Following https://github.com/fastai/course-v3/blob/master/nbs/dl1/lesson1-pets.ipynb

This is my own data as on hackster where my previous model had 92% accuracy

Trainng on floydhub GPU

Loading output library...

Helper to extract class label

Loading output library...
Loading output library...
Loading output library...

Training

#Training

By default fast.ai does transfer learning

Loading output library...

Error rate down to 3.4%

Lets save the state of the model

Loading output library...
Loading output library...

It appears I have a couple of incorrectly labelled images, not too surprising as I labelled them manually. Occasionally it is confusing rain for birds..?

Unfreezing, fine-tuning, and learning rates

#Unfreezing,-fine-tuning,-and-learning-rates

Lets train the whole model and see if accuracy improves..? Probably I should clean the dataset first but I am impatient

Loading output library...

Error rate up, just as in the tutorial. Lets find the best error rate

Loading output library...

OK the learning rates in range 1e-6,1e-3 look like a good bet

Loading output library...

That's an improvement already!

Loading output library...
Loading output library...

Not much in it. I wont waste compute on this dataset, but anyways we are doing better than classificationbox :)