DIAGNijmegen / StreamingCNN
To train deep convolutional neural networks, the input data and the activations need to be kept in memory. Given the limited memory available in current GPUs, this limits the maximum dimensions of the input data. Here we demonstrate a method to train convolutional neural networks while holding only parts of the image in memory.
☆100Updated last year
Alternatives and similar repositories for StreamingCNN:
Users that are interested in StreamingCNN are comparing it to the libraries listed below
- Use streaming to train whole-slides images with single image-level labels, by reducing GPU memory requirements with 99%.☆78Updated 2 years ago
- Code accompanying the paper Neural Image Compression for Gigapixel Histopathology Image Analysis☆50Updated last year
- A Python module that produces image patches and annotation masks from whole slide images for deep learning in digital pathology.☆78Updated 2 years ago
- Dense Steerable Filter CNN☆75Updated 2 years ago
- Datasets, Transforms and Utilities specific to Biomedical Imaging☆109Updated 6 years ago
- Implementation of PyTorch-based multi-task pre-trained models☆33Updated 4 years ago
- Stain normalization parameters used in the paper "F. Ciompi et al., The importance of stain normalization in colorectal tissue classifica…☆28Updated 5 years ago
- This Python package enables the training and inference of deep learning models for very large data, such as megapixel images, using atten…☆98Updated 5 years ago
- MIDL 2018 / MEDIA 2019: one binary extremely large and inflecting sparse kernel (pytorch)☆44Updated 5 years ago
- Feature Aware Normalization - Code for "Context-based Normalization of Histological Stains using Deep Convolutional Features"☆15Updated 6 years ago
- Official code for "Self-Supervised driven Consistency Training for Annotation Efficient Histopathology Image Analysis" Published in Medic…☆62Updated 3 years ago
- Tensorflow Code for "PHiSeg: Capturing Uncertainty in Medical Image Segmentation", Proc. MICCAI 2019☆125Updated 2 years ago
- Weakly Supervised Mitosis Detection in Breast Histopathology Images using Concentric Loss☆25Updated 5 years ago
- A PyTorch implementation of the Probabilistic U-Net, applied to probabilistic glioma growth☆43Updated 5 years ago
- Syntax - the arrangement of whole-slide-images and their image tiles to create well-formed computational pathology pipelines.☆55Updated 2 years ago
- This is a PyTorch implementation of the paper: "Processing Megapixel Images with Deep Attention-Sampling Models".☆41Updated last year
- Roto-reflection equivariant CNNs for Keras as presented in B. S. Veeling, J. Linmans, J. Winkens, T. Cohen, M. Welling. "Rotation Equivar…☆85Updated 5 years ago
- Segmenting WSIs using Deep Convolutional Neural Networks☆19Updated 6 years ago
- This is the source code for training and testing our three class CNN algorithm for generalized nuclei segmentation (IEEE TMI paper) using…☆53Updated 5 years ago
- Lightweight framework for fast prototyping and training deep neural networks with PyTorch and TensorFlow☆220Updated 4 years ago
- Self-supervised learning for microscopy images☆55Updated 5 years ago
- This repository contains my implementations of the algorithms which we used for evaluation of the MoNuSeg challenge at MICCAI 2018.☆44Updated 3 years ago
- Repository for the article "Unsupervised domain adaptation for medical imaging segmentation with self-ensembling".☆43Updated 6 years ago
- SlideRunner is a tool for massive cell annotations in whole slide images☆77Updated last year
- ☆77Updated 3 months ago
- HistoSegNet: Semantic Segmentation of Histological Tissue Type in Whole Slide Images (ICCV 2019)☆87Updated 5 years ago
- Neural Ordinary Differential Equations for Semantic Segmentation of Individual Colon Glands☆109Updated 4 years ago
- ☆66Updated 6 years ago
- Survival Convolutional Neural Networks☆69Updated last year
- Attention-based Deep MIL implementation and application☆157Updated 3 years ago