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