White Papers

Deep Learning Performance: Scale-up vs Scale-out
Architectures & Technologies Dell EMC | Infrastructure Solutions Group
14
▪ Top-5 Accuracy on the training dataset
▪ Training time
Training Tests
▪ Short Tests to get throughput images/second
▪ Long Tests to get accuracy convergence and training time
Dataset
ILSVRC2012
Table 1: Benchmark Setup
4.3 Neural Models & parameters
Short Tests
Long Tests
Models
▪ VGG-16
▪ VGG-19
▪ Inception-v3
▪ Inception-v4
▪ ResNet50
▪ GoogLeNet
▪ AlexNet
▪ VGG-19
▪ Inception-v4
▪ ResNet50
Batch sizes
▪ 32
▪ 64
▪ 128
▪ 256
▪ 512
▪ 2014
▪ 2048
▪ 32
▪ 64
▪ 128
▪ 256
GPUs
▪ 1
▪ 2
▪ 3
▪ 4
▪ 5
▪ 6
▪ 7
▪ 8
▪ 3
▪ 4
▪ 8
Training Steps or Epochs
100 steps
90 epochs
Table 2: Neural Models & Parameters