ImageSegmentation
function
defined in module
FastVision
ImageSegmentation(size, classes; kwargs...)
Learning task for image segmentation. Images are resized to
size
and a class is predicted for every pixel.
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.ImageSegmentation
:
The following pages link back here:
Discovery, New visualization tools for FastAI.jl, Quickstart, fastai API comparison