Skip to main content

Table 1 Training and inference time of different network architectures on a Nvidia GTX 1080 TI

From: ReCSAI: recursive compressed sensing artificial intelligence for confocal lifetime localization microscopy

Network architecture

Training time [s]

Inference time [s]

CS-CNN

1102.0

440.8

CS-Inception

2091.3

502.5

CS-U

596.4

72.5

CS-Res-U

64.1

88.8

  1. Training times are measured per epoch. For the evaluation of inference time, a FLIMbee dataset with 4500 frames of 45 \(\times\) 45 px is used
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us