Icon

kn_​dl_​01_​preprocess_​image_​data

Preprocess image data

In this workflow we pre-process the image data, which we will use throughout the following example workflows.


Please note: The workflow series is heavily inspired by the great blog-post of François Chollet (see https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html.)

1. Workflow 01 Preprocess image data: In this workflow we pre-process the image data, which we will use throughout the following example workflows. You can download the data from https://www.kaggle.com/c/dogs-vs-cats/data (file train.zip) and unzip it to a desired location.

2. Workflow 02 Train simple CNN
3. Workflow 03 Fine-tune VGG16 Python
4. Workflow 04 Fine-tune VGG16

In order to run the example, please make sure you have the following KNIME extensions installed:

- KNIME Deep Learning - Keras Integration (Labs)
- KNIME Image Processing (Community Contributions Trusted)
- KNIME Image Processing - Deep Learning Extension (Community Contributions Trusted)
- KNIME Image Processing - Python Extension (Community Contributions Trusted)
- KNIME Streaming Execution (Labs)

You also need a local Python installation that includes Keras. Please refer to https://www.knime.com/deeplearning#keras for installation recommendations and further information.



KNIME Deep Learning - Classify Cats and Dogs In this series of workflows we want to demonstrate how to solve an image classification problem using KNIME Deep Learning - Keras integration.We want to train a model to distinguish cats and dogs on images. Data from:https://www.kaggle.com/c/dogs-vs-cats/overviewAdapted from:Keras - Cats vs. Dogs (christian.birkhold)https://hub.knime.com/knime/spaces/Examples/latest/04_Analytics/14_Deep_Learning/02_Keras/04_Cats_and_Dogs~gEkDg2tB3SliwDgo/ Read, normalize and resizethe input images.First 12500 rowsare cats, rest dogs.$File name$ LIKE "*cat*" =>"Cat"$File name$ LIKE "*dog*" =>"Dog"We only work with 6.000 randomly selected images.You can adjust the numberas desired.Sort bypath name.../data/train/from the downloaded file"dogs-vs-cats.zip"from Kaggle extract all the files fromthe "train.zip" to:to ../data/train/../data/preprocessed_150x150.table10%just to get thesetup running../data/preprocessed_150x150_sample.table Load and preprocessimages (Local Files) Rule Engine Row Sampling Sorter List Files/Folders Path to URI URL to File Path Table Writer Row Sampling Table Writer KNIME Deep Learning - Classify Cats and Dogs In this series of workflows we want to demonstrate how to solve an image classification problem using KNIME Deep Learning - Keras integration.We want to train a model to distinguish cats and dogs on images. Data from:https://www.kaggle.com/c/dogs-vs-cats/overviewAdapted from:Keras - Cats vs. Dogs (christian.birkhold)https://hub.knime.com/knime/spaces/Examples/latest/04_Analytics/14_Deep_Learning/02_Keras/04_Cats_and_Dogs~gEkDg2tB3SliwDgo/ Read, normalize and resizethe input images.First 12500 rowsare cats, rest dogs.$File name$ LIKE "*cat*" =>"Cat"$File name$ LIKE "*dog*" =>"Dog"We only work with 6.000 randomly selected images.You can adjust the numberas desired.Sort bypath name.../data/train/from the downloaded file"dogs-vs-cats.zip"from Kaggle extract all the files fromthe "train.zip" to:to ../data/train/../data/preprocessed_150x150.table10%just to get thesetup running../data/preprocessed_150x150_sample.table Load and preprocessimages (Local Files) Rule Engine Row Sampling Sorter List Files/Folders Path to URI URL to File Path Table Writer Row Sampling Table Writer

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: jon
Created at: 2017-10-29
On NodePit since: 2022-03-14
Last update: 2024-04-28
Created with KNIME version: v4.6.4
Tags: deep learningKerasimage classification

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!