In this workflow we are fine-tuning a ResNet50 (https://keras.io/api/applications/resnet/#resnet50-function). First, we download the network from Keras using the DL Python Network Creator node. To implement the fine-tuning approach, we freeze the parameters of all network layers except for batch normalization layers. This is done to allow the normalization to adapt to the new data. Finally, we add a new trainable network head to output cat and dog probabilities (the original network head is already removed when loading the model from Keras).
Workflow
Fine-tune VGG16
Used extensions & nodes
Created with KNIME Analytics Platform version 4.2.0
- Go to item
- Go to item
- Go to item
- Go to item
- Go to item
- Go to item
Loading deployments
Loading ad hoc executions
Legal
By using or downloading the workflow, you agree to our terms and conditions.
Discussion
Discussions are currently not available, please try again later.