Differences

This shows you the differences between two versions of the page.

--- pipeline:window:cryolo:picking_general_refine [2019/09/18 12:52]
twagner [4. Training]
+++ pipeline:window:cryolo:picking_general_refine [2019/09/18 12:53]
twagner [Picking particles - Using the general model refined for your data]
@@ Line 6: / Line 6: @@
 What does //fine-tuning// mean?
-The general model was trained on a lot of particles with a variety of shapes and therefore learned a robust set of generic features. The last layers, however, learn a fairly abstract representation of the particles and it might be that they do not perfectly fit your particle at hand. In order to adapt this abstract representation within the network to your specific particle, fine-tuning only affects the last two convolutional layers, but keeps all others fixed.
+The general model was trained on a lot of particles with a variety of shapes and therefore learned a robust set of generic features. The last layers, however, learn a fairly abstract representation of the particles and it might be that they do not perfectly fit your particle at hand. In order to adapt this abstract representation within the network to your specific particle, fine-tuning only affects the last convolutional layers, but keeps all others fixed.
 Why should I //fine-tune// my model instead of training from scratch?