Skip to main content

Table 3 Experimental specifications used to perform semantic segmentation on cloud

From: A state-of-the-art technique to perform cloud-based semantic segmentation using deep learning 3D U-Net architecture

Cloud server

RAM

56 GiB

Storage

340 GiB

GPU

1 × K80

Instance

Azure NC6

vCPU(s)

6

Cost

$1.321/hour

NVIDIA Tesla K80 accelerator

Memory

24 GB GDDR5

Bandwidth

480 GB/s

CUDA cores

4992

Single-precision

8.73 teraflops

Double-precision

2.91 teraflops

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us