Cannot Improve Accuracy Of Alexnet On Oxford-102 (tensorflow)

Hi I tried to implement AlexNet without using pretrained weights. I tried to train the net on Oxford-102 dataset, but I keep getting 0.9% accuracy throughout the process and changi

Solution 1:

Your accuracy looks fine to me although it's a bit strange to be defined each time in the loop.

What does bother me is the fact that you train for only ten steps. It seems that your training set consists of 6149 images and you are training 128 images in a batch. Doing this ten times, you have looked at 1280 out of 6000 images - way too few to see an effect in the accuracy.

Instead, you want to look at all the training data - that's around 48 training steps, or one epoch - and you better want to do this a couple of times. The exact number of epochs depends on multiple factors like the data and network but you should at least take 10 epochs - so that's 480 training steps.