So I'm working on a classification problem, I used convolutional neural networks to classify grayscale ECG beat images of dimension 200x200 (I had around 4000 images for each class in training and I had 4 classes), the model is shown below:
I'm getting these results:
and the loss and accuracy curves ar shown below :
When studying deep learning theory, I learned that when using minibatch gradient descent the loss curves will have some noise in it, but in my case I'm not seeing any noise the loss is decreasing smoothly, so are my results logical?? If so please can you explain why I didn't get any noise in my curve? Thank you in advance.
