ModelTask
Enums · AiDotNet.Enums
Defines the specific task or capability that a machine learning model performs.
For Beginners
This tells you what a model actually does — its job. A model can perform multiple tasks. For example, a Vision Transformer might do both Classification and FeatureExtraction. Knowing the task helps you pick the right model for your specific problem.
Fields
| Field | Summary |
|---|---|
ModelTask ActionRecognition |
Recognizes and classifies human actions in video. |
ModelTask AnomalyDetection |
Identifies unusual patterns or outliers that don’t conform to expected behavior. |
ModelTask AudioGeneration |
Generates audio content (music, sound effects, speech). |
ModelTask BinaryClassification |
Assigns inputs to one of exactly two categories. |
ModelTask CausalInference |
Estimates cause-and-effect relationships from observational data. |
ModelTask Classification |
Assigns inputs to one of several predefined categories. |
ModelTask Clustering |
Groups similar data points together without predefined labels. |
ModelTask CodeGeneration |
Generates source code from natural language or other code. |
ModelTask Compression |
Reduces the size or dimensionality of data while preserving essential information. |
ModelTask Denoising |
Removes noise or unwanted artifacts from data. |
ModelTask DepthEstimation |
Estimates the distance of objects from the camera or sensor. |
ModelTask Detection |
Locates and identifies objects within an input (typically an image). |
ModelTask DimensionalityReduction |
Reduces the number of features or dimensions in data while preserving structure. |
ModelTask DrugDiscovery |
Discovers or designs new drug molecules. |
ModelTask Editing |
Modifies or manipulates existing data based on instructions, conditions, or references. |
ModelTask Embedding |
Produces dense vector representations that capture semantic meaning. |
ModelTask Enhancement |
Improves the overall quality of audio, images, or other signals. |
ModelTask FeatureExtraction |
Extracts meaningful features or representations from raw data. |
ModelTask Forecasting |
Predicts future values based on historical time-dependent data. |
ModelTask FrameInterpolation |
Generates intermediate frames between existing video frames. |
ModelTask Generation |
Creates new data (images, text, audio, etc.) that resembles the training data. |
ModelTask GraphClassification |
Classifies entire graphs into categories. |
ModelTask ImageEditing |
Modifies or manipulates images based on instructions or conditions. |
ModelTask ImageToVideo |
Generates video by animating a single input image. |
ModelTask Inpainting |
Fills in missing or masked regions of data. |
ModelTask LinkPrediction |
Predicts missing edges between nodes in a graph. |
ModelTask MolecularGeneration |
Predicts properties of molecular structures. |
ModelTask MotionGeneration |
Generates realistic human or object motion sequences. |
ModelTask MultiClassClassification |
Assigns inputs to one of three or more categories. |
ModelTask MusicGeneration |
Generates music compositions. |
ModelTask NamedEntityRecognition |
Identifies named entities (people, places, organizations) in text. |
ModelTask NodeClassification |
Predicts labels or properties of nodes in a graph. |
ModelTask ObjectDetection |
Detects and classifies objects in images. |
ModelTask OpticalFlow |
Estimates the motion of pixels between consecutive frames. |
ModelTask PoseEstimation |
Estimates body joint positions from images or video. |
ModelTask ProteinFolding |
Predicts protein 3D structures from amino acid sequences. |
ModelTask QuestionAnswering |
Answers questions based on given context or knowledge. |
ModelTask Ranking |
Orders items by relevance or importance for a given query. |
ModelTask Recommendation |
Suggests relevant items to users based on preferences and behavior. |
ModelTask RecommendationFiltering |
Filters and recommends items based on user preferences. |
ModelTask Regression |
Predicts a continuous numeric value from input features. |
ModelTask Restoration |
Repairs, enhances, or recovers degraded data. |
ModelTask Segmentation |
Assigns a label to every pixel or element in the input. |
ModelTask SemanticSearch |
Finds relevant documents or passages for a query. |
ModelTask SentimentAnalysis |
Determines the emotional tone of text. |
ModelTask SignalProcessing |
Processes, analyzes, or transforms raw signals (audio, radio, sensor data). |
ModelTask SourceSeparation |
Separates individual sources from a mixed signal. |
ModelTask SpeechRecognition |
Converts spoken audio into text transcription. |
ModelTask StyleTransfer |
Transfers the visual style of one image to the content of another. |
ModelTask Summarization |
Condenses long text into shorter summaries. |
ModelTask SuperResolution |
Increases the resolution or quality of data. |
ModelTask SurvivalAnalysis |
Predicts time-to-event outcomes accounting for censored data. |
ModelTask Synthesis |
Creates synthetic data that preserves statistical properties of real data. |
ModelTask TabularPrediction |
Predicts outcomes from tabular/structured data. |
ModelTask TextGeneration |
Generates text from prompts or context. |
ModelTask TextToImage |
Generates images from text descriptions. |
ModelTask TextToSpeech |
Converts text into spoken audio output. |
ModelTask TextToVideo |
Generates video content from text descriptions. |
ModelTask ThreeDGeneration |
Creates 3D models, meshes, or point clouds. |
ModelTask Tracking |
Follows specific objects across multiple frames in a video. |
ModelTask Translation |
Converts input from one form to another (e.g., between languages). |
ModelTask VideoGeneration |
Generates video content from various inputs (text, image, or video). |
ModelTask VideoToVideo |
Transforms an existing video into a modified version. |
int value__ |