Update transfer_learning.ipynb - fix initial_epoch for fine tuning

initial_epoch for the fine tuning phase should be 1 more than history.epoch[-1], so that the history_fine.epoch would be [10, 11, ...19], a total of 10 fine tune epochs.
Without the '+1', history.epoch is [0, 1, ...9], and history_fine.epoch is [9, 10, ... 19], the epoch index overlaps at 9, fine tune actually trained for 11 epochs, not 10, and the model is actually trained for 21 epochs in total (confirmed in the x axis of the combined training history curve - 21 data points)

Author: sharkfisher

site/en/tutorials/images/transfer_learning.ipynb

@@ -930,7 +930,7 @@
         "\n",
         "history_fine = model.fit(train_dataset,\n",
         "                         epochs=total_epochs,\n",
-        "                         initial_epoch=history.epoch[-1],\n",
+        "                         initial_epoch=history.epoch[-1]+1,\n",
         "                         validation_data=validation_dataset)"
       ]
     },