Icon

2023-Valtorta-Classificazione danni da operazioni di manipolazione

There has been no title set for this workflow's metadata.

This workflow aims to classify mixed types of defect in wafer maps.
This is a portable version, where the source dataset has already been converted to table.

URL: Dataset and documentation on Kaggle https://www.kaggle.com/datasets/co1d7era/mixedtype-wafer-defect-datasets

Keras neural network setup. Data preparation. Appendingone-hot encodedlabels to images.Converting row to52x52 image.Converting stringcolumns to collectioncontaing images data.Img size: 52x52Kernel size: 2x2.Pool size: 2x2Neruron: 100Linear activation func.Neuron: 8Sigmoid activation func.Epochs: 10Batch size: 100Splitting training set(60-40)Splitting validation setand test set (50-50)Recognisingdefects.Converting probabilityto predictions.Visualizing images.Exporting model.Reading labels data.Reading maps. Column Appender Data Row to Image Create CollectionColumn Keras Input Layer Keras Convolution2D Layer Keras AveragePooling 2D Layer Keras Flatten Layer Keras Dense Layer Keras Dense Layer Keras NetworkLearner Partitioning Partitioning Keras NetworkExecutor Math Formula(Multi Column) Image Viewer Visualization Model Writer Table Reader Table Reader Keras neural network setup. Data preparation. Appendingone-hot encodedlabels to images.Converting row to52x52 image.Converting stringcolumns to collectioncontaing images data.Img size: 52x52Kernel size: 2x2.Pool size: 2x2Neruron: 100Linear activation func.Neuron: 8Sigmoid activation func.Epochs: 10Batch size: 100Splitting training set(60-40)Splitting validation setand test set (50-50)Recognisingdefects.Converting probabilityto predictions.Visualizing images.Exporting model.Reading labels data.Reading maps. Column Appender Data Row to Image Create CollectionColumn Keras Input Layer Keras Convolution2D Layer Keras AveragePooling 2D Layer Keras Flatten Layer Keras Dense Layer Keras Dense Layer Keras NetworkLearner Partitioning Partitioning Keras NetworkExecutor Math Formula(Multi Column) Image Viewer Visualization Model Writer Table Reader Table Reader

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: rikyv
Created at: 2023-08-29
On NodePit since: 2023-09-26
Last update: 2024-04-26
Created with KNIME version: v5.1.1
Tags: classificationPythonDeep learning

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

Try NodePit Runner!