New
Guides
Samples
Module Changes
arcgis.gis
User
- Adds
generate_direct_access_url()
method for upload of large files to datastores
- Adds
arcgis.raster
- Adds new submodule
arcgis.raster.utils
- functions to interact with ArcGIS Online raster stores
ImageryLayer
- Adds
process_as_multidimensional
parameter to following functions:
- Adds
arcgis.raster.analytics
- Adds new functions:
compute_change_raster
analyze_changes_using_landtrendr
zonal_statistics_as_table
- Adds note to
tiles_only
parameter documentation to clarify its use and avaiability to create dynamic imagery in all relevant methods
arcgis.geoanalytics
- Adds
ellapse_time
property toGPJob
returned when tools are run asynchronously
arcgis.learn
- New Table of Contents heading:
- New Table of Contents entry and models:
- Adds cell size ranges and output units to trained models (
Esri Model Definitions
) - Adds
monitor
parameter tofit()
methods of models for use withearly_stopping
andcheckpoint
Data Preparation Methods
- Adds documentation to
path
parameter forprepare_data()
- Adds keyword parameters and documentation to
prepare_data()
:min_points
classes_of_interest
extra_features
remap_classes
background_classcode
- Adds ability to use a folder or list of paths (multi-folder support) in
path
parameter forprepare_data()
- Adds
working_dir
parameter to data prepartion methods which sets a default path as a prefix for saving trained models and checkpoints
- Adds documentation to
Unstructured Text Models
arcgis.learn.text
moduleTextClassifier
- adds support for
working_dir
parameter
- adds support for
3D Models
PointCNN
- Adds keyword parameters when using output of
prepare_data()
min_points
classes_of_interest
extra_features
remap_classes
background_classcode
- Adds ability to remap classes
- Adds documentation to describe
precision
,f1
, andrecall
metrics forfit()
method
- Adds keyword parameters when using output of
Feature, Tabular and Timeseries Models
- Adds ability to publish non-spatial dataframes as
Table
items with thepredict()
methods MLModel
TimeSeriesModel
- Adds ability to publish non-spatial dataframes as
Pixel Classification Models
- Adds
ConnectNet
Model - Adds
dice_loss_average
keyword parameter to initialization options - Adds inference and exports support to:
- Adds threshholding functionality to:
MultiTaskRoadExtractor
- Adds support for multispectral data
- Adds support for using multiple folders for training model
Image Translations Models
Model Management
- Adds
train_model()
method
Fixes
Samples
Module Changes
arcgis.raster
ImageryLayer
- Fixes table structure in documentation for:
- Fixes clipping input error when rendering tiles only Sentinel-2 imagery
arcgis.raster.analytics
- Improves warning documentation if
Raster Function Template (RFT)
initialization fails - Fixes issue where
create_image_collection()
created blank output ifinput_rasters
referred toSentinel-2
orPleiades
data
arcgis.raster.functions
- Fixes table structure in documentation for:
- Fixes incorrect
band_indexes
parameter order innbr
documentation
arcgis.network.analysis
- Fixes
Token Required
errors when using tools withGIS
object created usingapi_key
:
arcgis.learn
- Fixes to various functions and model methods for
ArcGIS Pro Notebooks
show_batch()
lr_find()
model.show_results()
- Fixes
WARNING 003054: Input Raster does not support PIXEL_SPACE (raw image space). Running in MAP_SPACE
warning message when running the Classify Pixels Using Deep Learning tool inArcGIS Pro
Data Preparation Methods
- Fixes
expected scalar type Float
Exception withprepare_data()
when usingpytorch 1.7.0
- Fixes
Pixel Classification Models
- Improves
per_class_metrics()
results on models initialized from unbalanced datasets - Fixes
fit()
method in segmentation models returningNaN
values for certain attributes:UNetClassifier
,PSPNetClassifier
,DeepLab
MultiTaskRoadExtractor
- Fixes issue for
show_results()
plotting images incorrectly - Fixes issue causing
save()
only to work after callingfit()
- Fixes
load()
so it only needs the model name - Fixes errors with
fit()
when using monitor functionality - Fixes parameter table for
show_results()
documentation
- Improves
Unstructured Text Models
arcgis.learn.text
module- Adds capability to use
HuggingFace
pretrained models for: - Adds transformer backbone options for:
- Adds capability to use
Object Classification Models
Feature Classifier
- Fixes error when using an input object resulting from
prepare_data(dataset_type='ImageNet')
- Fixes issues with
plot_confusion_matrix()
- when using with an object created with
backend=tensorflow
- illegible results when dataset has a large number of classes
- when run on object created from the
from_model()
method and with adata
argument
- when using with an object created with
- Fixes issue with
lr_find()
:- with object created with
mixup=True
- with
MultiLabeled_Tiles
dataset type object andmixup=True
- with object created with
- Fixes issue with using
predict()
on a trained model
- Fixes error when using an input object resulting from
Feature, Tabular and Timeseries Models
MLModel
- Fixes inaccurate
predict()
results because training transformations were not incorporating training statistics
- Fixes inaccurate
TimeSeriesModel
- Fixes
AttributeError: '<object-name>' object has no attribute 'inverse_transform'
when using thescore()
method
- Fixes
3D Models
PointCNN
- Fixes bug with
predict_las()
returning class codes from the model instead of the actual class codes in specific scenarios - Fixes error message raised with
from_model()
if library dependencies are missing - Fixes
show_results()
andshow_batch()
when run against data object created with aremap_classes
argument inprepare_data()
- Fixes bug with
Object Detection Models
SingleShotDetector
- Fixes out of memory error when using
show_results()
on model with multispectral data - Fixes error when loading and executing on CPU device
- Fixes out of memory error when using
RetinaNet
- Fixes issue where
FasterRCNN
andMaskRCNN
returned no results with multispectral data- Fixes error when loading and executing on CPU device
Image Translation Models
Pix2Pix
- Fixes
Key Error
when callingsave()
on object created with mulitspectral data - Fixes issue with
save()
not having an FID metric - Fixes issue with
compute_metrics()
returning too many significant digits
- Fixes
CycleGAN
compute_metrics()
- Fixes issue with returning FID metrics without respective names
- Fixes issue with values returning with too many significant digits
SuperResolution
- Fixes issue with
compute_metrics()
returning PSNR and SSIM metrics without respective names - Fixes issue with
prepare_data()
failing fordataset_type='superres'
or when usingsuperres
data fordata
argument
- Fixes issue with
ImageCaptioner
- Fixes
AttributError
about missing temporary folder withlr_find()
- Fixes