The following ORT classes are available for instantiating a base model class without a specific head.
[[autodoc]] onnxruntime.ORTModel
The following ORT classes are available for the following natural language processing tasks.
[[autodoc]] onnxruntime.ORTModelForCausalLM - forward
[[autodoc]] onnxruntime.ORTModelForMaskedLM
[[autodoc]] onnxruntime.ORTModelForSeq2SeqLM - forward
[[autodoc]] onnxruntime.ORTModelForSequenceClassification
[[autodoc]] onnxruntime.ORTModelForTokenClassification
[[autodoc]] onnxruntime.ORTModelForMultipleChoice
[[autodoc]] onnxruntime.ORTModelForQuestionAnswering
The following ORT classes are available for the following computer vision tasks.
[[autodoc]] onnxruntime.ORTModelForImageClassification
[[autodoc]] onnxruntime.ORTModelForSemanticSegmentation
The following ORT classes are available for the following audio tasks.
[[autodoc]] onnxruntime.ORTModelForAudioClassification
[[autodoc]] onnxruntime.ORTModelForAudioFrameClassification
[[autodoc]] onnxruntime.ORTModelForCTC
[[autodoc]] onnxruntime.ORTModelForSpeechSeq2Seq - forward
[[autodoc]] onnxruntime.ORTModelForAudioXVector
The following ORT classes are available for the following multimodal tasks.
[[autodoc]] onnxruntime.ORTModelForVision2Seq - forward
[[autodoc]] onnxruntime.ORTModelForPix2Struct - forward
The following ORT classes are available for the following custom tasks.
[[autodoc]] onnxruntime.ORTModelForCustomTasks
[[autodoc]] onnxruntime.ORTModelForFeatureExtraction
[[autodoc]] onnxruntime.ORTStableDiffusionPipeline - call
[[autodoc]] onnxruntime.ORTStableDiffusionImg2ImgPipeline - call
[[autodoc]] onnxruntime.ORTStableDiffusionInpaintPipeline - call
[[autodoc]] onnxruntime.ORTStableDiffusionXLPipeline - call
[[autodoc]] onnxruntime.ORTStableDiffusionXLImg2ImgPipeline - call
[[autodoc]] onnxruntime.ORTLatentConsistencyModelPipeline - call