Research Article
A Novel Memory-Scheduling Strategy for Large Convolutional Neural Network on Memory-Limited Devices
Figure 8
mmCNN strategy for VGG-S model under different constraints of GPU memory size. (a) VGG-S 200M. (b) VGG-S 100M. (c) VGG-S 50M. (d) VGG-S 10M. (e) VGG-S 5M.
(a) |
(b) |
(c) |
(d) |
(e) |