ZFTurbo

Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.

Repository for training models for music source separation.

Model for MDX23 music separation contest

Verilog Generator of Neural Net Digit Detector for FPGA

Code for 15th place in Kaggle Google AI Open Images - Object Detection Track

Library for 3D augmentations

Modification of convolutional neural net "UNET" for image segmentation in Keras framework

Generator of verilog description for FPGA MobileNet implementation

Set of models for classifcation of 3D volumes

Optimize layers structure of Keras model to reduce computation time

Set of models for segmentation of 3D volumes

Function to calculate mAP for set of detected boxes and annotated boxes.

Solutions

PyTorch Volume Models for 3D data

Segmentation models for 3D data with different backbones. PyTorch.

3rd place solution

Model for CDX23 (Cinematic Sound Demixing) contest

Code and pre-trained models for Instance Segmentation track in Open Images Dataset

EfficientNets in 3D variant for keras and TF.keras

Pretrained VGG16 neural net in C language