Set of Keras models for segmentation of 3D volumes .
Set of models for classification of 3D volumes.
Set of models for classification of 1D data.
Library for 3D augmentations
Python implementation of several methods for ensembling boxes from object detection models: Non-maximum Suppression (NMS), Soft-NMS, Non-maximum weighted (NMW), Weighted boxes fusion (WBF)
EfficientNet models in 3D variant for keras and TF.keras
Music source separation in the waveform domain.
Keras implementation of layer which performs augmentations of images using GPU.
Keras inference time optimizer
Function to calculate mAP for set of detected boxes and annotated boxes.