This chapter contains some of the advanced techniques and tricks that can be used to train SOTA image classification models.
ImageNet: how many images?
ImageNet: how many categories?
ImageNet: what size are images?
differing but ~500px across
MNIST: how many images?
MNIST: how many categories?
MNIST: what size are images?
CIFAR10: how many images?
CIFAR_: how many categories? (blank gives the game away!)
CIFAR10: what size are images?
How does Imagenette differ from ImageNet?
Only 10/1000 classes, so about 1% (10k) of the number of images
If experiment iteration is slow, what can you do to the dataset?
Create a simplified version to use while iterating
When using a pre-trained model, what should you transfer as well as the weights?
FastAI: how to transfer normalisation statistics when using a pre-trained model
FastAI automatically adds a
Normalise transform with the correct statistics
What is the term for iteratively increasing the size of each datapoint during training?
What dataset modification can be used to speed up the training of CV models?
Why might progressive resizing not help for transfer learning?
If the pre-training task had a similar image size to the target task, keeping the size the same may be beneficial