You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
HistoSeg is an Encoder-Decoder DCNN which utilizes the novel Quick Attention Modules and Multi Loss function to generate segmentation masks from histopathological images with greater accuracy. This repo contains the code to Test and Train the HistoSeg
This includes a complete pipeline for nuclei segmentation in microscopy images using a U-Net decoder with an EfficientNet-B3 encoder (pretrained on ImageNet). We include dataset description, RLE ground-truth handling, preprocessing and augmentation, model architecture, loss functions and equations, training and inference , baseline descriptions.