGG16, a network pre-trained on ImageNet, including a variant with a higher learning rate;
- a notebook comparing the results.
The trained models are saved in Keras format alongside them.
See also
In the knowledge graph
Handwritten digit OCR and the 11 things it is linked to. Open any dot for its page, or explore it in the full graph.
As data
Everything on this page is read from triples in the knowledge graph. These are the 24 it states about Handwritten digit OCR, and 6 more its ontology implies; the console runs SPARQL over the whole graph, here in your browser.
@prefix id: <https://ask.chaipat.cc/id/> . @prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> . @prefix cj: <https://ask.chaipat.cc/ns#> . @prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> . @prefix xsd: <http://www.w3.org/2001/XMLSchema#> . id:OCRDigits a cj:Project ; rdfs:label "Handwritten digit OCR" ; cj:description "Notebooks and models for recognising handwritten digits." ; cj:context id:OpenSource ; cj:repository "https://github.com/AppleBoiy/ocr-handwritten-digit"^^xsd:anyURI ; cj:firstCommit "2024-10-23"^^xsd:date ; cj:lastCommit "2024-10-23"^^xsd:date ; cj:commitCount 3 ; cj:kind "study" ; cj:license "MIT" ; cj:theme id:ThemeML ; cj:uses id:Python , id:Jupyter , id:MachineLearning , id:TensorFlow ; cj:tier 3 ; cj:implements id:OCR , id:CNN , id:TransferLearning , id:EarlyStopping ; cj:integrates id:GoogleColab ; cj:article "https://ask.chaipat.cc/wiki/OCRDigits"^^xsd:anyURI ; cj:activeIn id:Y2024 ; cj:activity _:b111 .