add EmbeddingBagOffsetsSum op and tests#100
Conversation
Signed-off-by: Zhibin Li <zhibin.li@intel.com>
7810ae1 to
d5c0a49
Compare
...ional/plugin/plaidml/shared_tests_instances/single_layer_tests/embedding_bag_offsets_sum.cpp
Outdated
Show resolved
Hide resolved
...ional/plugin/plaidml/shared_tests_instances/single_layer_tests/embedding_bag_offsets_sum.cpp
Outdated
Show resolved
Hide resolved
inference-engine/src/plaidml_plugin/ops/embedding_bag_offsets_sum.cpp
Outdated
Show resolved
Hide resolved
...ional/plugin/plaidml/shared_tests_instances/single_layer_tests/embedding_bag_offsets_sum.cpp
Outdated
Show resolved
Hide resolved
...ional/plugin/plaidml/shared_tests_instances/single_layer_tests/embedding_bag_offsets_sum.cpp
Outdated
Show resolved
Hide resolved
inference-engine/src/plaidml_plugin/ops/embedding_bag_offsets_sum.cpp
Outdated
Show resolved
Hide resolved
Signed-off-by: Zhibin Li <zhibin.li@intel.com>
inference-engine/src/plaidml_plugin/ops/embedding_bag_offsets_sum.cpp
Outdated
Show resolved
Hide resolved
inference-engine/src/plaidml_plugin/ops/embedding_bag_offsets_sum.cpp
Outdated
Show resolved
Hide resolved
tzerrell
left a comment
There was a problem hiding this comment.
I missed a test failure in my earlier review (specifically the ETS=(5.6)_I(0.1.2.2.3)_O(0.0.2.2)_DI0_WW1_WDI0_netPRC=FP32_indPRC=I32 case)
tzerrell
left a comment
There was a problem hiding this comment.
This error did not reproduce, I must have used a mismatched PlaidML version. So the failure was spurious and this PR is good.
47446d1 to
6e2da16
Compare
|
Should this be reverted or should I just open a new PR for revision? By the way, I wonder how I can use Doesn't |
|
I don't think a reversion is necessary; opening a new PR with revisions should be sufficient. I'll get back to you on your other comments once I have a chance to look more carefully. |
* [DOCS] [41549] Fix broken code block in Install OpenVINO from PyPI Repository (openvinotoolkit#2800) * Turned list into headings * fixes * fix * add animation (openvinotoolkit#2865) * Align `time_tests` with master branch from 4021e14 (openvinotoolkit#2881) * Added info on DockerHub CI Framework (openvinotoolkit#2919) * Feature/azaytsev/cherry pick pr2541 to 2021 1 (openvinotoolkit#2960) * added OpenVINO Model Server to docs (openvinotoolkit#2541) * added OpenVINO Model Server * updated documentation to include valid links * minor fixes * Fixed links and style * Update README.md fixed links to model_server * more corrections * dropped reference in ie_docs and minor fixes * Update README.md Fixed links to Inference Engine pages Co-authored-by: Alina Alborova <alina.alborova@intel.com> Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com> * Added Model Server docs to 2021/1 Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com> Co-authored-by: Alina Alborova <alina.alborova@intel.com> * See Also sections in MO Guide (openvinotoolkit#2770) * convert to doxygen comments * layouts and code comments * separate layout * Changed layouts * Removed FPGA from the documentation * Updated according to CVS-38225 * some changes * Made changes to benchmarks according to review comments * Added logo info to the Legal_Information, updated Ubuntu, CentOS supported versions * Updated supported Intel® Core™ processors list * Fixed table formatting * update api layouts * Added new index page with overview * Changed CMake and Python versions * Fixed links * some layout changes * some layout changes * some layout changes * COnverted svg images to png * layouts * update layout * Added a label for nGraph_Python_API.md * fixed links * Fixed image * removed links to ../IE_DG/Introduction.md * Removed links to tools overview page as removed * some changes * Remove link to Integrate_your_kernels_into_IE.md * remove openvino_docs_IE_DG_Graph_debug_capabilities from layout as it was removed * update layouts * Post-release fixes and installation path changes * Added PIP installation and Build from Source to the layout * Fixed formatting issue, removed broken link * Renamed section EXAMPLES to RESOURCES according to review comments * add mo faq navigation by url param * Removed DLDT description * Pt 1 * Update Deep_Learning_Model_Optimizer_DevGuide.md * Extra file * Update IR_and_opsets.md * Update Known_Issues_Limitations.md * Update Config_Model_Optimizer.md * Update Convert_Model_From_Kaldi.md * Update Convert_Model_From_Kaldi.md * Update Convert_Model_From_MxNet.md * Update Convert_Model_From_ONNX.md * Update Convert_Model_From_TensorFlow.md * Update Converting_Model_General.md * Update Cutting_Model.md * Update IR_suitable_for_INT8_inference.md * Update Aspire_Tdnn_Model.md * Update Convert_Model_From_Caffe.md * Update Convert_Model_From_TensorFlow.md * Update Convert_Model_From_MxNet.md * Update Convert_Model_From_Kaldi.md * Added references to other fws from each fw * Fixed broken links * Fixed broken links * fixes * fixes * Fixed wrong links Co-authored-by: Nikolay Tyukaev <ntyukaev_lo@jenkins.inn.intel.com> Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com> Co-authored-by: Tyukaev <nikolay.tyukaev@intel.com> * Fixes (openvinotoolkit#3105) * Renamed Benchmark App into Benchmark Tool in the menu (openvinotoolkit#3032) * [DOC] Update Docker install guide (openvinotoolkit#3055) (openvinotoolkit#3200) * [DOC] Update Docker install guide * [DOC] Add proxy for Windows Docker install guide * [DOC] move up prebuilt images section * Update installing-openvino-linux.md * Update installing-openvino-docker-linux.md * Update installing-openvino-docker-linux.md Formatting fixes * Update installing-openvino-docker-linux.md Fixed formatting issues * Update installing-openvino-docker-windows.md Minor fixes * Update installing-openvino-docker-linux.md Fixed formatting issues * [DOC] update text with CPU image, remove proxy for win * Update installing-openvino-docker-windows.md Minor fixes * Update installing-openvino-docker-windows.md Minor fix * Update installing-openvino-docker-windows.md Minor fix * Update installing-openvino-docker-windows.md Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com> (cherry picked from commit 4a09888) * Align time_tests with master (openvinotoolkit#3238) * Align time_tests with master * Fix "results" uploading to DB in time_tests * Add new model to `tgl_test_config.yml` * Fix onnx tests versions (openvinotoolkit#3240) * [40929] DL Workbench in Get Started (openvinotoolkit#2740) * Initial commit * Added the doc * More instructions and images * Added slide * Borders for screenshots * fixes * Fixes * Added link to Benchmark app * Replaced the image * tiny fix * tiny fix * Links to DL Workbench Installation Guide (openvinotoolkit#2861) * Links to WB * Changed wording * Changed wording * Fixes * Changes the wording * Minor corrections * Removed an extra point * [41545] Add links to DL Workbench from components that are available in the DL WB (openvinotoolkit#2801) * Added links to MO and Benchmark App * Changed wording * Fixes a link * fixed a link * Changed the wording * Feature/azaytsev/change layout (openvinotoolkit#3295) * Changes according to feedback comments * Replaced @ref's with html links * Fixed links, added a title page for installing from repos and images, fixed formatting issues * Added links * minor fix * Added DL Streamer to the list of components installed by default * Link fixes * Link fixes * ovms doc fix (openvinotoolkit#2988) * added OpenVINO Model Server * ovms doc fixes Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com> * Add several new models to `tgl_test_config.yml` in time_tests (openvinotoolkit#3269) * Fix wrong path for `yolo-v2-tiny-ava-0001` for time_tests * Add several new models to `tgl_test_config.yml` in time_tests * Fix a typo in DL Workbench Get Started (openvinotoolkit#3338) * Fixed a typo * Update openvino_docs.xml Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com> * ops math formula fix (openvinotoolkit#3333) Co-authored-by: Nikolay Tyukaev <ntyukaev_lo@jenkins.inn.intel.com> * Fix paths for `squeezenet1.1` in time_tests config (openvinotoolkit#3416) * GNA Plugin doc review (openvinotoolkit#2922) * Doc review * Addressed comments * Removed an inexistent link * Port PlaidML plugin forward to 2021.1 (#32) Adds PlaidML plugin to this repo on the 2021.1 branch * Enable testing of BatchNorm (#33) * Require specific path to shared library (#34) * enable separate source/so paths * fix tabs * Fix multiple outputs and add Split (#42) Fixes the problem with multiple outputs in the PlaidML plugin described in #36. Adds the Split operation with tests, which utilizes multiple outputs. * Swish (#47) * Add Reverse & tests to PlaidML Plugin (#35) * Make separate PlaidMLProgramBuilder (#92) * Variadic Split (#91) * variadic split w/o -1 * -1 implemented * Fix -1 support in variadic split and test it * Style consistency * Cleanup * Fix exception message * Add BinaryConvolution (#93) * Add working tests back (#97) * Attempt to add tests back * Change op name for logical_and to match tests * Add Tests for *Convert *Convolution_Backprop_Data *Fake_quantize *SoftMax *Tile *Transpose * Fix comparison and logical tests, use IE ref mode for now * Remove cumsum and logical tests * Remove comparison tests and it's fixes * Add bucketize op and tests (#90) * Add extract image patches op (#96) * Hswish via ReLU (#95) * Hswish via ReLU * ReLU max_value used * Add reorg_yolo op (#101) * Remove conv bprop & fake quant tests (#106) * add EmbeddingBagOffsetsSum op and tests (#100) * Add LSTMCell (#102) * Add RNNCell (#109) Co-authored-by: Ling, Liyang <liyang.ling@intel.com> * Add space_to_batch op (#104) * Add tests for MinMax, DepthToSpace (#105) * Add GELU (#107) * Add GRUCell (#110) Co-authored-by: Ling, Liyang <liyang.ling@intel.com> * Fix support for using OpenVINO as a subproject (#111) * Build fixes for newer compilers (#113) * add EmbeddingBagPackedSum op and tests (#114) Co-authored-by: Tim Zerrell <tim.zerrell@intel.com> * Add shuffle_channels op and test. (#112) * Tests for squared difference op (#115) Co-authored-by: Tim Zerrell <tim.zerrell@intel.com> * Add acosh, asinh, atanh into tests (#118) * Reverse sequence (#116) * Add PriorBox op and test. (#117) * Remove obsolete PlaidML code (#120) Co-authored-by: Alina Alborova <alina.alborova@intel.com> Co-authored-by: Nikolay Tyukaev <nikolay.tyukaev@intel.com> Co-authored-by: Vitaliy Urusovskij <vitaliy.urusovskij@intel.com> Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com> Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com> Co-authored-by: Nikolay Tyukaev <ntyukaev_lo@jenkins.inn.intel.com> Co-authored-by: Kate Generalova <kate.generalova@intel.com> Co-authored-by: Rafal Blaczkowski <rafal.blaczkowski@intel.com> Co-authored-by: Tim Zerrell <tim.zerrell@intel.com> Co-authored-by: Brian Retford <brian.retford@intel.com> Co-authored-by: Michael Yi <michael.w.yi@intel.com> Co-authored-by: Liyang Ling <liyang.ling@intel.com> Co-authored-by: Namrata Choudhury <namrata.choudhury@intel.com> Co-authored-by: Xin Wang <xin1.wang@intel.com> Co-authored-by: xinghong chen <xinghong.chen@intel.com> Co-authored-by: Zhibin Li <haoyouab@gmail.com> Co-authored-by: Frank Laub <frank.laub@intel.com>
Some test cases need more discussion and clarification. Please see inline comments.