All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
- n/a
- n/a
- The
dlm-extension
endpoint is itself deprecated in favor ofmlm-extension
(a direct fork ofdlm-extension
) with the corresponding schema hosted on https://crim-ca.github.io/mlm-extension/v1.0.0/schema.json.
- n/a
- n/a
- more Task Enum tasks
- Model Output Object
- batch_size and hardware summary
mlm:accelerator
,mlm:accelerator_constrained
,mlm:accelerator_summary
to specify hardware requirements for the model- Use common metadata Asset Object to refer to model asset and source code.
- use
classification:classes
in Model Output - add
scene-classification
to the Enum Tasks to allow disambiguation between pixel-wise and patch-based classification
disk_size
replaced byfile:size
(see Best Practices - File Extension)memory_size
underdlm:architecture
moved directly under Item properties asmlm:memory_size
- replaced all hardware/accelerator/runtime definitions into distinct
mlm
fields directly under the STAC Item properties (top-level, not nested) to allow better search support by STAC API. - reorganized
dlm:architecture
nested fields to exist at the top level of properties asmlm:name
,mlm:summary
and so on to provide STAC API search capabilities. - replaced
normalization:mean
, etc. with statistics from STAC 1.1 common metadata - added
pydantic
models for internal schema objects instac_model
package and published to PYPI - specified rel_type to be
derived_from
and specify how model item or collection json should be named - replaced all Enum Tasks names to use hyphens instead of spaces
- replaced
dlm:task
bymlm:tasks
using an array of value instead of a single one, allowing models to represent multiple tasks they support simultaneously or interchangeably depending on context - replace
pre_processing_function
andpost_processing_function
to use similar definitions to the Processing Extension - Expression Object such that more extended definitions of custom processors can be defined. - updated JSON schema to reflect changes of MLM fields
- any
dlm
-prefixed field or property
- Data Object, replaced with Model Input Object that uses the
name
field from the common metadata band object which also recordsdata_type
andnodata
type
- n/a
- Added example model architecture summary text.
- Modified
$id
if the extension schema to refer to the expected location when eventually released (https://schemas.stacspec.org/v1.0.0-beta.3/extensions/dl-model/json-schema/schema.json
). - Replaced
dtype
field bydata_type
to better align with the corresponding field ofraster:bands
. - Replaced
nodata_value
field bynodata
to better align with the corresponding field ofraster:bands
. - Refactored schema to use distinct definitions and references instead of embedding all objects
within
dl-model
properties. - Allow schema to contain other
dlm:
-prefixed elements usingpatternProperties
and explicitly deny otheradditionalProperties
. - Allow
class_name_mapping
to be directly provided as a mapping of index-based properties and class-name values.
- Specifying
class_name_mapping
by array is deprecated. Direct mapping as an object of index to class name should be used. For backward compatibility, mapping as array and using nested objects withindex
andclass_name
properties is still permitted, although overly verbose compared to the direct mapping.
- Field
nodata_value
. - Field
dtype
.
- Fixed references to other STAC extensions to use the official schema links on
https://stac-extensions.github.io/
. - Fixed examples to refer to local files.
- Fixed formatting of tables and descriptions in README.
- Initial release of the extension description and schema.
- n/a
- n/a
- n/a
- n/a