Release v0.4.0

Added

• Model Preparation Algorithm (MPA)
  • Better saliency map support
    • Replace current saliency map generation with Recipro-CAM for cls task (#1363)
    • Class-wise saliency map generation for the detection task (#1402)
    • Align saliency map labels for all tasks (#1447)
  • Improve object counting algorithm for high-res images via image tiling
    • Add tiling module for detection, rotated detection and instance segmentation (#1200)
    • Fliter object less than 1 pixel (#1305)
    • Add tiling deployment (#1387)
  • Enabling GPU execution for exported code (#1416)
  • Add active score evaluation and probability output to the classification task (#1417)

Changed

• Normalize top-1 metrics to [0, 1] (#1394)

Fixed

• Hot-fix for Detection fix two stage error (#1433)
• Fixing ZeroDivisionError in iteration counter for detection-classification project trainings (#1449)
• Some minor issues

Release v0.3.1

Fixed

• Neural Network Compression Framework (NNCF)

  • Fix CUDA OOM for NNCF optimization model MaskRCNN-EfficientNetB2B (#1319)

• Model Preparation Algorithm (MPA)

  • Fix 'Shape out of bounds' error when accepting AI predictions for detection oriented (#1326)
  • Fix weird confidence behaviour issue on predictions for hierarchical classification (#1332)
  • Fix training failure issue for hierarchical classification (#1329)
  • Fix training failure issues for segmentation and instance segmentation during inference process (#1338)
  • Some minor issues

Security

• Update vulnerable Python dependencies in OTE (#1303)

Release v0.3.0

Added

• Model Preparation Algorithm (MPA)
  • Add new tasks / model templates for Class-Incremental Learning
    • Instance Segmentation (#1142)
    • Classification
      • Multilabel (#1132)
      • Hierarchical-label (#1159)
    • SSD and YOLOX model template for Detection (#1156)
  • Saliency map support
    • Classification (#1166)
    • Detection (#1155)
    • Segmentation (#1158)
  • NNCF (#1157) support
  • HPO (#1168) support
  • Balanced Sampler support for Classification (#1139)
  • Add Adaptive Training for Detection / Instance Segmentation (#1190)
• Anomaly
  • Add real-life training tests (#898)
  • Add additional check for early stopping parameter (#1110)
  • Add DRAEM task implementation (#1203)

Changed

• Model Preparation Algorithm (MPA)

  • Replace Class-Incremental Learning models as OTE default models (#1150)
  • Replace OTE ignored label support with external ignored label
    • Classification (#1132)
    • Detection (#1128)
    • Segmentation (#1134)
  • Enable mixed precision for Classification / Detection / Segmentation (#1198)
  • Enhance training schedule for Classification (#1212)
  • Change Model optimization hyper-parameters for Classification / Detection (#1170)
  • Disable Obsolete test cases for OTE CI (#1220)

• Anomaly

  • Extend conftest configuration for anomaly backend (#1097)
  • Expose more params to the UI (#1085)
  • Change directory structure for anomaly templates (#1105)
  • Use is_anomalous attribute instead of string matching (#1120)
  • Set nncf version (#1124)
  • Move to learning parameters (#1152)
  • Change OpenVINO MO Command (#1221)

Fixed

• Model Preparation Algorithm (MPA)

  • Fix inference issues for Detection (#1167)
  • Fix model compatibility issue between SC1.1 and 1.2 in Segmentation (#1264)
  • Some minor issues

• Anomaly

  • Fix non deterministic + sample.py (#1118)
  • Fix exportable code for anomaly tasks (#1113)
  • Fix local anomaly segmentation performance bug (#1219)
  • Fix progress bar (#1223)
  • Fix inference when model backbone changes (#1242)

Release v0.2.0

Added

• Model Preparation Algorithm (MPA), a newly introduced OTE Algorithm backend for advanced transfer learning
  • Class-Incremental Learning support for OTE models
    • Image Classification
    • Object Detection
    • Semantic Segmentation
• Object counting & Rotated object detection are added to Object Detection backend
• Increased support for NNCF / FP16 / HPO
• Ignored label support
• Stop training on NaN losses

Release v0.1.1

Fixed

• Some minor issues

Release v0.1.0

Added

• OTE SDK, defines an interface which can be used by OTE CLI to access OTE Algorithms.
• OTE CLI, contains set of commands needed to operate with deep learning models using OTE SDK Task interfaces.
• OTE Algorithms, contains sub-projects implementing OTE SDK Task interfaces for different deep learning models.
  • Anomaly Classification
  • Image Classification
  • Object Detection
  • Semantic Segmentation