You are looking the documentation of a development version. The release version is available at master.

I2FeaturesToGrid

builders

Name

Default Value

Description

Type

Mandatory

Name

builders_class_name

[‘I2Classification’]

The name of the class defining the builder

list

False

builders_class_name

builders_paths

/path/to/iota2/sources

The path to user builders

str

False

builders_paths

Notes

builders_class_name

Available builders are : ‘I2Classification’, ‘I2FeaturesMap’ and ‘I2Obia’

builders_paths

If not indicated, the iota2 source directory is used: */iota2/sequence_builders/

chain

Name

Default Value

Description

Type

Mandatory

Name

features_path

None

input directory containing features as rasters

str

False

features_path

from_rasterdb_resampling_method

nn

output features type choice among gdalwarp.html#cmdoption-gdalwarp-r. Enabled if chain.rasters_grid_path is set

str

False

from_rasterdb_resampling_method

from_vectordb_resampling_method

near

output features type choice among gdalwarp.html#cmdoption-gdalwarp-r. Enabled if chain.grid is set

str

False

from_vectordb_resampling_method

grid

None

input grid to fit

str

False

grid

list_tile

None

List of tile to process, separated by space

str

True

list_tile

out_worldclim_dtype

float32

output worlclim data type, ie : ‘uint16’, ‘float32’.

np.dtype

False

out_worldclim_dtype

out_worldclim_rescale_range

None

rescale worldclim data between 0 and max(np.dtype) at run time for RAM usage purpose.

np.dtype

False

out_worldclim_rescale_range

output_features_pix_type

float

output features type choice among uint8/uint16/int16/uint32/int32/float/double.

str

False

output_features_pix_type

output_path

None

Absolute path to the output directory

str

True

output_path

rasters_grid_path

None

input grid to fit

str

False

rasters_grid_path

resampling_bco_radius

2

otb radius for bicubic interpolation.

int

False

resampling_bco_radius

s1_dir

None

Sentinel1 data directory

str

False

s1_dir

s2_path

None

Absolute path to Sentinel-2 images (THEIA format)

str

False

s2_path

spatial_resolution

[]

Output spatial resolution

list or scalar

True

spatial_resolution

srtm_path

None

Path to a directory containing srtm data

str

False

srtm_path

tile_field

None

column name in ‘grid’ containing tile’s name.

str

False

tile_field

worldclim_path

None

Path to a directory containing world clim data

str

False

worldclim_path

Notes

output_path

Absolute path to the output directory.It is recommended to have one directory per run of the chain

rasters_grid_path

all rasters must be in the same directory and must be named by tile ie : ‘T31TCJ.tif’

resampling_bco_radius

otb radius for bicubic interpolation. Enabled if ‘nn’ was set to bco in ‘from_rasterdb_resampling_method’ parameter

s1_dir

The directory must contains all *.SAFE Sentinel1 data.

spatial_resolution

The spatial resolution expected.It can be provided as integer or float,or as a list containing two values for non squared resolution

pretrained_model

Name

Default Value

Description

Type

Mandatory

Name

boundary_buffer

None

List of boundary buffer size

list

False

boundary_buffer

function

None

Predict function name

str

False

function

mode

None

Algorythm nature (classification or regression)

str

False

mode

model

None

Serialized object containing the model

str

False

model

module

/path/to/iota2/sources

Absolute path to the python module

str

False

module

Notes

function

This function must have the imposed signature. It not accept any others parameters. All model dedicated parameters must be stored alongside the model.

mode

The python module must contains the predict function It must handle all the potential dependencies and import related to the correct model instanciation

model

In the configuration file, the mandatory keys $REGION and $SEED must be present as they are replaced by iota2. In case of only one region, the region value is set to 1. Look at the documentation about the model constraint.

module

The python module must contains the predict function It must handle all the potential dependencies and import related to the correct model instanciation