OTB.TrainDimensionalityReduction: Train a dimensionality reduction model

Trainer for dimensionality reduction algorithms (autoencoders, PCA, SOM). All input samples are used to compute the model, like other machine learning models.The model can be used in the ImageDimensionalityReduction and VectorDimensionalityReduction applications.

Inputs

Input geometries used for training (note: all geometries from the layer will be used)

format
href
Please set a value for io.

XML file containing mean and variance of each feature.

format
href

List of field names in the input vector data used as features for training.

string
Please set a value for feat.

Sizes of the SOM map (one per dimension). For instance, [12;15] means a 2D map of size 12x15. Support2D to 5D maps.

string

Sizes of the initial neighborhood in the SOM map (one per dimension). The number of sizes should be the same as the map sizes

string

Number of iterations for SOM learning

integer

Initial learning coefficient

number

Final learning coefficient

number

Maximum initial neuron weight

number

Available memory for processing (in MB).

integer

Outputs

Output file containing the estimated model (.txt format).

format
transmission

Execution options

successUri
inProgressUri
failedUri

format

mode

Execute End Point

View the execution endpoint of a process.

{"id": "OTB.TrainDimensionalityReduction", "title": "Train a dimensionality reduction model", "description": "Trainer for dimensionality reduction algorithms (autoencoders, PCA, SOM). All input samples are used to compute the model, like other machine learning models.The model can be used in the ImageDimensionalityReduction and VectorDimensionalityReduction applications.", "mutable": false, "version": "1.0.0", "jobControlOptions": ["sync-execute", "async-execute", "dismiss"], "outputTransmission": ["value", "reference"], "links": [{"rel": "http://www.opengis.net/def/rel/ogc/1.0/execute", "type": "application/json", "title": "Execute End Point", "href": "https://host1.tb.geonovum.geolabs.fr/ogc-api/processes/OTB.TrainDimensionalityReduction/execution"}], "inputs": {"io": {"title": "Input geometries used for training (note: all geometries from the layer will be used)", "description": "Input geometries used for training (note: all geometries from the layer will be used)", "extended-schema": {"oneOf": [{"allOf": [{"$ref": "http://zoo-project.org/dl/link.json"}, {"type": "object", "properties": {"type": {"enum": ["text/xml", "application/vnd.google-earth.kml+xml", "application/json", "application/zip"]}}}]}, {"type": "object", "required": ["value"], "properties": {"value": {"oneOf": [{"type": "string", "contentEncoding": "utf-8", "contentMediaType": "text/xml"}, {"type": "string", "contentEncoding": "utf-8", "contentMediaType": "application/vnd.google-earth.kml+xml"}, {"type": "object"}, {"type": "string", "contentEncoding": "base64", "contentMediaType": "application/zip"}]}}}]}, "schema": {"oneOf": [{"type": "string", "contentEncoding": "utf-8", "contentMediaType": "text/xml"}, {"type": "string", "contentEncoding": "utf-8", "contentMediaType": "application/vnd.google-earth.kml+xml"}, {"type": "object"}, {"type": "string", "contentEncoding": "base64", "contentMediaType": "application/zip"}]}, "raw_schema1": "true", "id": "io"}, "io.stats": {"title": "XML file containing mean and variance of each feature.", "description": "XML file containing mean and variance of each feature.", "minOccurs": 0, "extended-schema": {"oneOf": [{"allOf": [{"$ref": "http://zoo-project.org/dl/link.json"}, {"type": "object", "properties": {"type": {"enum": ["text/xml"]}}}]}, {"type": "object", "required": ["value"], "properties": {"value": {"oneOf": [{"type": "string", "contentEncoding": "utf-8", "contentMediaType": "text/xml"}]}}}], "nullable": true}, "schema": {"oneOf": [{"type": "string", "contentEncoding": "utf-8", "contentMediaType": "text/xml"}]}, "raw_schema1": "true", "id": "io.stats"}, "feat": {"title": "List of field names in the input vector data used as features for training.", "description": "List of field names in the input vector data used as features for training.", "maxOccurs": 1024, "schema": {"type": "string"}, "id": "feat"}, "algorithm": {"title": "Sizes of the SOM map (one per dimension). For instance, [12;15] means a 2D map of size 12x15. Support2D to 5D maps.", "description": "Sizes of the SOM map (one per dimension). For instance, [12;15] means a 2D map of size 12x15. Support2D to 5D maps.", "minOccurs": 0, "maxOccurs": 1024, "schema": {"type": "string", "default": "10 10", "nullable": true}, "id": "algorithm"}, "algorithm.som.n": {"title": "Sizes of the initial neighborhood in the SOM map (one per dimension). The number of sizes should be the same as the map sizes", "description": "Sizes of the initial neighborhood in the SOM map (one per dimension). The number of sizes should be the same as the map sizes", "minOccurs": 0, "maxOccurs": 1024, "schema": {"type": "string", "default": "3 3", "nullable": true}, "id": "algorithm.som.n"}, "algorithm.som.ni": {"title": "Number of iterations for SOM learning", "description": "Number of iterations for SOM learning", "minOccurs": 0, "schema": {"type": "integer", "default": 5, "nullable": true}, "id": "algorithm.som.ni"}, "algorithm.som.bi": {"title": "Initial learning coefficient", "description": "Initial learning coefficient", "minOccurs": 0, "schema": {"type": "number", "default": 1, "format": "float", "nullable": true}, "id": "algorithm.som.bi"}, "algorithm.som.bf": {"title": "Final learning coefficient", "description": "Final learning coefficient", "minOccurs": 0, "schema": {"type": "number", "default": 0.1, "format": "float", "nullable": true}, "id": "algorithm.som.bf"}, "algorithm.som.iv": {"title": "Maximum initial neuron weight", "description": "Maximum initial neuron weight", "minOccurs": 0, "schema": {"type": "number", "default": 10, "format": "float", "nullable": true}, "id": "algorithm.som.iv"}, "ram": {"title": "Available memory for processing (in MB).", "description": "Available memory for processing (in MB).", "minOccurs": 0, "schema": {"type": "integer", "default": 256, "nullable": true}, "id": "ram"}}, "outputs": {"io.out": {"title": "Output file containing the estimated model (.txt format).", "description": "Output file containing the estimated model (.txt format).", "extended-schema": {"oneOf": [{"allOf": [{"$ref": "http://zoo-project.org/dl/link.json"}, {"type": "object", "properties": {"type": {"enum": ["text/xml", "text/plain"]}}}]}, {"type": "object", "required": ["value"], "properties": {"value": {"oneOf": [{"type": "string", "contentEncoding": "utf-8", "contentMediaType": "text/xml"}, {"type": "string", "contentEncoding": "utf-8", "contentMediaType": "text/plain"}]}}}]}, "schema": {"oneOf": [{"type": "string", "contentEncoding": "utf-8", "contentMediaType": "text/xml"}, {"type": "string", "contentEncoding": "utf-8", "contentMediaType": "text/plain"}]}, "raw_schema1": "true", "id": "io.out"}}}

https://host1.tb.geonovum.geolabs.fr/ogc-api/processes/OTB.TrainDimensionalityReduction.html
Last modified: Sat Feb 19 15:43:34 CET 2022