Lessons from using Alexnet to train a cat/fish classifier
Learnings: Using Alexnet model with kernel settings of size=11, stride=4, padding=2, and image size of 227x227, I could reach 70% accuracy with training of 30 epochs. This, unfortunately, is the same level of accuracy as my Simplenet in the previous post Training Using a simple neural network from the previous post, I could reach an accuracy level of 0.7. However whilst implementing the following CNN from chapter 3 of the Pytorch book, I realized that I had quite a few issues trying to get it to converge. ...