setup
function
defined in module
FastAI
setup(Block, data)
Create an instance of block type
Block
from data container
data
.
setup
(
Label
,
[
"
cat
"
,
"
dog
"
,
"
cat
"
]
)
==
Label
(
[
"
cat
"
,
"
dog
"
]
)
setup(Encoding, block, data; kwargs...)
Create an encoding using statistics derived from a data container
data
with observations of block
block
. Used when some arguments of the encoding are dependent on the dataset.
data
should be the training dataset. Additional
kwargs
are passed through to the regular constructor of
Encoding
.
(
images
,
labels
)
,
blocks
=
loaddataset
(
"
imagenette2-160
"
,
(
Image
,
Label
)
)
setup
(
FastVision
.
ImagePreprocessing
,
FastVision
.
Image
{
2
}
(
)
,
images
;
buffered
=
false
)
data
,
block
=
loaddataset
(
"
adult_sample
"
,
TableRow
)
setup
(
FastTabular
.
TabularPreprocessing
,
block
,
data
)
There are
6
methods for FastAI.setup
:
The following pages link back here:
Tabular Classification, Text Classification, TimeSeries Classification
FastAI.jl , blocks/label.jl , datablock/block.jl , FastTabular.jl , blocks/tablerow.jl , encodings/tabularpreprocessing.jl , tasks/classification.jl , tasks/regression.jl , FastVision.jl , blocks/image.jl , encodings/imagepreprocessing.jl , tasks/utils.jl