Validated workloads

We validated performance 1 for the following workloads:

CPU Tensorflow

TensorFlow Workload

Genre of Deep learning

Resnet50 v1

Image recognition

Resnet50 v2

Image recognition

Inception V3

Image recognition

Inception V4

Image recognition

Inception-ResNetv2

Image recognition

MobileNet v1

Image recognition

Faster RCNN

Object detection

VGG16

Image recognition

SSD-VGG16

Object detection

SSD-MobileNetv1

Object detection

R-FCN

Object detection

Yolo v2

Object detection

Transformer-LT

Language translation

Wide & Deep

Recommender system

NCF

Recommender system

U-Net

Image segmentation

DCGAN

Generative adversarial network

DRAW

Image generation

A3C

Reinforcement learning

CPU ONNX

Additionally, we validated the following workloads are functional through nGraph ONNX importer. ONNX models can be downloaded from the ONNX Model Zoo.

ONNX Workload

Genre of Deep Learning

DenseNet-121

Image recognition

Inception-v1

Image recognition

Inception-v2

Image recognition

ResNet-50

Image recognition

Mobilenet

Image recognition

Shufflenet

Image recognition

SqueezeNet

Image recognition

VGG-16

Image recognition

ZFNet-512

Image recognition

MNIST

Image recognition

Emotion-FERPlus

Image recognition

BVLC AlexNet

Image recognition

BVLC GoogleNet

Image recognition

BVLC CaffeNet

Image recognition

BVLC R-CNN ILSVRC13

Object detection

ArcFace

Face Detection and Recognition

GPU TensorFlow

TensorFlow Workload

Genre of Deep Learning

Resnet50 v2

Image recognition

Inception V3

Image recognition

Inception V4

Image recognition

Inception-ResNetv2

Image recognition

VGG-16

Image recognition

GPU ONNX

ONNX Workload

Genre of Deep Learning

Inception V1

Image recognition

Inception V2

Image recognition

ResNet-50

Image recognition

SqueezeNet

Image recognition

Important

Please see Intel’s Optimization Notice for details on disclaimers.

Footnotes

1

Benchmarking performance of DL systems is a young discipline; it is a good idea to be vigilant for results based on atypical distortions in the configuration parameters. Every topology is different, and performance changes can be attributed to multiple causes. Also watch out for the word “theoretical” in comparisons; actual performance should not be compared to theoretical performance.