TorchSharpCatalog Class
Definition
Important
Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.
Collection of extension methods for MulticlassClassificationCatalog.MulticlassClassificationTrainers to create instances of TorchSharp trainer components.
public static class TorchSharpCatalogtype TorchSharpCatalog = classPublic Module TorchSharpCatalog- Inheritance
-
TorchSharpCatalog
Remarks
This requires additional nuget dependencies to link against TorchSharp native dlls. See ImageClassificationTrainer for more information.
Methods
| EvaluateObjectDetection(MulticlassClassificationCatalog, IDataView, DataViewSchema+Column, DataViewSchema+Column, DataViewSchema+Column, DataViewSchema+Column, DataViewSchema+Column) |
Evaluates scored object detection data. |
| NamedEntityRecognition(MulticlassClassificationCatalog+MulticlassClassificationTrainers, NerTrainer+NerOptions) |
Fine tune a Named Entity Recognition model. |
| NamedEntityRecognition(MulticlassClassificationCatalog+MulticlassClassificationTrainers, String, String, String, Int32, Int32, BertArchitecture, IDataView) |
Fine tune a NAS-BERT model for Named Entity Recognition. The limit for any sentence is 512 tokens. Each word typically will map to a single token, and we automatically add 2 specical tokens (a start token and a separator token) so in general this limit will be 510 words for all sentences. |
| NameEntityRecognition(MulticlassClassificationCatalog+MulticlassClassificationTrainers, NerTrainer+NerOptions) |
Obsolete.
Obsolete: please use the NamedEntityRecognition(MulticlassClassificationCatalog+MulticlassClassificationTrainers, NerTrainer+NerOptions) method instead |
| NameEntityRecognition(MulticlassClassificationCatalog+MulticlassClassificationTrainers, String, String, String, Int32, Int32, BertArchitecture, IDataView) |
Obsolete.
Obsolete: please use the NamedEntityRecognition(MulticlassClassificationCatalog+MulticlassClassificationTrainers, String, String, String, Int32, Int32, BertArchitecture, IDataView) method instead |
| ObjectDetection(MulticlassClassificationCatalog+MulticlassClassificationTrainers, ObjectDetectionTrainer+Options) |
Fine tune an object detection model. |
| ObjectDetection(MulticlassClassificationCatalog+MulticlassClassificationTrainers, String, String, String, String, String, String, Int32) |
Fine tune an object detection model. |
| QuestionAnswer(MulticlassClassificationCatalog+MulticlassClassificationTrainers, QATrainer+Options) |
Fine tune a ROBERTA model for Question and Answer. The limit for any sentence is 512 tokens. Each word typically will map to a single token, and we automatically add 2 specical tokens (a start token and a separator token) so in general this limit will be 510 words for all sentences. |
| QuestionAnswer(MulticlassClassificationCatalog+MulticlassClassificationTrainers, String, String, String, String, String, String, Int32, Int32, Int32, BertArchitecture, IDataView) |
Fine tune a ROBERTA model for Question and Answer. The limit for any sentence is 512 tokens. Each word typically will map to a single token, and we automatically add 2 specical tokens (a start token and a separator token) so in general this limit will be 510 words for all sentences. |
| SentenceSimilarity(RegressionCatalog+RegressionTrainers, SentenceSimilarityTrainer+SentenceSimilarityOptions) |
Fine tune a NAS-BERT model for NLP sentence Similarity. The limit for any sentence is 512 tokens. Each word typically will map to a single token, and we automatically add 2 specical tokens (a start token and a separator token) so in general this limit will be 510 words for all sentences. |
| SentenceSimilarity(RegressionCatalog+RegressionTrainers, String, String, String, String, Int32, Int32, BertArchitecture, IDataView) |
Fine tune a NAS-BERT model for NLP sentence Similarity. The limit for any sentence is 512 tokens. Each word typically will map to a single token, and we automatically add 2 specical tokens (a start token and a separator token) so in general this limit will be 510 words for all sentences. |
| TextClassification(MulticlassClassificationCatalog+MulticlassClassificationTrainers, String, String, String, String, String, Int32, Int32, BertArchitecture, IDataView) |
Fine tune a NAS-BERT model for NLP classification. The limit for any sentence is 512 tokens. Each word typically will map to a single token, and we automatically add 2 specical tokens (a start token and a separator token) so in general this limit will be 510 words for all sentences. |
| TextClassification(MulticlassClassificationCatalog+MulticlassClassificationTrainers, TextClassificationTrainer+TextClassificationOptions) |
Fine tune a NAS-BERT model for NLP classification. The limit for any sentence is 512 tokens. Each word typically will map to a single token, and we automatically add 2 specical tokens (a start token and a separator token) so in general this limit will be 510 words for all sentences. |