Transfer learning is a method of reusing an already trained model for another task . The original training step is called pre-training. The general idea is that, pre-training “teaches” the model more general features, while the latter final training stage “teaches” it features specific to our own (limited) data.
Read moreCan you train a model with TensorFlow Lite?
After converting your model to TensorFlow Lite and deploying it with your app, you can retrain the model on a device using new data and the train signature method of your model .6 Oca 2022
Read more