Segmentation Models - v1.0.1

Minor fixes

• FocalLoss fixed alpha and positional arguments order
• PSPNet changed last layer upsampling to nearest - > bilinear

Segmentation Models - v1.0.0

Areas of improvement

• Support for keras and tf.keras
• Losses as classes, base loss operations (sum of losses, multiplied loss)
• NCHW and NHWC support
• Removed pure tf operations to work with other keras backends
• Reduced a number of custom objects for better models serialization and deserialization

New featrues

• New backbones: EfficentNetB[0-7]
• New loss function: Focal loss
• New metrics: Precision, Recall

API changes

• get_preprocessing moved from sm.backbones.get_preprocessing to sm.get_preprocessing

Segmentation Models - v1.0.0b1

• Support for keras and tf.keras
• Focal loss; precision and recall metrics
• New losses functionality: aggregation and multiplication by factor
• NCHW and NHWC support
• Removed pure tf operations to work with other keras backends
• Reduced a number of custom objects for better models serialization and deserialization

Segmentation Models 0.2.1

Areas of improvements

• Added set_regularization function
• Added beta argument to dice loss
• Added threshold argument for metrics
• Fixed prerprocess_input for mobilenets
• Fixed missing parameter interpolation in ResizeImage layer config
• Some minor improvements in docs, fixed typos