News for hackers. Stuff that matters.
Re:Show HN: Invertornot.com – API to enhance your images in ... by klntsky on Monday March 25, 2024 @07:19PM (#39822400)
What's your accuracy?
Re:Show HN: Invertornot.com – API to enhance your images in ... by mattismegevand on Tuesday March 26, 2024 @04:20AM (#39825321)
Close to 100%, this problem seem to be easily solved by the model. I plan to do cross validation and also to explore the use of a smaller model.
Re:Show HN: Invertornot.com – API to enhance your images in ... by klntsky on Tuesday March 26, 2024 @08:54AM (#39827237)
Did you separate the test dataset from the training one?
Re:Show HN: Invertornot.com – API to enhance your images in ... by gwern on Tuesday March 26, 2024 @02:48PM (#39831397)
Does it matter? It's not a research project trying to rigorously evaluate novel architectural modifications or something, but just a project trying to be useful within the limited resources of a hobbyist. If someone labeled a bunch of the remaining errors, that data would then be better used as more training data than to benchmark.

In practice, the accuracy, whatever it is, appears to be very high and more than adequate to justify its use.

Re:Show HN: Invertornot.com – API to enhance your images in ... by klntsky on Friday March 29, 2024 @07:19AM (#39862718)
Yes it does. You will always get close to 100% accuracy on small datasets if you evaluate the model using the train dataset - due to overfit.