Release 1.4.0

Release 1.4.0

New scripts:

• lm-1b FP32 inference
• MobileNet V1 Int8 inference
• DenseNet 169 FP32 inference
• SSD-VGG16 FP32 and Int8 inference
• SSD-ResNet34 Int8 inference
• ResNet50 v1.5 FP32 and Int8 inference
• Inception V3 FP32 inference using TensorFlow Serving

Other script changes and bug fixes:

• Updated SSD-MobileNet accuracy script to take a full path to the coco_val.records, rather than a directory
• Added a deprecation warning for using checkpoint files
• Changed Inception ResNet V2 FP32 to use a frozen graph rather than checkpoints
• Added support for custom volume mounts when running with docker
• Moved model default env var configs to config.json files
• Added support for dummy data with MobileNet V1 FP32
• Added support for TCMalloc (enabled by default for int8 models)
• Updated model zoo unit test to use json files for model parameters
• Made the reference file optional for Transformer LT performance testing
• Added iteration time to accuracy scripts
• Updated Transformer LT Official to support num_inter and num_intra threads
• Fixed path to the calibration script for ResNet101 Int8

New tutorials:

• Transformer LT inference using TensorFlow
• Transformer LT inference using TensorFlow Serving
• ResNet50 Int8 inference using TensorFlow Serving
• SSD-MobileNet inference using TensorFlow Serving

Documentation updates:

• Added Contribute.md doc with instructions on adding new models
• Added note about setting environment variables when running on bare metal
• Updated model README files to use TensorFlow 1.14.0 docker images (except for Wide and Deep int8)
• Updated FasterRCNN Int8 README file to clarify that performance testing uses raw images
• Fixed docker build command in the TensorFlow Serving Installation Guide
• NCF documentation update to remove line of code that causes an error
• Updated mlperf/inference branch and paths in README file

Known issues:

• RFCN FP32 accuracy is not working with the gcr.io/deeplearning-platform-release/tf-cpu.1-14 docker image
• The TensorFlow Serving Installation Guide still shows example commands that build version 1.13. This will be updated to 1.14 when the official TensorFlow Serving release tag exists. To build version 1.14 now, you can use one of the following values for TF_SERVING_VERSION_GIT_BRANCH in your multi-stage docker build: "1.14.0-rc0" or "r1.14".

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)