v1.3.1

Revised language regarding performance expectations.

v1.3.0

Release 1.3.0

New benchmarking scripts:

• FaceNet FP32 inference
• GNMT FP32 inference
• Inception ResNet V2 Int8 inference
• Inception V4 Int8 inference
• MTCC FP32 inference
• RFCN Int8 inference
• SSD-MobileNet Int8 inference
• SSD-ResNet34 FP32 inference
• Transformer LT Official FP32 inference

Other script changes and bug fixes:

• Renamed Fast RCNN to Faster RCNN
• Fixed SSD-MobileNet FP32 inference container error with python3
• Added python file to download and preprocess the Wide and Deep census dataset
• Added ability for ResNet50 FP32 --output-results to work with benchmarking
• Added --data-num-inter-threads and --data-num-intra-threads to the launch script (currently supported by ResNet50, ResNet101, and InceptionV3)
• Added data layer optimization and calibration option for ResNet50, ResNet101 and InceptionV3
• Bug fixes and an arg update for Wide and Deep large dataset
• Only print lscpu info with verbose logging
• Reduced duplicated code in Wide and Deep inference scripts
• Added ability to run benchmarking script without docker
• ResNet50 fix for the issue of not reporting the average of all segments

New tutorials:

• ResNet101 and Inception V3 tutorial contents
• TensorFlow Serving Object Detection Tutorial
• TensorFlow Recommendation System Tutorial
• ResNet50 Quantization Tutorial

Documentation updates:

• Improved main README with repo purpose and structure
• Updated NCF README file
• Added links to the arXiv papers for each model
• Updated TF Serving BKMs for split parallelism vars
• Added note to TF BKM about KMP_AFFINITY when HT is off

v1.2.1

Release 1.2.1

Benchmarking Scripts

• Fix dummy data performance problem for RN50 FP32 and InceptionV3 FP32

v1.2.0

Release 1.2.0

Benchmarking Scripts

• Updated frozen graphs for ResNet50 Int8, ResNet101 Int8, and InceptionV3 Int8
• New docker image for int8 models noted in the README docs
• Added ability to customize number of warmup steps and steps from the launch script for ResNet50 Int8, ResNet101 Int8, and InceptionV3 Int8
• Removed 3D UNet
• Add --output-results for ResNet50 FP32 to get inference results file

New benchmarking scripts:

• First rev of Wide & Deep large dataset FP32 and Int8 benchmarking scripts

Bug Fixes

• Fixed to allow --num-inter-threads and --num-intra-threads to be passed in from the launch script
• Fixed FastRCNN FP32 benchmark script
• Fixed MobileNet V1 import error

v1.1.0

Release 1.1.0

Benchmarking Scripts

• Added links to download pre-trained models for: ResNet50, ResNet101, Fast RCNN, Inception V3, Wide & Deep, Mask RCNN, and NCF
• Added --output-dir flag to launch_benchmarks.py to allow specifying a custom output directory
• Added ability to allow user-specified environment variables
• Added accuracy metrics for SSD-MobileNet FP32

New benchmarking scripts:

• Image Segmentation
  • UNet FP32 inference
• Language Translation
  • Transformer Language FP32 inference

New Documentation

• Image Recognition with ResNet50 Tutorial
• Launch Benchmark script documentation

Bug Fixes

• Fixed launch_benchmarks.py to allow killing the container using ctrl-c

Other Updates

• Updated TensorFlow Serving Installation Guide
• Linked Intel-Optimized TensorFlow Installation Guide

v1.0.0

Release 1.0.0

The initial release of the Model Zoo for Intel Architecture.

Benchmarking scripts

Benchmarking scripts for running inference on the follow Intel-optimized TensorFlow models are included in this release:

• Adversarial Networks
  • DCGAN (FP32)
• Classification
  • Wide and Deep (FP32)
• Content Creation
  • DRAW (FP32)
• Image Recognition
  • Inception ResNet V2 (FP32)
  • Inception V3 (Int8 and FP32)
  • MobileNet V1 (FP32)
  • ResNet101 (Int8 and FP32)
  • ResNet50 (Int8 and FP32)
  • SqueezeNet (FP32)
• Image Segmentation
  • 3D UNet (FP32)
  • Mask R-CNN (FP32)
• Object Detection
  • Fast R-CNN (FP32)
  • R-FCN (FP32)
  • SSD-MobileNet (FP32)
• Recommendation
  • NCF (FP32)
• Text-to-Speech
  • WaveNet (FP32)

All of the above FP32 scripts were tested using Intel-optimized TensorFlow v1.12.

Documents

The following documents are included in this release:

Best Practices

• Intel-Optimized TensorFlow Serving:
  • Installation Guide
  • General Best Practices

Tutorials by Use Case

• Intel-Optimized TensorFlow Serving:
  • Image Recognition (ResNet50 and InceptionV3)