DL-VGG16-MultiClassification

This workflow trains a deep-learning model for image-classification with 2 or more custom image-classes.
The model is trained by transfer-learning of a VGG-16 base, pre-trained on the ImageNet dataset. The base remains frozen, only fresh dense classification layers added on top are trained.

If you use this workflow please cite:

Thomas LSV, Schaefer F and Gehrig J.
Fiji plugins for qualitative image annotations: routine analysis and application to image classification
[version 1; peer review: 1 approved with reservations]
F1000Research 2020, 9:1248 doi: 10.12688/f1000research.26872.1

External resources

• YouTube tutorial
• Publication
• Original workflow
• GitHub repository
• Example dataset