On multi-GPU systems, MLCN with model parallelism is about twice as efficient as original CapsNet with data parallelism, and a simple greedy lane-to-GPU heuristic reduces execution time by nearly half versus random assignment.
Inception-v4, inception-resnet and the impact of residual connections on learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficiency and Scalability of Multi-Lane Capsule Networks (MLCN)
On multi-GPU systems, MLCN with model parallelism is about twice as efficient as original CapsNet with data parallelism, and a simple greedy lane-to-GPU heuristic reduces execution time by nearly half versus random assignment.