Why in binary classification of images with CNN the loss and accuracy graph are so unstable? I mean accuracy of validation test does not increase smoothly, it goes to 80%, then comes to 60%, then again goes to 84% and so on. Same is the case with train accuracy. Now how do I know that how many epochs is the optimal number?
$\begingroup$
$\endgroup$
2
-
$\begingroup$ Adjust your batch_size and learning_rate, then see $\endgroup$– 10xAINov 3, 2020 at 6:45
-
$\begingroup$ supprisely by decreasing the batch size sharply (from 100 to 12) it is working great. what do you think? $\endgroup$– NaghNov 3, 2020 at 7:23
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
There is no way to definitely note how many epochs is required. Your accuracy graphs may be unstable for several reasons such as -
- Irregular data distribution
- Faulty model
- Large batch size (as mentioned in the comments)
- Overfitting and underfitting (in this case im not too sure which one)
You can fix it through the following methods -
- Analyse your data well and see if one class is heavily grater than other.
- Make sure all duplicate images are removed.
- Try different models, start with pre-trained. Shouldn't take much compute power.
- Approach transfer learning (neural networks)
- Adjust learning rate (as mentioned above)
- General hyperparameter tuning.
if the dataset is from somewhere public, see the models and the approaches others have used. You might see where your model actually lacks.
