Training Multiscale-CNN for Large Microscopy Image Classification in One Hour

Abstract

Existing approaches to train neural networks that use large images require to either crop or down-sample data during pre-processing, use small batch sizes, or split the model across devices mainly due to the prohibitively limited memory capacity available on GPUs and emerging accelerators. These techniques often lead to longer time to convergence or time to train (TTT), and in some cases, lower model accuracy. CPUs, on the other hand, can leverage significant amounts of memory. While much work has been done on parallelizing neural network training on multiple CPUs, little attention has been given to tune neural network training with large images on CPUs. In this work, we train a multiscale convolutional neural network (M-CNN) to classify large biomedical images for high content screening in one hour. The ability to leverage large memory capacity on CPUs enables us to scale to larger batch sizes without having to crop or down-sample the input images. In conjunction with large batch sizes, we find a generalized methodology of linearly scaling of learning rate and train M-CNN to state-of-the-art (SOTA) accuracy of 99% within one hour. We achieve fast time to convergence using 128 two socket Intel Xeon 6148 processor nodes with 192GB DDR4 memory connected with 100Gbps Intel Omnipath architecture.

Image‐based deep learning reveals the responses of human motor neurons to stress and VCP‐related ALS

“…In order to improve accuracy and reduce overfitting, we performed five augmentations on each image of the training set as follows and as previously described 57 : (1) 90° rotation, (2) one horizontal mirror, (3) one vertical mirror, (4) 90° rotation of horizontal mirror and (5) 90° rotation of vertical mirror. This results in a sixfold increase of the number of available images for training (five rotations + original).…”

Image-based deep learning reveals the responses of human motor neurons to stress and ALS

“…In order to improve accuracy and reduce overfitting, we performed five augmentations on each image of the training set as follows and as previously described 49 : 1) 90 degrees rotation, 2) one horizontal mirror, 3) one vertical mirror, 4) 90 degrees rotation of horizontal mirror and 5) 90 degrees rotation of vertical mirror. This results in a 6-fold increase of the number of available images for training (five rotations + original).…”