Icon

04. Deploy Model

Deploy the trained U-NetFor Option 1: Use the conda environment for Keras, which was already create in the previous exercise For Option 2: Use the conda environment for Tensorflow2, which was already create in the previous exercise Option 1: Deploy a Unet using No-Code nodes1. Reuse the Preprocessing Image component created in 01.Exercise to apply the identical preprocessing to the test data 2. Read in your U-Net from the previous exercise using the Model Reader node3. Use the Conda Environment Propagation node to ensure the correct conda environment (use the Keras environment created in the beginning under Preferences) is selected. 4. Use the Keras Network Executor node to apply the trained model on the test data - connections: - use the preprocessed test data as input - use the model from the Model Reader as model input - connect the conda environment flow variable from the Conda Environment Propagation node to the Flow Variable input port - Node Settings: - input column: preprocessed image column "Img Calc" - add output: select "conv2d_19/Sigmoid:0", Conversion: "To Image", rename column "output" - Executable Selection tab: select conda environment flow variable5. After converting the predicted image to labels, use the Interactive Segmentation View node to evaluate your prediction results Option 2: Deploy a Unet using Tensorflow2 nodes1. Reuse the Preprocessing Image component created in 01.Exercise to apply the identical preprocessing to the test data 2. Use the Conda Environment Propagation node to ensure the correct conda environment (use the Tensorflow2 environment created in the beginning under Preferences) is selected. 3. Read in your U-Net from the previous exercise using the Tensorflow2 Network Reader node - Node Settings: - Executable Selection tab: select conda environment flow variable4. Use the Tensorflow2 Network Executor node to apply the trained model on the test data - connections: - use the preprocessed test data as input - use the model from the Tensorflow2 Network Reader as model input - Node settings: - input columns: preprocessed image column "Img Calc" - add output: select "conv2d_19/Sigmoid:0", Conversion: "To Image", rename column "output" - Executable Selection tab: select conda environment flow variable5. After converting the predicted image to labels, use the Interactive Segmentation View node to evaluate your prediction results trained.modelconvert labelings to byteconvert image to labelmerge predicted labelswith input imagemerge predicted labelwith input imageconvert labelings to byteconvert imageto label Model Reader Image Converter Image to Labeling InteractiveSegmentation View List Files/Folders Path to String Image Reader(Table) Joiner Joiner Image Converter Image to Labeling InteractiveSegmentation View Image Reader(Table) Path to String List Files/Folders Conda EnvironmentPropagation Conda EnvironmentPropagation Deploy the trained U-NetFor Option 1: Use the conda environment for Keras, which was already create in the previous exercise For Option 2: Use the conda environment for Tensorflow2, which was already create in the previous exercise Option 1: Deploy a Unet using No-Code nodes1. Reuse the Preprocessing Image component created in 01.Exercise to apply the identical preprocessing to the test data 2. Read in your U-Net from the previous exercise using the Model Reader node3. Use the Conda Environment Propagation node to ensure the correct conda environment (use the Keras environment created in the beginning under Preferences) is selected. 4. Use the Keras Network Executor node to apply the trained model on the test data - connections: - use the preprocessed test data as input - use the model from the Model Reader as model input - connect the conda environment flow variable from the Conda Environment Propagation node to the Flow Variable input port - Node Settings: - input column: preprocessed image column "Img Calc" - add output: select "conv2d_19/Sigmoid:0", Conversion: "To Image", rename column "output" - Executable Selection tab: select conda environment flow variable5. After converting the predicted image to labels, use the Interactive Segmentation View node to evaluate your prediction results Option 2: Deploy a Unet using Tensorflow2 nodes1. Reuse the Preprocessing Image component created in 01.Exercise to apply the identical preprocessing to the test data 2. Use the Conda Environment Propagation node to ensure the correct conda environment (use the Tensorflow2 environment created in the beginning under Preferences) is selected. 3. Read in your U-Net from the previous exercise using the Tensorflow2 Network Reader node - Node Settings: - Executable Selection tab: select conda environment flow variable4. Use the Tensorflow2 Network Executor node to apply the trained model on the test data - connections: - use the preprocessed test data as input - use the model from the Tensorflow2 Network Reader as model input - Node settings: - input columns: preprocessed image column "Img Calc" - add output: select "conv2d_19/Sigmoid:0", Conversion: "To Image", rename column "output" - Executable Selection tab: select conda environment flow variable5. After converting the predicted image to labels, use the Interactive Segmentation View node to evaluate your prediction results trained.modelconvert labelings to byteconvert image to labelmerge predicted labelswith input imagemerge predicted labelwith input imageconvert labelings to byteconvert imageto label Model Reader Image Converter Image to Labeling InteractiveSegmentation View List Files/Folders Path to String Image Reader(Table) Joiner Joiner Image Converter Image to Labeling InteractiveSegmentation View Image Reader(Table) Path to String List Files/Folders Conda EnvironmentPropagation Conda EnvironmentPropagation

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: janinamothes
Created at: 2021-08-16
On NodePit since: 2021-11-15
Last update: 2024-04-26
Created with KNIME version: v4.4.1

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

Try NodePit Runner!