learningtasks
function
defined in module
FastAI.Registries
learningtasks(; filters...)
Show a registry of available learning tasks. Pass in filters as keyword arguments to look at a subset.
See also
finding functionality,
datasets
, and
datarecipes
. For more information on registries, see
FeatureRegistries.jl
.
Show all available learning tasks:
using
FastAI
,
FastVision
learningtasks
(
)
ID | Name | Block types | Category | Description | Learning task | Package |
---|---|---|---|---|---|---|
:id | :name | :blocks | :category | :description | :constructor | :package |
"vision/imageclfmulti" | Image classification (multi-label) |
|
supervised | Multi-label image classification task where every image can have multiple class labels associated with it. |
|
|
"vision/imagekeypoint" | Image keypoint regression |
|
supervised | Keypoint regression task with a fixed number of keypoints to be detected. |
|
|
"vision/imagesegmentation" | Image segmentation |
|
supervised | Semantic segmentation task in which every pixel in an image is classified. |
|
|
"vision/imageclfsingle" | Image classification (single-label) |
|
supervised | Single-label image classification task where every image has a single class label associated with it. |
|
|
"tabular/clfsingle" | Tabular classification (single-label) |
|
supervised | Task where a table row with categorical and continuous variables is classified as one of a number of classes. |
|
|
"tabular/regression" | Tabular regression |
|
supervised | Task where a number of continuous variables are regressed from a table row with categorical and continuous variables. |
|
|
Show all computer vision tasks:
learningtasks
(
package
=
FastVision
)
ID | Name | Block types | Category | Description | Learning task | Package |
---|---|---|---|---|---|---|
:id | :name | :blocks | :category | :description | :constructor | :package |
"vision/imageclfmulti" | Image classification (multi-label) |
|
supervised | Multi-label image classification task where every image can have multiple class labels associated with it. |
|
|
"vision/imagekeypoint" | Image keypoint regression |
|
supervised | Keypoint regression task with a fixed number of keypoints to be detected. |
|
|
"vision/imagesegmentation" | Image segmentation |
|
supervised | Semantic segmentation task in which every pixel in an image is classified. |
|
|
"vision/imageclfsingle" | Image classification (single-label) |
|
supervised | Single-label image classification task where every image has a single class label associated with it. |
|
|
Show all classification tasks, i.e. where the target block is a
Label
:
learningtasks
(
blocks
=
(
Any
,
Label
)
)
ID | Name | Block types | Category | Description | Learning task | Package |
---|---|---|---|---|---|---|
:id | :name | :blocks | :category | :description | :constructor | :package |
"vision/imageclfsingle" | Image classification (single-label) |
|
supervised | Single-label image classification task where every image has a single class label associated with it. |
|
|
"tabular/clfsingle" | Tabular classification (single-label) |
|
supervised | Task where a table row with categorical and continuous variables is classified as one of a number of classes. |
|
|
Get an explanation of fields in the learning task registry:
info
(
learningtasks
(
)
)
Information on registry Learning tasks
Fields:
Name Column Type Description
ID :id (ID) String
Name :name String The name of the learning task
Block types :blocks Any Types of the blocks that are compatible with this task
Category :category String Kind of task, e.g. "supervised"
Description :description String More information about the learning task
Learning task :constructor Any Function instance to create a corresponding learning task.
Package :package Module
Description:
A registry for learning tasks. loading an entry will return a function that
can be used to construct a LearningTask given blocks.
taskfn = load(learningtasks(id))
task = taskfn(blocks; kwargs...)
Inspect ?taskfn for documentation on the arguments that the function
accepts.
See datarecipes to load these datasets in a format compatible with learning
tasks.
There is
1
method for FastAI.Registries.learningtasks
:
The following pages link back here:
Discovery, Feature registries in FastAI.jl, How to find functionality