Data prep & training by task (with screenshots)

Every workspace type has its own data → label → package/version → train chrome. This guide walks each task with live UI screenshots from OneOpen ML Studio.

Note

Screenshots were captured from a local oneopen start session (v1.0.0). Your sidebar lists projects (each under a workspace); the workflow rail and train catalogs match the project type.

Studio overview

From the home page you create a workspace, import data, label, version (image tasks), and train.

Studio home — workspaces, Data → Label → Version → Train rail

Pick the task when creating a project — this locks annotation tools, tabs, export formats, and the train catalog.

New project form with project type selector

Computer vision

Image projects share upload + canvas (or class-click) labeling. Detection and segmentation also use Generate (preprocess / augment / split). Classification uses Generate for splits/snapshots, then YOLO-Cls or torchvision classifiers.

Object detection

Prep: upload images → draw boxes (or Label Assist) → Generate version.
Train: YOLO detect, LibreYOLO, Face (MTCNN-style / RetinaFace-style), Faster R-CNN, RetinaNet, SSD-Lite.

Detection project overview workflow Upload images for a detection project Bounding-box annotator with Box / Polygon / SAM / Label Assist Generate tab — preprocess, augmentation, splits Train / Export tab for object detection Detection model catalog (YOLO + Face + Torchvision)

Image classification

Prep: upload images → click a class per image (no boxes).
Train: YOLO-Cls (v8 / 11 / 26) plus ResNet, EfficientNet, MobileNetV3, ConvNeXt, ViT, DenseNet, Swin, MaxViT, SqueezeNet.

Image classification overview — Assign image class Classification annotator — Class tool, no box tools Train panel with YOLO-Cls / torchvision classifiers Classification model list

Instance & semantic segmentation

Prep: upload images → polygons / SAM (and boxes if needed) → Generate.
Train: YOLO-Seg (v8 / 11 / 26), Mask R-CNN, DeepLabV3, FCN, LR-ASPP.

Instance and semantic projects share the same segment train catalog; labeling emphasis is masks/polygons.

Instance segmentation overview Segmentation annotator tools Segmentation Train / Export Segmentation model catalog Semantic segmentation overview

Text & tabular

No Generate tab — import samples, label, then Train / Export (JSONL / CSV + adapters).

Text classification

Prep: import JSONL/CSV → assign class buttons.
Train: TF-IDF + Logistic Regression (fit) or Hugging Face prepare package.

Text classification workflow rail Import text samples Text sample labeling UI Text train / export options Text training recipes

Named entity recognition (NER)

Prep: import text → mark character spans + entity types.
Train: Hugging Face token-classification prepare JSONL.

NER project overview NER span annotation UI NER train / export

Tabular classification

Prep: import CSV rows → class per row.
Train: sklearn Logistic Regression.

Tabular classification overview Tabular row labeling Tabular classification train panel

Tabular regression

Prep: import CSV → numeric target (no Classes tab).
Train: sklearn Ridge / regression adapter.

Tabular regression overview Numeric target annotation Tabular regression train panel

Audio & video

Import URI/path JSONL, label clips or transcripts, then train baselines or prepare packages for external trainers (Whisper, VideoMAE / X3D, etc.).

Audio classification

Audio classification overview Audio clip labeling Audio classifier train panel

Transcription (ASR)

No Classes tab — write transcripts, then Whisper / HF ASR prepare.

Transcription project overview Transcript editor Whisper / ASR package train panel

Video classification

Video classification overview Video clip labeling Video classifier train panel

Action recognition

Action recognition overview Action / clip labeling Action-recognition prepare / train

LLM datasets

No Classes / Generate tabs. Curate instruction, preference, or RAG records, export JSONL, fine-tune externally (TRL / Axolotl / Unsloth) or use Studio prepare packages.

Instruction tuning (SFT)

Instruction tuning overview — Curate / Package / Fine-tune Instruction / input / output curator SFT package train panel LLM SFT recipe list

Preference (DPO / ORPO)

Preference dataset overview Prompt / chosen / rejected curator DPO package train panel

RAG evaluation

RAG eval overview Query / contexts / answer curator RAG eval package train panel

Quick reference

Project type

Label UI

Version / Generate

Train highlights

Object detection

Boxes, polygon, SAM, Label Assist

Yes

YOLO, Face, Faster R-CNN, RetinaNet, SSD

Image classification

Whole-image class

Yes

YOLO-Cls, ResNet, EfficientNet, ViT, Swin…

Instance / semantic seg

Polygons / SAM

Yes

YOLO-Seg, Mask R-CNN, DeepLabV3, FCN

Text classification

Class buttons

No

TF-IDF / HF prepare

NER

Spans

No

HF token-cls prepare

Tabular cls / reg

Class or value

No

sklearn

Audio cls

Clip class

No

Audio baseline

Transcription

Transcript text

No

Whisper prepare

Video / action

Clip / action class

No

Video baseline / action package

Instruction / preference / RAG

Field curator

No

SFT / DPO / RAG JSONL