Icon

05_​Use_​a_​TFHub_​Model

Use a TensorFlow Hub model for TensorFlow 2
Alternative: Use a "DL Python NetworkCreator" and call hub.KerasLayer("<url>") Use a TensorFlow Hub model for TensorFlow 2This workflow shows how a model from the TensorFlow Hub can be used in KNIME. MobileNet isused to predict the class of 6 images. Use the "Load TensorFlow HubModel" Component Create a TF2 Networkwith MobileNet6 sampleimages......of size224x224x3Run the modelGet class withmax probabilityReplace class indexby class nameAdd Row prefixfor Cell ReplacerView the resultNormalizebetween 0 and 1ImageNet labels Load TensorFlowHub Model DL PythonNetwork Creator List Files Image Reader(Table) TensorFlow 2Network Executor Many to One Cell Replacer String Manipulation Image Viewer Image Calculator CSV Reader (Labs) Alternative: Use a "DL Python NetworkCreator" and call hub.KerasLayer("<url>") Use a TensorFlow Hub model for TensorFlow 2This workflow shows how a model from the TensorFlow Hub can be used in KNIME. MobileNet isused to predict the class of 6 images. Use the "Load TensorFlow HubModel" Component Create a TF2 Networkwith MobileNet6 sampleimages......of size224x224x3Run the modelGet class withmax probabilityReplace class indexby class nameAdd Row prefixfor Cell ReplacerView the resultNormalizebetween 0 and 1ImageNet labelsLoad TensorFlowHub Model DL PythonNetwork Creator List Files Image Reader(Table) TensorFlow 2Network Executor Many to One Cell Replacer String Manipulation Image Viewer Image Calculator CSV Reader (Labs)

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: benjamin
Created at: 2020-07-03
On NodePit since: 2020-08-25
Last update: 2024-04-18
Created with KNIME version: v4.2.0
Tags: tftfhubTensorFlow HubTensorFlowDeep LearningTensorFlow 2MobileNetImage 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!