MNIST benchmarks with Spatial Transformer Networks, Vision Transformers and SpinalNets, with model modifications including CoordConv layers.
-
Updated
Oct 12, 2021 - Jupyter Notebook
MNIST benchmarks with Spatial Transformer Networks, Vision Transformers and SpinalNets, with model modifications including CoordConv layers.
Affliated with Leibniz Institute for Neurobiology, Magdeburg and AI Lab, OVGU Magdeburg, we implemented data analysis for single photon calcium imaging with deep learning.
Research about STN, CoordConv and Selective Kernel Networks combined for MNIST dataset.
Semi-Convolutional Operator for keras
Grand Challenge 2017 Multi-Modality Whole Heart Segmentation
TensorFlow implementation of CoordConv Layer introduced by UBER
Code accompanying the paper "Spherical View Synthesis for Self-Supervised 360 Depth Estimation", 3DV 2019
Keras implementation of CoordConv for all Convolution layers
Pytorch implementation of "An intriguing failing of convolutional neural networks and the CoordConv solution" - https://arxiv.org/abs/1807.03247
Add a description, image, and links to the coordconv topic page so that developers can more easily learn about it.
To associate your repository with the coordconv topic, visit your repo's landing page and select "manage topics."