arcprize
arcprize copied to clipboard
The data needs to get harder incrementally. It's pointless to train a fresh model on something a 100 IQ person probably couldn't solve. Starting with ultra simple tasks until loss...
We should evaluate every 100 epochs to get a sense of improvement
We are kind of blindly just matrix transforming, color swapping and augmenting. - Implement visualization of current augmentation to verify that it makes sense - Add noise patterns underneath black...