Warwick Electron Microscopy Datasets

Abstract

Large, carefully partitioned datasets are essential to train neural networks and standardize performance benchmarks. As a result, we have set up new repositories to make our electron microscopy datasets available to the wider community. There are three main datasets containing 19769 scanning transmission electron micrographs, 17266 transmission electron micrographs, and 98340 simulated exit wavefunctions, and multiple variants of each dataset for different applications. To visualize image datasets, we trained variational autoencoders to encode data as 64-dimensional multivariate normal distributions, which we cluster in two dimensions by t-distributed stochastic neighbor embedding. In addition, we have improved dataset visualization with variational autoencoders by introducing encoding normalization and regularization, adding an image gradient loss, and extending t-distributed stochastic neighbor embedding to account for encoded standard deviations. Our datasets, source code, pretrained models, and interactive visualizations are openly available at https://github.com/Jeffrey-Ede/datasets.

arXiv comment16 pages, 4 figures, 2 tables

References in corpus (8)

• scikit-image: Image processing in Python
• A Review of Convolutional Neural Networks for Inverse Problems in Imaging
• Why does deep and cheap learning work so well?
• Machine Learning and Big Scientific Data
• Partial Scanning Transmission Electron Microscopy with Deep Learning
• Improving Electron Micrograph Signal-to-Noise with an Atrous Convolutional Encoder-Decoder
• Adaptive Learning Rate Clipping Stabilizes Learning
• Effects of layer thickness on the mechanical behavior of oxidation-strengthened Zr/Nb nanoscale multilayers

Cited by in corpus (3)

• Review: Deep Learning in Electron Microscopy
• Partial Scanning Transmission Electron Microscopy with Deep Learning
• Automated Real-Space Lattice Extraction for Atomic Force Microscopy Images