PZnet: Efficient 3D ConvNet Inference on Manycore CPUs

03/18/2019
by   Sergiy Popovych, et al.
0

Convolutional nets have been shown to achieve state-of-the-art accuracy in many biomedical image analysis tasks. Many tasks within biomedical analysis domain involve analyzing volumetric (3D) data acquired by CT, MRI and Microscopy acquisition methods. To deploy convolutional nets in practical working systems, it is important to solve the efficient inference problem. Namely, one should be able to apply an already-trained convolutional network to many large images using limited computational resources. In this paper we present PZnet, a CPU-only engine that can be used to perform inference for a variety of 3D convolutional net architectures. PZNet outperforms MKL-based CPU implementations of PyTorch and Tensorflow by more than 3.5x for the popular U-net architecture. Moreover, for 3D convolutions with low featuremap numbers, cloud CPU inference with PZnet outperfroms cloud GPU inference in terms of cost efficiency.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/23/2019

Chunkflow: Distributed Hybrid Cloud Processing of Large 3D Images by Convolutional Nets

It is now common to process volumetric biomedical images using 3D Convol...
research
04/22/2020

Microscopy Image Restoration using Deep Learning on W2S

We leverage deep learning techniques to jointly denoise and super-resolv...
research
04/29/2019

Convolutional nets for reconstructing neural circuits from brain images acquired by serial section electron microscopy

Neural circuits can be reconstructed from brain images acquired by seria...
research
10/23/2019

Random 2.5D U-net for Fully 3D Segmentation

Convolutional neural networks are state-of-the-art for various segmentat...
research
11/18/2020

Larq Compute Engine: Design, Benchmark, and Deploy State-of-the-Art Binarized Neural Networks

We introduce Larq Compute Engine, the world's fastest Binarized Neural N...
research
07/08/2021

Comparison of 2D vs. 3D U-Net Organ Segmentation in abdominal 3D CT images

A two-step concept for 3D segmentation on 5 abdominal organs inside volu...
research
11/20/2016

Deep Tensor Convolution on Multicores

Deep convolutional neural networks (ConvNets) of 3-dimensional kernels a...

Please sign up or login with your details

Forgot password? Click here to reset