How to continue training a pre-trained model?

I’m currently using VGG16 pretrained model on my set of images
model = VGG16()
model = Model(inputs = model.inputs, outputs = model.layers[-2].output)
and then for each image I get its features model.predict(img, use_multiprocessing=True)
but I also would like to take some subset of my images to make a little further training of VGG16 model on that subset (so the final model would be trained on VGG16’s images + on my images)

how can I implement that?

It is very similar to the fine-tuning described in:


For a more extended tutorial take a look also to:

1 Like

I’d also add this great tutorial: إعادة تدريب مصنف الصور  |  TensorFlow Hub

It’s not specific for VGG but might give some insights