ImageClassificationSingle
function defined in module
FastVision
ImageClassificationSingle(size, classes; kwargs...)
ImageClassificationSingle(blocks[, data]; kwargs...)
Learning task for single-label image classification. Images are resized to
size and classified into one of
classes.
Use
ImageClassificationMulti for the multi-class setting.
computestats = false: Whether to compute image statistics on dataset
data or use default ImageNet stats.
aug_projections =
DataAugmentation.Identity: augmentation to apply during
ProjectiveTransforms (resizing and cropping)
aug_image =
DataAugmentation.Identity: pixel-level augmentation to apply during
ImagePreprocessing
C = RGB{N0f8}: Color type images are converted to before further processing. Use
Gray{N0f8} for grayscale images.
There are
2
methods for FastVision.ImageClassificationSingle:
The following pages link back here:
Blocks and encodings, Discovery, FastAI.jl, How to train a model, Introduction, New visualization tools for FastAI.jl, Performant data pipelines, Quickstart, fastai API comparison