Transfer Learning Inception V3 : Continue Training if Accuracy Fluctuating?

0
votes

I'm still doing transfer learning using Inception V3 on tensorflow. Here is the screenshot of my training using Tensorboard.
Base training source code : https://raw.githubusercontent.com/tensorflow/hub/master/examples/image_retraining/retrain.py

My dataset is around 1 mil with 80:10:10 training:validation:test ratio.
32:128 for training batch size:validation batch size
0.001 learning rate

enter image description here

As you can see the training accuracy and validation accuracy keep fluctuating (up and down). Is there any point to continue the training? Or is there something that causes this problem that I can try to solve?

1
tensorflowdeep-learningtraining-data
Do you have more metrics? Maybe your batchsize, learning rate combination is not optimal. This often results in fluctuating. For me, more metrics are needed to give an answer – Tristate
Updated my post – gameon67
Have you tried reducing learning_rate? – Pallavi
Also try k-fold cross validation or add some regularizer. – Pallavi
@PallaviJog I did try 0.0005 but same result – gameon67

1 Answers

0
votes

Looks like your accuracy is moving quite a bit. What kind of optimizer are you using? Adam? In any case, it might help if you added in learning rate decay.