Skip to content
ModAsteraDocumentation
日本語
Product documentation

Use the ModAstera platform

Follow complete, screenshot-led workflows from account setup and data preparation through annotation, model training, deployment, settings, and recovery.

01

Get started

Account access, onboarding, dashboard, and workspace navigation.

  1. Sign up, sign in, and complete onboardingCreate a verified account, complete your profile, and enter the correct organization workspace.
  2. Recover account accessReset a password, recover from an expired confirmation link, and understand locked or expired sessions.
  3. Use the dashboard and workspace navigationConfirm the active workspace, understand the dashboard, and find every user-facing product area.
02

Datasets and samples

Create, import, review, split, share, and reuse data.

  1. Create a dataset and add samplesChoose the right creation path, upload or register supported data, and follow asynchronous processing to completion.
  2. Use the dataset library and dataset actionsFind the right dataset, interpret access and readiness, review analysis, and choose actions that are available to your role.
  3. Import, verify, and export annotationsMap CSV, platform JSON, COCO, or mask annotations, inspect the preview, resolve errors, and manage annotation files safely.
  4. Find, inspect, and edit dataset samplesUse split tabs, search, filters, card, list, and table views, then inspect processing and edit only the intended sample scope.
  5. Manage splits, collaboration, and advanced dataset actionsCreate reproducible splits, protect test membership, clone safely, manage access, and use inference or DICOM extraction when eligible.
  6. Work across datasets in All SamplesFind samples across the workspace, select a compatible scope, create or extend a dataset, and delete only confirmed samples.
03

Annotation

Manual, assisted, video, and medical-image annotation.

  1. Annotate image samplesSet up labels, draw and review image annotations, and save work without losing sample context.
  2. Annotation tools, assisted annotation, and shortcutsUse drawing, editing, assisted-annotation, recovery, and keyboard controls safely and efficiently.
  3. Video, medical, and volumetric annotationAnnotate video frames and medical-image slices while preserving the correct frame, slice, view, and orientation context.
04

Pipelines and results

Configure, train, recover, version, and evaluate models.

  1. Create and configure a model pipelineStart a new training workflow or restore a pipeline snapshot, then confirm the dataset, instructions, backend, and explainability settings.
  2. Review pipeline resources and training configurationInspect the generated plan and adjust compatible resources before committing compute to a training run.
  3. Use the segmentation model catalogChoose the right segmentation outcome, understand the new model families, and verify an automatically planned architecture before starting compute.
  4. Run, monitor, and compare pipelinesStart one pipeline run, follow preparation and queue state, respond to GPU guidance, and compare compatible completed work.
  5. Recover runs and manage pipeline versionsChoose the correct continuation action, preserve version history, share access, and export restorable pipeline snapshots.
  6. Review pipeline results and model reportsInterpret task-specific evaluation visuals, distinguish operating points, compare versions, and create a model report grounded in the selected result.
05

Deployments

Test predictions, manage versions, and monitor usage.

  1. Deploy and test a modelCreate or open a deployment for an eligible completed model, activate it deliberately, and run a representative test.
  2. Test prediction inputs and explainabilityProvide the correct input for image, medical, tabular, or language models and inspect summaries, artifacts, explanations, and execution history.
  3. Manage and monitor deploymentsOperate deployment state and versions, review traffic and latency, and download a usage report for the selected period.
06

Settings and support

Profile, team, storage, integrations, health, and recovery.

  1. Manage your account, team, and permissionsUpdate your profile and preferences, then manage organization membership when your role permits it.
  2. Manage resource lifecycle and storageChange dataset access, archive or restore resources, review storage, and delete data safely.
  3. Configure allowed apps and API keysRegister browser origins, create server-side credentials, and manage the complete API-key lifecycle safely.
  4. Check service health and recover from blocked statesDistinguish platform outages, locked membership, device limitations, missing pages, and retryable errors.
  5. Annotation file reference and troubleshootingPrepare supported annotation files and systematically recover from upload, annotation, training, and result problems.