Version 0.13.1

What's Changed

• bug fix by @phborba in #67

Full Changelog: v0.13.0...v0.13.1

Version 0.13.0

• Dataset conversion added. It is possible to convert between some formats of dataset;
• Tversky Loss and Focal Tversky Loss added;
• LabelSmoothingLoss added;
• MixUpAugmentationLoss added;
• KnowledgeDistillationLoss added;
• Mixup augmentation added to Frame Field Model;

Version 0.12.1

• Bug fixes on mask building;
• Bug fixes on detection model training.
• New mode on build masks;

Version 0.12.0

• Minor improvements on polygonization methods;
• Inference server added;

Version 0.11.0

• Gradient Centralization added;

Version 0.10.0

• Object Detection added;
• Instance Segmentation added;

Version 0.9.0

• PolygonRNN model added;
• Added the option of choosing the number of images on ImageCallback;
• Added the option of adding created masks to existing csv;
• Added the option of generating bounding boxes in create masks;
• Added the option of converting csv dataset to coco dataset;

Version 0.8.1

• Minor improvements and bug fixes on polygon building inference;
• Bug fixes on mask builder;
• Performance improvement on mask builder using coco format;

Version 0.8.0

• Added inference features;
• Improved polygon inference;

Version 0.7.2

• Changed the versions of pytorch and torchvision.