search

datalass1 / fastai

this repo will show code and notes covered during the fastai course
0 stars 0 forks source link

lesson 2 practice with a kaggle dataset #8

Closed datalass1 closed 5 years ago

datalass1 commented 5 years ago

To make sense of learning rates, augmentation, stochastic gradient descent with restarts, precompute=True/False, freeze and unfreeze, epochs, over-fitting, training time augmentation (TTA), confusion matrix, cycle_len and cycle_mult.

Also: Exercise: look at the other cases and convince yourself that this make sense. Exercise: how would you rewrite binary_loss using if instead of * and + ?

datalass1 commented 5 years ago

log loss: http://wiki.fast.ai/index.php/Log_Loss uploaded notebook to github.