Icon

Cats and Dogs Image Classification

Cats and Dogs - Training and Deploying (Based on workflows by Roberto Cadili)
Read and apply feature extraction part of VGG16 Train, execute, and evalutate network Create Keras network layers Read and preprocess imageshttps://www.kaggle.com/c/dogs-vs-cats/data Classifying Images of Cats and Dogs - TrainingThis workflow reads images of cats and dogs, performs some image preprocessing, and uses Transfer Learning (VGG16) to train the 3 top layers and evaluate a Convolutional Neural Network(CNN) for image classification (fast execution). Read and preprocess new images Apply model to new data output >= 0.5 Catoutput <0.5 DogRead pretrained VGG16Apply VGG16on training dataFlatten output to 8192 neuronsInput: 819264 neuronsReLUDrop Rate = 0.53 neuronsSoftmaxTrain the model for 5 epochs (Adam)Apply the modelon new dataEvaluate the modeloutput >= 0.5 Catoutput <0.5 DogUnify RowIDsResize to 150x150Path to 100test imagesNormalize between 0..1Read imagesRemove superfluous columnsApply the VGG16on test dataPoin to local folderwith Kaggle image train dataabout cats and dogsNode 328Node 329Node 330Node 348Apply the VGG16on test dataApply the modelon new dataRemove superfluous columnsNode 352 Rule Engine DL PythonNetwork Creator Keras NetworkExecutor Keras Flatten Layer Keras Input Layer Keras Dense Layer Keras Dropout Layer Keras Dense Layer Keras NetworkLearner Keras NetworkExecutor Scorer Rule Engine RowID Image Resizer Paths to images Image Calculator Image Reader(Table) Column Filter Keras NetworkExecutor Read andpreprocess images Conda EnvironmentPropagation Table View Table View Keras NetworkWriter Table Manipulator Keras NetworkExecutor Keras NetworkExecutor Column Filter Table Manipulator Read and apply feature extraction part of VGG16 Train, execute, and evalutate network Create Keras network layers Read and preprocess imageshttps://www.kaggle.com/c/dogs-vs-cats/data Classifying Images of Cats and Dogs - TrainingThis workflow reads images of cats and dogs, performs some image preprocessing, and uses Transfer Learning (VGG16) to train the 3 top layers and evaluate a Convolutional Neural Network(CNN) for image classification (fast execution). Read and preprocess new images Apply model to new data output >= 0.5 Catoutput <0.5 DogRead pretrained VGG16Apply VGG16on training dataFlatten output to 8192 neuronsInput: 819264 neuronsReLUDrop Rate = 0.53 neuronsSoftmaxTrain the model for 5 epochs (Adam)Apply the modelon new dataEvaluate the modeloutput >= 0.5 Catoutput <0.5 DogUnify RowIDsResize to 150x150Path to 100test imagesNormalize between 0..1Read imagesRemove superfluous columnsApply the VGG16on test dataPoin to local folderwith Kaggle image train dataabout cats and dogsNode 328Node 329Node 330Node 348Apply the VGG16on test dataApply the modelon new dataRemove superfluous columnsNode 352 Rule Engine DL PythonNetwork Creator Keras NetworkExecutor Keras Flatten Layer Keras Input Layer Keras Dense Layer Keras Dropout Layer Keras Dense Layer Keras NetworkLearner Keras NetworkExecutor Scorer Rule Engine RowID Image Resizer Paths to images Image Calculator Image Reader(Table) Column Filter Keras NetworkExecutor Read andpreprocess images Conda EnvironmentPropagation Table View Table View Keras NetworkWriter Table Manipulator Keras NetworkExecutor Keras NetworkExecutor Column Filter Table Manipulator

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: roberto.cadili
Created at: 2022-01-26
On NodePit since: 2022-11-02
Last update: 2024-12-17
Created with KNIME version: v4.6.1

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

Try NodePit Runner!