model_card_toolkit.Considerations
bookmark_borderbookmark
Stay organized with collections
Save and categorize content based on your preferences.
Considerations related to model construction, training, and application.
Inherits From: BaseModelCardField
model_card_toolkit.Considerations(
users: List[model_card_toolkit.User] = dataclasses.field(default_factory=list),
use_cases: List[model_card_toolkit.UseCase] = dataclasses.field(default_factory=list),
limitations: List[model_card_toolkit.Limitation] = dataclasses.field(default_factory=list),
tradeoffs: List[model_card_toolkit.Tradeoff] = dataclasses.field(default_factory=list),
ethical_considerations: List[model_card_toolkit.Risk] = dataclasses.field(default_factory=list),
_proto_type: dataclasses.InitVar[type(model_card_pb2.Considerations)] = model_card_pb2.Considerations
)
The considerations section includes qualitative information about your model,
including some analysis of its risks and limitations. As such, this section
usually requires careful consideration, and conversations with many relevant
stakeholders, including other model developers, dataset producers, and
downstream users likely to interact with your model, or be affected by its
outputs.
Attributes |
|---|
users
|
Who are the intended users of the model? This may include
researchers, developers, and/or clients. You might also include
information about the downstream users you expect to interact with your
model.
|
use_cases
|
What are the intended use cases of the model? What use cases are
out-of-scope?
|
limitations
|
What are the known limitations of the model? This may include
technical limitations, or conditions that may degrade model performance.
|
tradeoffs
|
What are the known accuracy/performance tradeoffs for the model?
|
ethical_considerations
|
What are the ethical risks involved in application
of this model? For each risk, you may also provide a mitigation strategy
that you've implemented, or one that you suggest to users.
|
Methods
clear
View source
clear()
Clear the subfields of this BaseModelCardField.
copy_from_proto
View source
copy_from_proto(
proto: message.Message
) -> 'BaseModelCardField'
Copies the contents of the model card proto into current object.
merge_from_proto
View source
merge_from_proto(
proto: message.Message
) -> 'BaseModelCardField'
Merges the contents of the model card proto into current object.
to_dict
View source
to_dict() -> Dict[str, Any]
Convert your model card to a python dictionary.
to_json
View source
to_json() -> str
Convert this class object to json.
to_proto
View source
to_proto() -> message.Message
Convert this class object to the proto.
__eq__
__eq__(
other
)
__len__
View source
__len__() -> int
Returns the number of items in a field.
Ignores None values recursively,
so the length of a field that only contains another field that has all None
values would be 0.
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2023-04-21 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2023-04-21 UTC."],[],[],null,["# model_card_toolkit.Considerations\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/model-card-toolkit/blob/v2.0.0/model_card_toolkit/model_card.py#L425-L457) |\n\nConsiderations related to model construction, training, and application.\n\nInherits From: [`BaseModelCardField`](../model_card_toolkit/BaseModelCardField) \n\n model_card_toolkit.Considerations(\n users: List[../model_card_toolkit/User] = dataclasses.field(default_factory=list),\n use_cases: List[../model_card_toolkit/UseCase] = dataclasses.field(default_factory=list),\n limitations: List[../model_card_toolkit/Limitation] = dataclasses.field(default_factory=list),\n tradeoffs: List[../model_card_toolkit/Tradeoff] = dataclasses.field(default_factory=list),\n ethical_considerations: List[../model_card_toolkit/Risk] = dataclasses.field(default_factory=list),\n _proto_type: dataclasses.InitVar[type(model_card_pb2.Considerations)] = model_card_pb2.Considerations\n )\n\nThe considerations section includes qualitative information about your model,\nincluding some analysis of its risks and limitations. As such, this section\nusually requires careful consideration, and conversations with many relevant\nstakeholders, including other model developers, dataset producers, and\ndownstream users likely to interact with your model, or be affected by its\noutputs.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Attributes ---------- ||\n|--------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `users` | Who are the intended users of the model? This may include researchers, developers, and/or clients. You might also include information about the downstream users you expect to interact with your model. |\n| `use_cases` | What are the intended use cases of the model? What use cases are out-of-scope? |\n| `limitations` | What are the known limitations of the model? This may include technical limitations, or conditions that may degrade model performance. |\n| `tradeoffs` | What are the known accuracy/performance tradeoffs for the model? |\n| `ethical_considerations` | What are the ethical risks involved in application of this model? For each risk, you may also provide a mitigation strategy that you've implemented, or one that you suggest to users. |\n\n\u003cbr /\u003e\n\nMethods\n-------\n\n### `clear`\n\n[View source](https://github.com/tensorflow/model-card-toolkit/blob/v2.0.0/model_card_toolkit/base_model_card_field.py#L174-L182) \n\n clear()\n\nClear the subfields of this BaseModelCardField.\n\n### `copy_from_proto`\n\n[View source](https://github.com/tensorflow/model-card-toolkit/blob/v2.0.0/model_card_toolkit/base_model_card_field.py#L129-L132) \n\n copy_from_proto(\n proto: message.Message\n ) -\u003e 'BaseModelCardField'\n\nCopies the contents of the model card proto into current object.\n\n### `merge_from_proto`\n\n[View source](https://github.com/tensorflow/model-card-toolkit/blob/v2.0.0/model_card_toolkit/base_model_card_field.py#L122-L127) \n\n merge_from_proto(\n proto: message.Message\n ) -\u003e 'BaseModelCardField'\n\nMerges the contents of the model card proto into current object.\n\n### `to_dict`\n\n[View source](https://github.com/tensorflow/model-card-toolkit/blob/v2.0.0/model_card_toolkit/base_model_card_field.py#L168-L172) \n\n to_dict() -\u003e Dict[str, Any]\n\nConvert your model card to a python dictionary.\n\n### `to_json`\n\n[View source](https://github.com/tensorflow/model-card-toolkit/blob/v2.0.0/model_card_toolkit/base_model_card_field.py#L164-L166) \n\n to_json() -\u003e str\n\nConvert this class object to json.\n\n### `to_proto`\n\n[View source](https://github.com/tensorflow/model-card-toolkit/blob/v2.0.0/model_card_toolkit/base_model_card_field.py#L51-L81) \n\n to_proto() -\u003e message.Message\n\nConvert this class object to the proto.\n\n### `__eq__`\n\n __eq__(\n other\n )\n\n### `__len__`\n\n[View source](https://github.com/tensorflow/model-card-toolkit/blob/v2.0.0/model_card_toolkit/base_model_card_field.py#L39-L44) \n\n __len__() -\u003e int\n\nReturns the number of items in a field.\nIgnores None values recursively,\nso the length of a field that only contains another field that has all None\nvalues would be 0."]]
View source on GitHub