Release 1.4.0 #26
Merged
Release 1.4.0 #26
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* add lm-1b * fix per reviewer comments * fix typo * minor fix * remove unused documents and others * minor fix * Fix formatting issue in the tf_model_args.txt * correct the lm-1b unit test * remove step in benchmarks/launch_benchmark.py
Also, updated the launch script documentation with instructions on using the `--debug` flag.
…file path including the file name as an input (#271) * Change usage for data location to use the full file path * Update the unit test commands
…t101 (#273) * Fix links that were moved to be shared between int8 and fp32
* add mobinetv1 benchmark * added README.md * added unit tests and update readme * minor fix * code review updated * updated readme * minor fix * fixed unit tests * unit tests fix * updated readme * Arg update * fix command examples * Fix minor typos * Add unit test commands, fix minor typos * Fix hanging indent * Fix hanging indent * code review items fixed * Add custom args * Update unit test command and README.md * change custom arg to use underscore not dash * add unit test commands * update the default values on custom args * update the default values on custom args * remove Inappropriate Intel licensing header
…ing (#276) * Change inception resnet v2 FP32 to use the frozen graph for benchmarking * fix test * Fix file path
* Fix arg parse * fix small typo
* Add support for custom volumes * Launch script documentation update
…r args (#282) * Fix help so that it doesn't require args * Add test for --help * Fixing file name in comment
* Clean up log snippets in docs * Indentation
* Initial structure of Densenet169 * Densenet169 * add custom args * Updated custom args default values * add argparse import * Unify the default value for output layer name in both accuracy and benchmark * Add Intel License header * flake8 style fix * Update README.md and add unit test commands * Remove unused files and add minor fix per code review * Update unit test command * Update KMP setting * import fix * Change default batch_size to 100 * Fix jason file * Fix typos
* add ssd_vgg16 coco based benchmarks * configure the env vars, clean up and update start.sh and readme. * cleanup and update readme. * update readme and other files to highlight this model works only with py3. * add and use the anchor_manipulator.py customized file. * apply changes to install cocoapi, and update readme with SKX based benchmark log snippet. * use a cocoapi that works with py3, modify to get the expected performance, add unit tests. * add changes based on code review * fix the model name to use ssd_vgg16 stead of ssd-vgg16 to fix python import. * fix unit tests, update readme. * uppdate log snippet in readme. * update unit tests after supporting memory alloc. * changes for Karthik's code review. * update the int8 log snippet based on CLX. * update the fp32 log snippet based on CLX.
…cisions (#290) * Make TCMalloc enabled for int8 by default, but disabled for other precisions. * Code cleanup * update start script * Updating doc to add more info on TCMalloc
…ds, and the instructions to install. (#292)
* submit for PR language translations tutorial * Removes .nfs files and adds model to main docs README * Deleted more .nfs files * Updated for legal, marketing, punctuation, and official model location * Improved code snippets and added transformer files to launch_benchmark guide * Fixed alignment in main doc README * Remove refs to RNN and LSTM and correct a sentence * Transformer_LT tutorial updates * Update Tutorial.md * Update Tutorial.md * Update Tutorial.md * Update Tutorial.md * Update Tutorial.md * Update Tutorial.md * Update Tutorial.md * Update Tutorial.md
…sing a custom script (SSD-VGG16 model). (#298) * add instructions for how to download coco dataset and it convert to tf records (using a custom script).
* add an example for a resnet50 json file. * add a method to parse the models args json files, add resnet50 and facenet model args, tested and validated it. * clean up parse csv code. * convert some models args to json. * modify the parsing method doc. * add rfcn test and delete tf_model_args.txt file. * add faster_cnn test. * add unit tests for more models. * remeove white spaces. * add more tests. * add more tests. * fix int8 unit tests to work with memory alloc enabled, add ssdvgg16 unit test. * update the contribute.md * add empty line at the end of the file. * fix rfcn performance script. * add densenet169 unit test. * print out comments for each test. * add the two missing tests.
* Fix tzdata installation hang with Ubuntu 18.04 * Update to use 'DEBIAN_FRONTEND=noninteractive' based on feedback from Ebi
…eads (#308) * Added the support to change num_inter_threads and num_intra_threads to the model * Update unit test args to include num_inter and num_intra
* Added SSD-MobileNet to existing tutorial * Added tutorial script and notebook * Improvements and fixes from testing * More small fixes * Adds SSD-MobileNet to main docs README * Updated benchmarking verbiage * Simplify package installs, docker ports, and detached mode * Created requirements.txt
* Update NCF doc for TF models code modification * Creates a backup and adds *.bak to gitignore
* Add affinity and config setting to get better performance on mobilenet-v1. * Remove redundant config settings for mobilenet_v1 inference.
* updated order of intel-tensorflow & tensorflow-serving-api installation.
* Install the development package for google-perftools * Creating symlinks for /usr/lib/libtcmalloc.so if doesn't exist
* Update lm-1b README due to branch and path changes * Added specific SHA (just the current one from master as of 6/26)
* Update README files to use tf-cpu docker image for 1.14 * Peg older version of pytest
jitendra42
requested review from
claynerobison,
dmsuehir,
karthikvadla and
mlukaszewski
as code owners
ashahba
pushed a commit
that referenced
this pull request
Jul 26, 2021
* Update the yearin the header in base specs * Make it a range 2020-2021
ashahba
pushed a commit
that referenced
this pull request
Oct 16, 2021
* Update the yearin the header in base specs * Make it a range 2020-2021
ashahba
added a commit
that referenced
this pull request
Mar 15, 2022
* Merge branch 'jitendra/training-bertlarge-bf16' into 'develop' Add Bert Large bfloat16 training See merge request intelai/models!412 * Regenerate Dockerfiles * SSD-ResNet34 FP32 Training - update num inter/intra threads calculation and README notes * Merge branch 'dina/ssdresnet34-fp32-training' into 'develop' SSD-ResNet34 FP32 Training - update num inter/intra threads calculation and README notes See merge request intelai/models!418 * Add the spec and quickstart files for SSD-ResNet34 FP32 Training * Merge branch 'dina/ssdresnet34-fp32-training-container' into 'develop' Add the spec and quickstart files for SSD-ResNet34 FP32 Training See merge request intelai/models!422 * Fix for notebook dockerfile * Regenerate Dockerfiles * Fix URL for 'scikit-learn' container * Add 'third_party' to docker and Model packages * Merge branch 'ashahba/thrird-party' into 'develop' Add 'third_party' to docker and Model packages See merge request intelai/models!423 * Cherry-pick from develop and resolve conflicts * Cherry-pick from develop and resolve conflicts * Cherry-pick from develop and resolve conflicts * Merge branch 'ashahba/imz-2.1.0' into 'develop' Update GCS links for IMZ v2.1.0 See merge request intelai/models!426 * Add Transformer lt mlperf FP32 training container * Merge branch 'wafaa/add_transformer_lt_mlperf_fp32_training_pkg_container' into 'develop' Add Transformer lt mlperf FP32 training container See merge request intelai/models!424 * More updates for IMZ v2.1.0 * Merge branch 'ashahba/imz-2.1.0' into 'develop' More updates for IMZ v2.1.0 See merge request intelai/models!427 * Regenerate Dockerfiles * Minor cleanup * Fix path to advanced options * Fix ssd-resnet34 Docker image name * Merge branch 'ashahba/ssd-resnet34-img' into 'develop' Fix ssd-resnet34 Docker image name See merge request intelai/models!430 * Use only HTTPS cloning * Merge branch 'ashahba/https-clone' into 'develop' Use only HTTPS cloning See merge request intelai/models!432 * Add k8s package for 'resnet50v1-5-fp32-training' * snapshot Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/model-builder-completion-performance' into 'develop' model builder refactoring See merge request intelai/models!431 * Add 'MINICONDA_VERSION' and update XGBoost * Merge branch 'ashahba/miniconda-version' into 'develop' Add 'MINICONDA_VERSION' and update XGBoost See merge request intelai/models!442 * Add new and misc TPPs for ML and PyTorch * Merge branch 'ashahba/tpps' into 'develop' Add new and misc TPPs for ML and PyTorch See merge request intelai/models!445 * parameterize IMAGE_VERSION so registry images can be changed easily, remove debug output to /tmp/out in model-builder Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/misc-fixes' into 'develop' parameterize IMAGE_VERSION so registry images can be changed easily, remove... See merge request intelai/models!446 * Fixed incorrect underscore to dash * Merge branch 'melanie/transformer_training_readme_fix' into 'develop' Fixed incorrect underscore to dash See merge request intelai/models!449 * Adds unzip to jupyter performance dockerfile * Merge branch 'melanie/add_unzip_jupyter_dockerfile' into 'develop' Adds unzip to jupyter performance dockerfile See merge request intelai/models!451 * Add another scikit-learn container * Merge branch 'ashahba/databricks' into 'develop' Add another scikit-learn container See merge request intelai/models!443 * Upgrade to versions required by SNYK * Merge branch 'ashahba/snyk' into 'develop' Upgrade to versions required by SNYK See merge request intelai/models!453 * Update URLs to public ones * Fix potential security vulnerabilities identified by 'Dependabot alerts' * Merge branch 'ashahba/prepare-for-release' into 'develop' Update URLs to public ones See merge request intelai/models!456 * Merge branch 'ashahba/dependabot-alerts' into 'develop' Fix potential security vulnerabilities identified by 'Dependabot alerts' See merge request intelai/models!457 * Rename TPP file for ML containers * Merge branch 'ashahba/ml-tpps' into 'develop' Rename TPP file for ML containers See merge request intelai/models!458 * fixing issues for perf analysis notebooks * Merge branch 'analyze_two_mkl_jsons' into 'develop' fixing issues for perf analysis notebooks See merge request intelai/models!439 * Merge branch 'analyze_two_mkl_jsons' into 'develop' fixing issues for perf analysis notebooks See merge request intelai/models!439 * Update public PyTorch URL * Merge branch 'ashahba/pytorch-link' into 'develop' Update public PyTorch URL See merge request intelai/models!460 * Update README.md (#69) fix the broken link : https://github.com/IntelAI/models/blob/master/benchmarks/object_detection/tensorflow/faster_rcnn/datasets/coco/README.md * Fix for Jupyter CPU info reporting * Fixed platform util to regex the last column of lscpu to look for empty string on a non-NUMA machine otherwise, platform util will just crashes. * Fix style checks and wide and deep units * Merge branch 'ashahba/fix-style-unit' into 'develop' Fix style checks and wide and deep units See merge request intelai/models!463 * Merge branch 'dtran/fix_numa' into 'develop' Fixed platform util to regex the last column of lscpu to look for empty string... See merge request intelai/models!462 * 'make all' needs to run both 'lint' and 'style' tests * Merge branch 'ashahba/fix-make-all' into 'develop' 'make all' needs to run both 'lint' and 'style' tests See merge request intelai/models!464 * Fixed regex to handle empty string for lscpu on non-NUMA machine. Added test to handle this case also * Merge branch 'dtran/fix_numa' into 'develop' Fixed regex to handle empty string for lscpu on non-NUMA machine. Added test... See merge request intelai/models!466 * Updated location of all_reduce util * Merge branch 'shwetaoj/change_all_reduce_path' into 'develop' Updated location of all_reduce util See merge request intelai/models!468 * Add Transformer language BFloat16 training package and container * Merge branch 'jitendra/tlt-bf16-training-package' into 'develop' Add Transformer language BFloat16 training package and container See merge request intelai/models!467 * Add DenseNet 169 FP32 inference package and container * Merge branch 'wafaa/add_densenet169_fp32_inf_pkg_container' into 'develop' Add DenseNet 169 FP32 inference package and container See merge request intelai/models!470 * Add oneContainer portal links to benchmarks/README.md * Merge branch 'dina/readme_portal_links' into 'develop' Add oneContainer portal links to benchmarks/README.md See merge request intelai/models!473 * fix for _all_models Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'dina/model-builder-frameworks' into 'develop' model-builder update to specify --framework See merge request intelai/models!472 * fix for only tags matching error Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'ashahba/bert-large-bfloat16' into 'develop' Add missing mpi and horovod packages for Bert Large BFloat16 See merge request intelai/models!476 * add k8s framework Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/model-builder-k8s-framework' into 'develop' add k8s framework See merge request intelai/models!475 * Fix for DLRM package paths in the spec * Merge branch 'sharvils/dlrm_spec_fix' into 'develop' Fix for DLRM package paths in the spec See merge request intelai/models!461 * Minimal 'intel' environment snapshot * Merge branch 'ashahba/scikit-learn-tf' into 'develop' Minimal 'intel' environment snapshot See merge request intelai/models!479 * update OUTPUT_DIR, imagePullPolicy Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/resnet50v1-5-fp32-training-k8s' into 'develop' resnet50v1-5-fp32-training-k8s package See merge request intelai/models!478 * bert-large-fp32-training-k8s package Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/bert-large-fp32-training-k8s' into 'develop' bert-large-fp32-training-k8s package See merge request intelai/models!480 * Fix for 'fatal error: ffi.h: No such file or directory' * Merge branch 'ashahba/imz-tf-tools' into 'develop' Fix for 'fatal error: ffi.h: No such file or directory' See merge request intelai/models!484 * resnet50v1-5-fp32-inference-k8s package Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/resnet50v1-5-fp32-inference-k8s' into 'develop' resnet50v1-5-fp32-inference-k8s package See merge request intelai/models!486 * Improves Jupyter notebook setting and usage of ModelZooRoot * Merge branch 'melanie/jupyter_modelzooroot' into 'develop' Improves Jupyter notebook setting and usage of ModelZooRoot See merge request intelai/models!469 * Add quickstart scripts and dockerfiles for wide and deep large dataset int8 and fp32 inference * Merge branch 'wafaa/add_wide_deep_large_ds_int8_fp32_inf_pkgs_containers' into 'develop' Add quickstart scripts and dockerfiles for wide and deep large dataset int8 and fp32 inference See merge request intelai/models!477 * Quickstart script clean up * Merge branch 'wafaa/add_wide_deep_large_ds_int8_fp32_inf_pkgs_containers' into 'develop' Add quickstart scripts and dockerfiles for wide and deep large dataset int8 and fp32 inference See merge request intelai/models!477 * Quickstart script clean up * Merge branch 'wafaa/add_wide_deep_large_ds_int8_fp32_inf_pkgs_containers' into 'develop' Add quickstart scripts and dockerfiles for wide and deep large dataset int8 and fp32 inference See merge request intelai/models!477 * Quickstart script clean up * Merge branch 'dina/quickstart_fixes' into 'develop' Quickstart script clean up See merge request intelai/models!487 * Add Resnet50 v1.5 BFloat16 Training package and container * Merge branch 'jitendra/rn50-bf16-training' into 'develop' Add Resnet50 v1.5 BFloat16 Training package and container See merge request intelai/models!485 * update readme * rfcn-fp32-inference-k8s package Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/rfcn-fp32-inference-k8s' into 'develop' rfcn-fp32-inference-k8s package See merge request intelai/models!483 * Merge branch 'jitendra/update-readme' into 'develop' Update readme See merge request intelai/models!489 * Remove some junk file * Remove duplicate proxy arg * Update partial and dockerfiles with Horovod release v0.21.0 * Merge branch 'ashahba/horovod-release' into 'develop' Update partial and dockerfiles with Horovod release v0.21.0 See merge request intelai/models!493 * Added functions to expose some of the properties like core, logical core, numa nodes * Merge branch 'dtran/platform_util_add' into 'develop' Added functions to expose some of the properties like core, logical core, numa nodes See merge request intelai/models!495 * fix the usecases table format * wide-deep-large-ds-fp32-training-k8s package Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/wide-deep-large-ds-fp32-training-k8s' into 'develop' wide-deep-large-ds-fp32-training-k8s package See merge request intelai/models!494 * Update for public URLs * Merge branch 'ashahba/public-urls' into 'develop' Update for public URLs See merge request intelai/models!500 * Merge branch 'melanie/readme_additions' into 'develop' Add new containers & packages to benchmarks README See merge request intelai/models!498 * Partials for DLRM pytorch container * Merge branch 'sharvils/dlrm_partials_conda' into 'develop' Partials for DLRM pytorch container See merge request intelai/models!394 * Add GNMT model package and container * Merge branch 'jitendra/gnmt-package' into 'develop' Add GNMT model package and container See merge request intelai/models!444 * Bring some missing commits from develop * Revert 'all_reduce' v1 compatibility * Prepare for Model Zoo v2.2.0 release * Merge branch 'ashahba/imz-v2.2.0' into 'develop' Prepare for Model Zoo v2.2.0 release See merge request intelai/models!503 * TensorFlow Serving Helm Chart * Merge branch 'ashahba/tensorflow-serving-chart' into 'develop' TensorFlow Serving Helm Chart See merge request intelai/models!490 * use 2.1.0 to 2.2.0 for images Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/k8-packages-misc-fixes' into 'develop' various fixes in documentation and yamls across k8 packages See merge request intelai/models!496 * fix for pipeline, see argoproj/argo-workflows#2522 (comment) Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/k8s-workflow-fix' into 'develop' fix for pipeline, see argoproj/argo-workflows#2522 (comment) See merge request intelai/models!504 * Fix unit_tests * fix for PREPROCESS_IMAGE_VERSION Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/k8s-rfcn-fp32-inference-fix' into 'develop' fix for PREPROCESS_IMAGE_VERSION See merge request intelai/models!505 * add pytorch resnet50 fp32/bf16 inference model * Merge branch 'pytorch-xiaobing' into 'develop' add pytorch resnet50 fp32/bf16 inference model See merge request intelai/models!416 * Adds doc partials for k8s packages * Merge branch 'melanie/k8s_documentation' into 'develop' Adds doc partials for k8s packages See merge request intelai/models!407 * Adds k8s packaging * Merge branch 'melanie/k8s_packages' into 'develop' Adds k8s packaging See merge request intelai/models!358 * Separate k8s from quickstart directory * Merge branch 'melanie/separate_k8s' into 'develop' Separate k8s from quickstart directory See merge request intelai/models!338 * Checkout remaining changes from develop * Sync with 61fbc22 * TensorFlow Serving Helm Chart * Merge branch 'ashahba/tensorflow-serving-chart' into 'develop' TensorFlow Serving Helm Chart See merge request intelai/models!490 * use 2.1.0 to 2.2.0 for images Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/k8-packages-misc-fixes' into 'develop' various fixes in documentation and yamls across k8 packages See merge request intelai/models!496 * fix for pipeline, see argoproj/argo-workflows#2522 (comment) Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/k8s-workflow-fix' into 'develop' fix for pipeline, see argoproj/argo-workflows#2522 (comment) See merge request intelai/models!504 * fix for PREPROCESS_IMAGE_VERSION Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/k8s-rfcn-fp32-inference-fix' into 'develop' fix for PREPROCESS_IMAGE_VERSION See merge request intelai/models!505 * Remove file due to bad merge * Fix dlrm training * Merge branch 'ashahba/dlrm-training-fix' into 'develop' Fix dlrm training See merge request intelai/models!506 * Fix dlrm training * Merge branch 'ashahba/dlrm-training-fix' into 'develop' Fix dlrm training See merge request intelai/models!506 * Add '3d-unet' to release branch * Hold off on 'Bert Large INT8' for now * Update 'intel-tensorflow' versions to 'v2.4' * Merge branch 'ashahba/tf-2.4.0' into 'develop' Update 'intel-tensorflow' versions to 'v2.4' See merge request intelai/models!575 * add instructions for docker numa cpuset binding for tf model containers * Merge branch 'wafaa/update_tf_doc_for_numa_cpuset_cpus' into 'develop' Update TF documentation to include docker NUMA --cpuset-cpus binding instructions See merge request intelai/models!583 * Python 3.8 updates * Merge branch 'dina/py3.8_var_develop' into 'develop' IMZ 2.3 update PY_VERSION=3.8 See merge request intelai/models!585 * Revert "Updated location of all_reduce util" This reverts commit fa252ce. * Update docker image for ssd-resnet34-bfloat16-training * Style fixes * Merge branch 'dina/style-fix' into 'develop' Style fixes (whitespace) See merge request intelai/models!589 * Revert "Amin/bert freeze graph" This reverts commit c2f652d. * Revert "Bert large export , read and write and run from freeze graph" This reverts commit 2c67881. * Add deprecation message for --num-instances * Merge branch 'dina/deprecate-num-instances' into 'develop' Add deprecation message for --num-instances See merge request intelai/models!588 * Update Public bucket URLs for v2.3 * Merge branch 'ashahba/public-bucket-urls' into 'develop' Update Public bucket URLs for v2.3 See merge request intelai/models!591 * Cleanup Bert Large Inference and Training README files * Merge branch 'ashahba/bert-inference' into 'develop' Cleanup Bert Large Inference and Training README files See merge request intelai/models!594 * Updated oneContainer Portal links for IMZ 2.3 * Update PyTorch containers and replace bf16 with bfloat16 * Merge branch 'ashahba/dlrm-training' into 'develop' Update PyTorch containers and replace bf16 with bfloat16 See merge request intelai/models!597 * removed internal references * Upgrade to 'TensorFlow Serving 2.4.0' Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Merge branch 'ashahba/tf-serving-2.4.0' into 'develop' Upgrade to 'TensorFlow Serving 2.4.0' See merge request intelai/models!624 Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Merge branch 'ashahba/master-pull' into 'develop' merge master also into develop See merge request intelai/models!627 * Fix the URL for 'oneAPI-samples' repo * Merge branch 'ashahba/fix-oneAPI-samples-url' into 'develop' Fix the URL for 'oneAPI-samples' repo See merge request intelai/models!632 * doc: edit AI Kit names and visibility in top level README (#74) Signed-off-by: David B. Kinder <david.b.kinder@intel.com> * Fix style checks Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Fix link to 'g3doc' installation Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Merge branch 'ashahba/g3doc-link' into 'develop' Fix 'g3doc' installation link See merge request intelai/models!724 * Fix ResNet50 BFloat16 Inference for Pytorch URL Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Update SSD ResNet34 backbone model links Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Merge branch 'ashahba/ssd-resnet34-backbone' into 'develop' Update SSD ResNet34 backbone model links See merge request intelai/models!755 * Move TF_ENABLE_MKL_NATIVE_FORMAT=0 for int8 to the env vars dict * Revert "Merge branch 'kanvi/3d_unet_fixes' into 'develop'" This reverts commit ed51f34, reversing changes made to 05491a0. * Revert "Merge branch 'jmj_dien2' into 'develop'" This reverts commit 05491a0, reversing changes made to ca9e686. * Revert "Merge branch 'kanvi/3d_unet_mlperf' into 'develop'" This reverts commit 08446dc, reversing changes made to 964df8e. * Revert "Merge branch 'ashahba/dien-styles' into 'develop'" This reverts commit bc96260, reversing changes made to acc0c20. * Revert "Merge branch 'jmj_dien_new1' into 'develop'" This reverts commit acc0c20, reversing changes made to b74fe8f. * Revert "Merge branch 'jmj_dien' into 'develop'" This reverts commit c7e0bc5, reversing changes made to 6fde767. * Merge branch 'sriniva2/int8_block_format' into 'tf-r2.5-imz-r2.4' Force int8 to go through blocked format See merge request intelai/models!623 * Merge branch 'dina/tf-r2.5-int8-fix' into 'tf-r2.5-imz-r2.4' Force TF_ENABLE_MKL_NATIVE_FORMAT=0 for int8 models See merge request intelai/models!759 * Revert "Merge branch 'ashahba/rcv1-svm' into 'develop'" This reverts commit 3333d84, reversing changes made to 1c083e2. * Revert "Merge branch 'dina/lpot' into 'develop'" This reverts commit 963c44a, reversing changes made to 8f79863. * Prevent adding wheels or other archives to the repo (#7) Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Prepare for Model Zoo v2.4.0 release (#20) * Prepare for Model Zoo v2.4.0 release Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Fix a typo in TFS version Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Fix TF Serving '2.5.1' docs too Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Remove unsupported models (#27) * Revert "Support precision=int8 flag for running int8 mode graph model files" This reverts commit 614e569. Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Revert "Add the model package and container for BERT large int8 inference (SQuAD)" This reverts commit bb5842a. Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Remove the broken link * Revert "Update BERT large docs for to separate out "advanced" and allow for using quickstart scripts when cloning the repo" This reverts commit de9c626. Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Prevent adding wheels or other archives to the repo (#7) Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Prepare for Model Zoo v2.4.0 release (#20) * Prepare for Model Zoo v2.4.0 release Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Fix a typo in TFS version Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Fix TF Serving '2.5.1' docs too Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Add init files in language modeling & tensorflow folders (#23) * add init files in language modeling & tensorflow folders * changed year * Update the year in the header in base specs (#26) * Update the yearin the header in base specs * Make it a range 2020-2021 * Update download links for Model Zoo v2.4.0 Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Update Package download URLs too Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Regen all Dockerfiles Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> Co-authored-by: Patil, Jitendra <jitendra.patil@intel.com> Co-authored-by: Jones, Dina S <dina.s.jones@intel.com> Co-authored-by: Taie, Wafaa S <wafaa.s.taie@intel.com> Co-authored-by: Kasravi, Kam D <kam.d.kasravi@intel.com> Co-authored-by: Melanie H Buehler <melanie.h.buehler@intel.com> Co-authored-by: Tran, Dzung D <dzung.d.tran@intel.com> Co-authored-by: Tsai, Louie <louie.tsai@intel.com> Co-authored-by: yinghu5 <ying.hu@intel.com> Co-authored-by: shwetaoj <shweta.ojha@intel.com> Co-authored-by: Shah, Sharvil <sharvil.shah@intel.com> Co-authored-by: Zhang, Xiaobing <xiaobing.zhang@intel.com> Co-authored-by: David Kinder <david.b.kinder@intel.com> Co-authored-by: Narayanamoorthy, Srinivasan <srinivasan.narayanamoorthy@intel.com>
ashahba
pushed a commit
that referenced
this pull request
Apr 1, 2022
* Update the yearin the header in base specs * Make it a range 2020-2021
ashahba
added a commit
that referenced
this pull request
Apr 1, 2022
* Merge branch 'jitendra/training-bertlarge-bf16' into 'develop' Add Bert Large bfloat16 training See merge request intelai/models!412 * Regenerate Dockerfiles * SSD-ResNet34 FP32 Training - update num inter/intra threads calculation and README notes * Merge branch 'dina/ssdresnet34-fp32-training' into 'develop' SSD-ResNet34 FP32 Training - update num inter/intra threads calculation and README notes See merge request intelai/models!418 * Add the spec and quickstart files for SSD-ResNet34 FP32 Training * Merge branch 'dina/ssdresnet34-fp32-training-container' into 'develop' Add the spec and quickstart files for SSD-ResNet34 FP32 Training See merge request intelai/models!422 * Fix for notebook dockerfile * Regenerate Dockerfiles * Fix URL for 'scikit-learn' container * Add 'third_party' to docker and Model packages * Merge branch 'ashahba/thrird-party' into 'develop' Add 'third_party' to docker and Model packages See merge request intelai/models!423 * Cherry-pick from develop and resolve conflicts * Cherry-pick from develop and resolve conflicts * Cherry-pick from develop and resolve conflicts * Merge branch 'ashahba/imz-2.1.0' into 'develop' Update GCS links for IMZ v2.1.0 See merge request intelai/models!426 * Add Transformer lt mlperf FP32 training container * Merge branch 'wafaa/add_transformer_lt_mlperf_fp32_training_pkg_container' into 'develop' Add Transformer lt mlperf FP32 training container See merge request intelai/models!424 * More updates for IMZ v2.1.0 * Merge branch 'ashahba/imz-2.1.0' into 'develop' More updates for IMZ v2.1.0 See merge request intelai/models!427 * Regenerate Dockerfiles * Minor cleanup * Fix path to advanced options * Fix ssd-resnet34 Docker image name * Merge branch 'ashahba/ssd-resnet34-img' into 'develop' Fix ssd-resnet34 Docker image name See merge request intelai/models!430 * Use only HTTPS cloning * Merge branch 'ashahba/https-clone' into 'develop' Use only HTTPS cloning See merge request intelai/models!432 * Add k8s package for 'resnet50v1-5-fp32-training' * snapshot Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/model-builder-completion-performance' into 'develop' model builder refactoring See merge request intelai/models!431 * Add 'MINICONDA_VERSION' and update XGBoost * Merge branch 'ashahba/miniconda-version' into 'develop' Add 'MINICONDA_VERSION' and update XGBoost See merge request intelai/models!442 * Add new and misc TPPs for ML and PyTorch * Merge branch 'ashahba/tpps' into 'develop' Add new and misc TPPs for ML and PyTorch See merge request intelai/models!445 * parameterize IMAGE_VERSION so registry images can be changed easily, remove debug output to /tmp/out in model-builder Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/misc-fixes' into 'develop' parameterize IMAGE_VERSION so registry images can be changed easily, remove... See merge request intelai/models!446 * Fixed incorrect underscore to dash * Merge branch 'melanie/transformer_training_readme_fix' into 'develop' Fixed incorrect underscore to dash See merge request intelai/models!449 * Adds unzip to jupyter performance dockerfile * Merge branch 'melanie/add_unzip_jupyter_dockerfile' into 'develop' Adds unzip to jupyter performance dockerfile See merge request intelai/models!451 * Add another scikit-learn container * Merge branch 'ashahba/databricks' into 'develop' Add another scikit-learn container See merge request intelai/models!443 * Upgrade to versions required by SNYK * Merge branch 'ashahba/snyk' into 'develop' Upgrade to versions required by SNYK See merge request intelai/models!453 * Update URLs to public ones * Fix potential security vulnerabilities identified by 'Dependabot alerts' * Merge branch 'ashahba/prepare-for-release' into 'develop' Update URLs to public ones See merge request intelai/models!456 * Merge branch 'ashahba/dependabot-alerts' into 'develop' Fix potential security vulnerabilities identified by 'Dependabot alerts' See merge request intelai/models!457 * Rename TPP file for ML containers * Merge branch 'ashahba/ml-tpps' into 'develop' Rename TPP file for ML containers See merge request intelai/models!458 * fixing issues for perf analysis notebooks * Merge branch 'analyze_two_mkl_jsons' into 'develop' fixing issues for perf analysis notebooks See merge request intelai/models!439 * Merge branch 'analyze_two_mkl_jsons' into 'develop' fixing issues for perf analysis notebooks See merge request intelai/models!439 * Update public PyTorch URL * Merge branch 'ashahba/pytorch-link' into 'develop' Update public PyTorch URL See merge request intelai/models!460 * Update README.md (#69) fix the broken link : https://github.com/IntelAI/models/blob/master/benchmarks/object_detection/tensorflow/faster_rcnn/datasets/coco/README.md * Fix for Jupyter CPU info reporting * Fixed platform util to regex the last column of lscpu to look for empty string on a non-NUMA machine otherwise, platform util will just crashes. * Fix style checks and wide and deep units * Merge branch 'ashahba/fix-style-unit' into 'develop' Fix style checks and wide and deep units See merge request intelai/models!463 * Merge branch 'dtran/fix_numa' into 'develop' Fixed platform util to regex the last column of lscpu to look for empty string... See merge request intelai/models!462 * 'make all' needs to run both 'lint' and 'style' tests * Merge branch 'ashahba/fix-make-all' into 'develop' 'make all' needs to run both 'lint' and 'style' tests See merge request intelai/models!464 * Fixed regex to handle empty string for lscpu on non-NUMA machine. Added test to handle this case also * Merge branch 'dtran/fix_numa' into 'develop' Fixed regex to handle empty string for lscpu on non-NUMA machine. Added test... See merge request intelai/models!466 * Updated location of all_reduce util * Merge branch 'shwetaoj/change_all_reduce_path' into 'develop' Updated location of all_reduce util See merge request intelai/models!468 * Add Transformer language BFloat16 training package and container * Merge branch 'jitendra/tlt-bf16-training-package' into 'develop' Add Transformer language BFloat16 training package and container See merge request intelai/models!467 * Add DenseNet 169 FP32 inference package and container * Merge branch 'wafaa/add_densenet169_fp32_inf_pkg_container' into 'develop' Add DenseNet 169 FP32 inference package and container See merge request intelai/models!470 * Add oneContainer portal links to benchmarks/README.md * Merge branch 'dina/readme_portal_links' into 'develop' Add oneContainer portal links to benchmarks/README.md See merge request intelai/models!473 * fix for _all_models Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'dina/model-builder-frameworks' into 'develop' model-builder update to specify --framework See merge request intelai/models!472 * fix for only tags matching error Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'ashahba/bert-large-bfloat16' into 'develop' Add missing mpi and horovod packages for Bert Large BFloat16 See merge request intelai/models!476 * add k8s framework Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/model-builder-k8s-framework' into 'develop' add k8s framework See merge request intelai/models!475 * Fix for DLRM package paths in the spec * Merge branch 'sharvils/dlrm_spec_fix' into 'develop' Fix for DLRM package paths in the spec See merge request intelai/models!461 * Minimal 'intel' environment snapshot * Merge branch 'ashahba/scikit-learn-tf' into 'develop' Minimal 'intel' environment snapshot See merge request intelai/models!479 * update OUTPUT_DIR, imagePullPolicy Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/resnet50v1-5-fp32-training-k8s' into 'develop' resnet50v1-5-fp32-training-k8s package See merge request intelai/models!478 * bert-large-fp32-training-k8s package Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/bert-large-fp32-training-k8s' into 'develop' bert-large-fp32-training-k8s package See merge request intelai/models!480 * Fix for 'fatal error: ffi.h: No such file or directory' * Merge branch 'ashahba/imz-tf-tools' into 'develop' Fix for 'fatal error: ffi.h: No such file or directory' See merge request intelai/models!484 * resnet50v1-5-fp32-inference-k8s package Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/resnet50v1-5-fp32-inference-k8s' into 'develop' resnet50v1-5-fp32-inference-k8s package See merge request intelai/models!486 * Improves Jupyter notebook setting and usage of ModelZooRoot * Merge branch 'melanie/jupyter_modelzooroot' into 'develop' Improves Jupyter notebook setting and usage of ModelZooRoot See merge request intelai/models!469 * Add quickstart scripts and dockerfiles for wide and deep large dataset int8 and fp32 inference * Merge branch 'wafaa/add_wide_deep_large_ds_int8_fp32_inf_pkgs_containers' into 'develop' Add quickstart scripts and dockerfiles for wide and deep large dataset int8 and fp32 inference See merge request intelai/models!477 * Quickstart script clean up * Merge branch 'wafaa/add_wide_deep_large_ds_int8_fp32_inf_pkgs_containers' into 'develop' Add quickstart scripts and dockerfiles for wide and deep large dataset int8 and fp32 inference See merge request intelai/models!477 * Quickstart script clean up * Merge branch 'wafaa/add_wide_deep_large_ds_int8_fp32_inf_pkgs_containers' into 'develop' Add quickstart scripts and dockerfiles for wide and deep large dataset int8 and fp32 inference See merge request intelai/models!477 * Quickstart script clean up * Merge branch 'dina/quickstart_fixes' into 'develop' Quickstart script clean up See merge request intelai/models!487 * Add Resnet50 v1.5 BFloat16 Training package and container * Merge branch 'jitendra/rn50-bf16-training' into 'develop' Add Resnet50 v1.5 BFloat16 Training package and container See merge request intelai/models!485 * update readme * rfcn-fp32-inference-k8s package Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/rfcn-fp32-inference-k8s' into 'develop' rfcn-fp32-inference-k8s package See merge request intelai/models!483 * Merge branch 'jitendra/update-readme' into 'develop' Update readme See merge request intelai/models!489 * Remove some junk file * Remove duplicate proxy arg * Update partial and dockerfiles with Horovod release v0.21.0 * Merge branch 'ashahba/horovod-release' into 'develop' Update partial and dockerfiles with Horovod release v0.21.0 See merge request intelai/models!493 * Added functions to expose some of the properties like core, logical core, numa nodes * Merge branch 'dtran/platform_util_add' into 'develop' Added functions to expose some of the properties like core, logical core, numa nodes See merge request intelai/models!495 * fix the usecases table format * wide-deep-large-ds-fp32-training-k8s package Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/wide-deep-large-ds-fp32-training-k8s' into 'develop' wide-deep-large-ds-fp32-training-k8s package See merge request intelai/models!494 * Update for public URLs * Merge branch 'ashahba/public-urls' into 'develop' Update for public URLs See merge request intelai/models!500 * Merge branch 'melanie/readme_additions' into 'develop' Add new containers & packages to benchmarks README See merge request intelai/models!498 * Partials for DLRM pytorch container * Merge branch 'sharvils/dlrm_partials_conda' into 'develop' Partials for DLRM pytorch container See merge request intelai/models!394 * Add GNMT model package and container * Merge branch 'jitendra/gnmt-package' into 'develop' Add GNMT model package and container See merge request intelai/models!444 * Bring some missing commits from develop * Revert 'all_reduce' v1 compatibility * Prepare for Model Zoo v2.2.0 release * Merge branch 'ashahba/imz-v2.2.0' into 'develop' Prepare for Model Zoo v2.2.0 release See merge request intelai/models!503 * TensorFlow Serving Helm Chart * Merge branch 'ashahba/tensorflow-serving-chart' into 'develop' TensorFlow Serving Helm Chart See merge request intelai/models!490 * use 2.1.0 to 2.2.0 for images Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/k8-packages-misc-fixes' into 'develop' various fixes in documentation and yamls across k8 packages See merge request intelai/models!496 * fix for pipeline, see argoproj/argo-workflows#2522 (comment) Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/k8s-workflow-fix' into 'develop' fix for pipeline, see argoproj/argo-workflows#2522 (comment) See merge request intelai/models!504 * Fix unit_tests * fix for PREPROCESS_IMAGE_VERSION Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/k8s-rfcn-fp32-inference-fix' into 'develop' fix for PREPROCESS_IMAGE_VERSION See merge request intelai/models!505 * add pytorch resnet50 fp32/bf16 inference model * Merge branch 'pytorch-xiaobing' into 'develop' add pytorch resnet50 fp32/bf16 inference model See merge request intelai/models!416 * Adds doc partials for k8s packages * Merge branch 'melanie/k8s_documentation' into 'develop' Adds doc partials for k8s packages See merge request intelai/models!407 * Adds k8s packaging * Merge branch 'melanie/k8s_packages' into 'develop' Adds k8s packaging See merge request intelai/models!358 * Separate k8s from quickstart directory * Merge branch 'melanie/separate_k8s' into 'develop' Separate k8s from quickstart directory See merge request intelai/models!338 * Checkout remaining changes from develop * Sync with 61fbc22 * TensorFlow Serving Helm Chart * Merge branch 'ashahba/tensorflow-serving-chart' into 'develop' TensorFlow Serving Helm Chart See merge request intelai/models!490 * use 2.1.0 to 2.2.0 for images Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/k8-packages-misc-fixes' into 'develop' various fixes in documentation and yamls across k8 packages See merge request intelai/models!496 * fix for pipeline, see argoproj/argo-workflows#2522 (comment) Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/k8s-workflow-fix' into 'develop' fix for pipeline, see argoproj/argo-workflows#2522 (comment) See merge request intelai/models!504 * fix for PREPROCESS_IMAGE_VERSION Signed-off-by: Kam D Kasravi <kam.d.kasravi@intel.com> * Merge branch 'kdkasrav/k8s-rfcn-fp32-inference-fix' into 'develop' fix for PREPROCESS_IMAGE_VERSION See merge request intelai/models!505 * Remove file due to bad merge * Fix dlrm training * Merge branch 'ashahba/dlrm-training-fix' into 'develop' Fix dlrm training See merge request intelai/models!506 * Fix dlrm training * Merge branch 'ashahba/dlrm-training-fix' into 'develop' Fix dlrm training See merge request intelai/models!506 * Add '3d-unet' to release branch * Hold off on 'Bert Large INT8' for now * Update 'intel-tensorflow' versions to 'v2.4' * Merge branch 'ashahba/tf-2.4.0' into 'develop' Update 'intel-tensorflow' versions to 'v2.4' See merge request intelai/models!575 * add instructions for docker numa cpuset binding for tf model containers * Merge branch 'wafaa/update_tf_doc_for_numa_cpuset_cpus' into 'develop' Update TF documentation to include docker NUMA --cpuset-cpus binding instructions See merge request intelai/models!583 * Python 3.8 updates * Merge branch 'dina/py3.8_var_develop' into 'develop' IMZ 2.3 update PY_VERSION=3.8 See merge request intelai/models!585 * Revert "Updated location of all_reduce util" This reverts commit fa252ce. * Update docker image for ssd-resnet34-bfloat16-training * Style fixes * Merge branch 'dina/style-fix' into 'develop' Style fixes (whitespace) See merge request intelai/models!589 * Revert "Amin/bert freeze graph" This reverts commit c2f652d. * Revert "Bert large export , read and write and run from freeze graph" This reverts commit 2c67881. * Add deprecation message for --num-instances * Merge branch 'dina/deprecate-num-instances' into 'develop' Add deprecation message for --num-instances See merge request intelai/models!588 * Update Public bucket URLs for v2.3 * Merge branch 'ashahba/public-bucket-urls' into 'develop' Update Public bucket URLs for v2.3 See merge request intelai/models!591 * Cleanup Bert Large Inference and Training README files * Merge branch 'ashahba/bert-inference' into 'develop' Cleanup Bert Large Inference and Training README files See merge request intelai/models!594 * Updated oneContainer Portal links for IMZ 2.3 * Update PyTorch containers and replace bf16 with bfloat16 * Merge branch 'ashahba/dlrm-training' into 'develop' Update PyTorch containers and replace bf16 with bfloat16 See merge request intelai/models!597 * removed internal references * Upgrade to 'TensorFlow Serving 2.4.0' Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Merge branch 'ashahba/tf-serving-2.4.0' into 'develop' Upgrade to 'TensorFlow Serving 2.4.0' See merge request intelai/models!624 Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Merge branch 'ashahba/master-pull' into 'develop' merge master also into develop See merge request intelai/models!627 * Fix the URL for 'oneAPI-samples' repo * Merge branch 'ashahba/fix-oneAPI-samples-url' into 'develop' Fix the URL for 'oneAPI-samples' repo See merge request intelai/models!632 * doc: edit AI Kit names and visibility in top level README (#74) Signed-off-by: David B. Kinder <david.b.kinder@intel.com> * Fix style checks Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Fix link to 'g3doc' installation Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Merge branch 'ashahba/g3doc-link' into 'develop' Fix 'g3doc' installation link See merge request intelai/models!724 * Fix ResNet50 BFloat16 Inference for Pytorch URL Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Update SSD ResNet34 backbone model links Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Merge branch 'ashahba/ssd-resnet34-backbone' into 'develop' Update SSD ResNet34 backbone model links See merge request intelai/models!755 * Move TF_ENABLE_MKL_NATIVE_FORMAT=0 for int8 to the env vars dict * Revert "Merge branch 'kanvi/3d_unet_fixes' into 'develop'" This reverts commit ed51f34, reversing changes made to 05491a0. * Revert "Merge branch 'jmj_dien2' into 'develop'" This reverts commit 05491a0, reversing changes made to ca9e686. * Revert "Merge branch 'kanvi/3d_unet_mlperf' into 'develop'" This reverts commit 08446dc, reversing changes made to 964df8e. * Revert "Merge branch 'ashahba/dien-styles' into 'develop'" This reverts commit bc96260, reversing changes made to acc0c20. * Revert "Merge branch 'jmj_dien_new1' into 'develop'" This reverts commit acc0c20, reversing changes made to b74fe8f. * Revert "Merge branch 'jmj_dien' into 'develop'" This reverts commit c7e0bc5, reversing changes made to 6fde767. * Merge branch 'sriniva2/int8_block_format' into 'tf-r2.5-imz-r2.4' Force int8 to go through blocked format See merge request intelai/models!623 * Merge branch 'dina/tf-r2.5-int8-fix' into 'tf-r2.5-imz-r2.4' Force TF_ENABLE_MKL_NATIVE_FORMAT=0 for int8 models See merge request intelai/models!759 * Revert "Merge branch 'ashahba/rcv1-svm' into 'develop'" This reverts commit 3333d84, reversing changes made to 1c083e2. * Revert "Merge branch 'dina/lpot' into 'develop'" This reverts commit 963c44a, reversing changes made to 8f79863. * Prevent adding wheels or other archives to the repo (#7) Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Prepare for Model Zoo v2.4.0 release (#20) * Prepare for Model Zoo v2.4.0 release Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Fix a typo in TFS version Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Fix TF Serving '2.5.1' docs too Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Remove unsupported models (#27) * Revert "Support precision=int8 flag for running int8 mode graph model files" This reverts commit 614e569. Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Revert "Add the model package and container for BERT large int8 inference (SQuAD)" This reverts commit bb5842a. Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Remove the broken link * Revert "Update BERT large docs for to separate out "advanced" and allow for using quickstart scripts when cloning the repo" This reverts commit de9c626. Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Prevent adding wheels or other archives to the repo (#7) Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Prepare for Model Zoo v2.4.0 release (#20) * Prepare for Model Zoo v2.4.0 release Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Fix a typo in TFS version Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Fix TF Serving '2.5.1' docs too Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Add init files in language modeling & tensorflow folders (#23) * add init files in language modeling & tensorflow folders * changed year * Update the year in the header in base specs (#26) * Update the yearin the header in base specs * Make it a range 2020-2021 * Update download links for Model Zoo v2.4.0 Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Update Package download URLs too Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> * Regen all Dockerfiles Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com> Co-authored-by: Patil, Jitendra <jitendra.patil@intel.com> Co-authored-by: Jones, Dina S <dina.s.jones@intel.com> Co-authored-by: Taie, Wafaa S <wafaa.s.taie@intel.com> Co-authored-by: Kasravi, Kam D <kam.d.kasravi@intel.com> Co-authored-by: Melanie H Buehler <melanie.h.buehler@intel.com> Co-authored-by: Tran, Dzung D <dzung.d.tran@intel.com> Co-authored-by: Tsai, Louie <louie.tsai@intel.com> Co-authored-by: yinghu5 <ying.hu@intel.com> Co-authored-by: shwetaoj <shweta.ojha@intel.com> Co-authored-by: Shah, Sharvil <sharvil.shah@intel.com> Co-authored-by: Zhang, Xiaobing <xiaobing.zhang@intel.com> Co-authored-by: David Kinder <david.b.kinder@intel.com> Co-authored-by: Narayanamoorthy, Srinivasan <srinivasan.narayanamoorthy@intel.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.