0 ×

04_​Fine-tune_​VGG16

Workflow

Fine-tune VGG16
In this workflow we are fine-tuning a VGG1G network, similar to "Fine-tune VGG16 (Python)". However, we won't make use of the DL Python Learner/Executor nodes, rather we use the DL Keras Network Learner and DL Network Executor to train and execute our networks in this workflow.
deep learning Keras image classification
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. 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 data2. Workflow 02 Train simple CNN3. Workflow 03 Fine-tune VGG16 Python4. Workflow 04 Fine-tune VGG16: In this workflow we are fine-tuning a VGG1G network, similar to "Fine-tune VGG16 (Python)". However, we won't make use ofthe DL Python Learner/Executor nodes, rather we use the DL Keras Network Learner and DL Network Executor to train and execute our networks in thisworkflow. This means we don't need to write any Python script for fine-tuning and execution the VGG16 (https://keras.io/applications/#vgg16, released by VGG(http://www.robots.ox.ac.uk/~vgg/research/very_deep/) at Oxford under the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/).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)You also need a local Python installation that includes Keras. Please refer to https://www.knime.com/deeplearning#keras for installation recommendationsand further information. Replace layersRead in preprocessedimages from Workflow 01_Preprocessing.Join Prediction and actual dataAfter 20 EpochsPartition into trainingand test set> 0.5 is dogDownload network from Keras.Alternatively, you can also use theDL Keras Network Readerand load any other stored network.Replace layersExecute the trained networkFine-tune last layersFine-tune last layers andfirst convolutional layerAdjust images to matchtensorflow image iterationorder DL PythonNetwork Editor Table Reader Joiner Scorer Partitioning RowID Rule Engine DL PythonNetwork Creator DL PythonNetwork Editor DL Network Executor DL Keras NetworkLearner DL Keras NetworkLearner Dimension Swapper Preprocessing 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. 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 data2. Workflow 02 Train simple CNN3. Workflow 03 Fine-tune VGG16 Python4. Workflow 04 Fine-tune VGG16: In this workflow we are fine-tuning a VGG1G network, similar to "Fine-tune VGG16 (Python)". However, we won't make use ofthe DL Python Learner/Executor nodes, rather we use the DL Keras Network Learner and DL Network Executor to train and execute our networks in thisworkflow. This means we don't need to write any Python script for fine-tuning and execution the VGG16 (https://keras.io/applications/#vgg16, released by VGG(http://www.robots.ox.ac.uk/~vgg/research/very_deep/) at Oxford under the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/).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)You also need a local Python installation that includes Keras. Please refer to https://www.knime.com/deeplearning#keras for installation recommendationsand further information. Replace layersRead in preprocessedimages from Workflow 01_Preprocessing.Join Prediction and actual dataAfter 20 EpochsPartition into trainingand test set> 0.5 is dogDownload network from Keras.Alternatively, you can also use theDL Keras Network Readerand load any other stored network.Replace layersExecute the trained networkFine-tune last layersFine-tune last layers andfirst convolutional layerAdjust images to matchtensorflow image iterationorderDL PythonNetwork Editor Table Reader Joiner Scorer Partitioning RowID Rule Engine DL PythonNetwork Creator DL PythonNetwork Editor DL Network Executor DL Keras NetworkLearner DL Keras NetworkLearner Dimension Swapper Preprocessing

Download

Get this workflow from the following link: Download

Nodes

04_​Fine-tune_​VGG16 consists of the following 22 nodes(s):

Plugins

04_​Fine-tune_​VGG16 contains nodes provided by the following 7 plugin(s):