* auto-batching POC squashed (all commits from auto-batch-2021.3 branch)
(cherry picked from commit d7742f2c747bc514a126cc9a4d5b99f0ff5cbbc7)
* applying/accomodating the API changes after rebase to the master
* replaying modified version of actual batch selection
* eearly experiments with model mem footprint
* changes from rebasing to the latest master
* experimenting with DG1 on the batch size selection, also collecting the mem footprint
* WIP:moving the auto-batching to the icore to let the MULT/AUTO support that, ALLOW_AUTO_BATCHING as a conventional config key. still fials hot device swap
* quick-n-dirty batch footpint vs device total mem
* code style
* testing which models perform badly due to kernels and NOT (batched) footprint
* stub pipeline task to comunicate the readiness rather than promise/future
* quick-n-dirty timeout impl
* explicit _completionTasks,reverting BA to use the timeout
* inputs outputs copies, works with AUTO and demo now
* accomodate the config per device-id, after rebase to the latest master
* allowing the auto-batching only with tput hint to let more conventional tests pass
* fix the pre-mature timeout restaring via waiting for batch1 requests completion
* moved the bacthed request statring ( along with input copies) to the dedicated thread
* [IE CLDNN] Disable bs_fs_yx_bsv16_fsv16 format for int8 convolution
* code style
* increasing the timeout to test the ssd_* models perf (timeout?) issues
* reducing number of output stuff in BA to avoid bloating the logs in experiments
* more aggressive batching for experiments, not limited to 32 and also 4 as a min
* more accurate timeout debugging info
* getting the reqs limitation from the plugin SetConfig as well
* refactor the reshape logic a bit to accomodate CPU for bathcing, also added remeote context
* let the benchamrk_app to consume specific batch values for the auto-batching such as BATCH:GPU(4)
* auto-batching functional test (with results check vs ref) and GPU instance for that
* fixed arithemtic on blobs ptrs
* clang
* handling possible batched network failure
* BATCH as the constants device name in test
* ENABLE_BATCH
* func tests for CPU, also DetectionOutput hetero tests (CPU and GPU)
* DetectionOutput hetero test for the CPU
* reenabling the Auto-Batching in the AUTO
* auto-batching device enabled in the test
* fixed the DO test
* improve the loading loop logic
* brushed the config keys
* allow hetero code-path for explicit device name like BATCH:GPU(4), used in the hetero code-path tests
* fix the test after refactoring
* clang
* moving ThreadSafeQueue to the ie_parallel, as it is re-used in the AUTO/MULTI and BATCH now
* auto-batching hetero test (subgraph with DetectionOutput)
* fixed minor changes that were result of experiments with impl
* code-style
* brushing, disabling CPU's HETERO tests until planned activity for 22.2
* removing home-baked MAX_BATCH_SZIE and swicthing to the official impl by GPU team
* remote blobs tests for the auto-batching (old API)
* brushed names a bit
* CreateContext and LoadNEtwork with context for the Auto-Batching plus remote-blobs tests
* fixed the ieUnitTests with adding CreateContext stub to the MockICore
* clang
* improved remote-blobs tests
* revert the back BA from exeprimenents with AB + device_use_mem
* conformance tests for BATCH, alos batch size 1 is default for BATCH:DEVICE
* remote blobs 2.0 tests, issue with context having the orig device name
* debugging DG1 perf drop (presumably due to non-fitting the device-mem)
* disbaling WA with batch/=2 for excesive mem footptint, leaving only streams 2
* remote blobs 2.0 tests for different tensor sharing types
* converting assert to throw to accomodate legacy API where the lock() was possible to be called
* revert the timeout back to avoid mixing the studies, fixed the footprint calc
* reverting to estimating the max batch by extrapolating from bacth1 size
* more conservative footptint etimation (with bacth1), graceful bacth 1 handling without duplication
* even graceful batch 1 handling without duplication
* WA for MAX_BATCH_SIZE failure, removing batch4 as a min for the auto-batching
* AutoBatchPlugin -> ov_auto_batch_plugin
* WA for gcc 4.8
* clang
* fix misprint
* fixed errors resulted from recent OV's Variant to Any transition
* skip auto-batching for already-batched networks
* AUTO_BATCH_TIMEOUT and tests
* GPU-specific L3
* switched to pure config, also improved ALLOW_AUTO_BATCHING config key handling logic
* debugging device info
* enabling the config tests for the GPU and fixing the Auto-batching tests to pass
* making the default (when not recognized the driver) cache size more aggressive, to accomodate recent HW with old drivers
* skip auto-batching for RNNs and alikes (e.g. single CHW input)
* fixed fallback to the bacth1 and moved HETERO path under condition to avoid bloating
* brushing
* Auto plugin GetMetric support gpu auto-batch
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add test case
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add comments on test
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* brushing the vars names, alos adding the excpetion handling
* disabling the auto-batching for the networks with non-batched outputs and faster-rcnn and alikes (CVS-74085) to minimize the of #failures
* add try catch
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* brushing the code changed in the GPU plugin
* Auto-Batch requests tests
* brushed varibles a bit (ref)
* cleaned debug output from the ie_core
* cleaned cmake for the Auto-Batch
* removed batchN estimation from batch1
* cleaned from debug printf
* comments, cleanup
* WA the mock test errors introduced with merging the https://github.com/myshevts/openvino/pull/13
* Adding back removed batchN estimation from batch1 to debug degradations on DG1 (resulted from too optimistic MAX_BATCH_SIZE?). This partially reverts commit e8f1738ac1.
* brushing ie_core.cpp
* fix 32bit compilation
* Code review: ENABLE_AUTO_BATCH
* consolidate the auot-batching logic in ie_core.cpp into single ApplyAutoBAtching
* renamed brushed the OPTIMAL_BATCH (now with_SIZE) and mimicks the MAX_BATCH_SZIE wrt MODEL_PTR
* default value for the OPTIMAL_BATCH_SIZE
* clang
* accomodate new func tests location
* fix shuffle of headers after clang + copyrights
* fixed misprint made during code refactoring
* moving the common therad-safe containers (like ThreadSafeQueue) to the dedicated dev_api header
* switch from the device name to the OPTIMAL_BATCH_SIZE metric presence as a conditin to consider Auto-Batching
* switching from the unsafe size() and minimizing time under lock
* code style
* brushed the ApplyAutoBatching
* brushed the netric/config names and descriptions
* completed the core intergration tests for the auto-batching
* ExecGraphInfo and check for incorrect cfg
* removed explicit dependencies from cmake file of the plugin
* disabling Auto-Batching thru the tput hint (to preserve current product default), only excplicit like BATCH:GPU used in the tests
Co-authored-by: Roman Lyamin <roman.lyamin@intel.com>
Co-authored-by: Hu, Yuan2 <yuan2.hu@intel.com>
* Renamed plugin
* Changed plugin source dir
* Fixed tests
* Renamed ENABLE_GNA to ENABLE_INTEL_GNA
* Fixed centos compile error
* One more renaming place
* HF for centos 7
* renamed the name in version api
* Fixed CI configurations
* Disabled GNA plugin for old gcc (<=5.4)
* Fixed Azure Win job
* Enable LTO for oneDNN GPU
* Use importer target for onednn_gpu
* Fixed install of OpenCL, ittapi
* Try to enable samples build
* Fixed ie_wheel build
* Disabled samples
* Fixed incorrect install of pugixml in dynamic build
* Fixed clDNN_unit_tests64 link
* Minimized a number of hardcoded paths
* Switched off ITT
* Disable TBBBind for static Windows
* Fixed link on Windows
* Fixes
* Static build for Window
* Disable unit-tests
* Disabled TF
* Fixed add dependency for PDPD unit tests
* Disabled GNA
* Enabled ngraph test utils
* Fixes
* Fixes
* Disable clDNN for static build on Windows
* Dynamic MCVS runtime for OpenCL
* Disable ITT traces for static libs
* Ability to switch TBBBind_2_5 OFF
* Disabled GPU on Windows build
* Fixed libGNA link
* Disabled some GNA tests
* Fixed multiple definitions issue
* Hide FrontEnd::load in DLL
* Install libGNAStubs
* Trying to fix Windows
* Trying to fix frontends
* Passed compilation on Windows
* Updated install rules for ngraph backends
* Try CPU, TEMPLATE tests
* Enabled unit-tests
* Enabled ngraph tests
* Try to fix unit-test
* Fixed unit-test on Linux
* Fixed compilation with ENABLE_IR_V7_READER=OFF
* Fixed tests on Linux
* Enable cpuFuncTests only in static build
* Try to fix testMockPluginFrontEnd test
* Try to enable TF
* Fixed python tests
* Partial revert
* Removed OV_FRONTEND_PATH
* Proper cmake install for static libraries case
* Added an ability to skip template plugin
* Added install rules for VPU / GPU
* Install more libraries
* Fixed absolute TBB include paths
* Disable GNA
* Fixed issue with linker
* Some fixes
* Fixed linkage issues in tests
* Disabled some tests
* Updated CI pipelines
* Fixed Windows linkage
* Fixed custom_opset test for static casr
* Fixed CVS-70313
* Continue on error
* Fixed clanf-format
* Try to fix Windows linker
* Fixed compilation
* Disable samples
* Fixed samples build with THREADING=SEQ
* Fixed link error on Windows
* Fixed ieFuncTests
* Added static Azure CI
* Revert "Fixed link error on Windows"
This reverts commit 78cca36fd2.
* Merge static and dynamic linux pipelines
* Fixed Azure
* 1. Removed explicit SHARED from libraries
2. Fixed double definition for ie_layer_validators
* Fixed SEG in unit-test: order of initialization for global vars
* Added an ability to find plugins.xml from static IE
* Fixes in unit-test
* Migrated to new macro for import / export
* Minimized number of custom dllexport
* Don't use IR v7 for static libraries
* Revert for merge
* Don't enable tests with dlopen for static libraries
* Code style
* Added condition for export
* Revert format_reader
* Removed forward decalaration with external linkage
* Fixed IE linkage on Windows
* Reverted back 2 flags
* Minimal RRTI for cpuFuncTests
* Minimal RRTI for cpuFuncTests
* Still need IR v7 reader
* Fixed build
* Fixed compilation
* clang-format fix
* Removed BUILD_AS_IS and used USE_STATIC_IE
* Enable IR v7 reader as static library
* Fixed compilation for GPU plugin
* Trying to build plugins as static library
* Plugins are able provide their own name for CreatePluginEngine function
* Fixed CPU
* Fixed comments
* Fixed ENABLE_IR_V7_READER usage
* Fixed VPU
* clang-format
* Fixes
* Fix
* Load multiple plugins at once
* Fixed interpreter undefined symbols
* Trying to dynamically register static plugins
* Reverted some ngraph changes
* Fixed cpuUnitTests compilation
* Fixed compilation
* Fixed myriad
* Fixed custom_opset tests
* Reverted linker flags
* Support both static and dynamic plugins
* Fixed compilation of myriadFuncTests
* Removed duplication
* Fixes after self-review
* Fixed linkage for preprocessing
* Fixes for Windows
* Fixes
* Fixed cmake options
* Fix
* Fix
* Fix 2
* Migrate POC for TensorFlow frontend
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Refactor InputModelTensorFlow API
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Repack POC to official API
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Remove tensorflow API from public include
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Make TF frontend work from MO and clean-up code
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply codestyle
* Fix win biuld
* Fix Linux build
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Implement Place class
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Determine outputs from graph
* Implement all Place classes
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Make small clean-up
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply code-style corrections
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Determine cut nodes
* Apply codestyle
* Rework to use places
* Fix conversion issue
* Fix build
* Fix conversion
* Small fixes
* Add test for tf frontend
* Add tests
* Implement partial conversion
* Use dynamic type in TFFrameworkNode
* Fix build on Linux
* Implement InputModelTF class
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix code by replacing InputModelTensorFlow to InputModelTF
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix to pass getPlaceByTensorName test
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Refactor and clean the code
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Finalize refactoring code
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Support freezing inputs
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Add support for pruning input ports as new model output
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply code-style fixes
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* move op convertors to separate files, refactoring
* openvino codestyle
* openvino codestyle
* fix crash of layer tests
* fix missprint
* Implement TensorFlow NodeContext and DecoderTFProto classes
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Switch to new NodeContext
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Remove ngraph_builder class and node_context_impl class
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Move decoder/graph_iterator to separate files and remove old files
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Document Decoder, GraphIterator, and NodeContext classes
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply code style
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Remove empty file graph_iterator_proto.cpp and redundant comments
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Use base class for GraphIterator in model class and correct exception class
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Use ends_with from util library
* Remain only InputModelTF constructor with GraphIterator and adopt other code
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct code after merge
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply code style
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix code based on feedback: delete extra namespace usage, etc.
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Make legacy TF frontend default in MO and avoid reading tf models from ReadNetwork
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix build issue with FrameworkNode after upstream merge
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct frontend name in test and clean the code
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* refactoring of tf FrontEnd: rename namespaces, delete default opset
* codestyle
* fix e2e tests
* change namespaces of external classes
* resolve review comment
* codestyle
* Clean useless comments and fix tests
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Add copyright for proto files
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Make op translators a part of FrontEndTF
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Align CMakeLists.txt file with other frontends
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Add job_pool into CMakeLists.txt for tensorflow tests
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Remove cout and WA in ie_network_reader.cpp
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct DecoderBase and FrontEndTF methods, clean the code from if 0, utility.hpp, ngraph_conversions.hpp
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Clean operation translator code and remove empty implementation
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Extend cmake template files with tensorflow frontend
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply code-style
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix build issues on MacOS and apply review feedback
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Remove ConstantFolding pass, add destructors for DecoderBase, GraphIterator, and fix Win build
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix Windows build issue
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply code-style fix
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix issues with code style: remove virtual keyword, OpMap removal
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Resolve review remarks
* Resolve review remarks
* codestyle
* resolve review remarks
* fix copyright
* resolve review comments
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
* Merge onnx_importer to onnx_ngraph_frontend
* address review comments
* use onnx_ngraph_frontend in docs/template_extension
* link onnx_ngraph_frontend instead of onnx_importer
* switch onnxruntime branch to rel-1.8.1_ov_2022.1 in https://github.com/intel/onnxruntime
* Remove pip install cmake since the 1.8.1 release doesnt require it
* add alias
* set IMPORTED_GLOBAL
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
This change implements a subset of FrontEnd API for ONNX:
Changes:
- move onnx_common, onnx_editor and onnx_import to ngraph/frontend/onnx
- introduce new target 'onnx_frontend_ngraph' located in ngraph/frontend/onnx/frontend
- new target implements subset of FrontEnd, InputModel and Place interfaces
* Added pugixml as submodule
* CVS-34900: updated pugixml to v1.11.4
* Fixed link with pugixml
* USe pugixml::static
* Try to fix bug
* Removed GITHUB_PULL_REQUEST
* Replaced OpenVINO_MAIN_SOURCE_DIR -> OpenVINO_SOURCE_DIR
* Removed some usages of IE_MAIN_SOURCE_DIR
* Use ngraph target directly
* Moved cmake/templates to <root>
* Removed ngraph versioning, reused IE one
* Merged converage
* Removed duplicatde ngraph cmake options
* Moved dependencies to <root>/cmake
* Removed installing of VERSION
* enable make clean to remove ie_wheel artifacts
* ./setup.py:132:1: E302 expected 2 blank lines
* fix CI build issue
* Removed not-needed components from ie_wheel
* Use explicit python3 vresion in ngraph pythpn
* Use python3 everywhere
* Reuse python3 more
* Added function to build with Py_LIMITED_API
* Sync 2 cmake python modules
* Fix for tools
* Fixed typo
* Enable python by default
* Enable python build iff python-dev is found
* More migration to Python3_VERSION
* Install wheel requirements
* Fixed ngraph Python separate build
* Fixed cython compilation
* Revert to old packages
* Added suffix
* Specify python version explicitly
* Don't depend on python interp to build python itself
* More improvements
* Revert offline transformations back to ie_wheel
* Refactoring
* Trying to build wheel independently on C++ runtime
* Build wheel only with main OpenVINO
* Fixed typo in test_utils cmake lists
* Adding link stage
* small fix
* git diff
* Try to fix python tests
Co-authored-by: Sergey Lyubimtsev <sergey.lyubimtsev@intel.com>
* Compile time enabling or disabling of first inference time counters
* First inference time counters
* Counters for validate_nodes_and_infer_types and check_all_parameters_registered removed from first inference time counters scope
* Code style fix
* Missing macro for CC and invalid domain names
* Code style fix
* Unused function warnings fixed
* Fixed documentation build when paths contain spaces
* ops math formula fix
* Fixed typo in
* Added more dependencies for openvino_docs
* Improvements
Co-authored-by: Nikolay Tyukaev <ntyukaev_lo@jenkins.inn.intel.com>
