| 3a9b7c8eb10692fc746a954bfbc4b53b774d267b |
|
10-Oct-2017 |
Yang Ni <yangni@google.com> |
Made embedding lookup take int lookups
Bug: 67459279
NN API only supported float tensors when this op was first added.
Now int tensors are allowed in the API and we have updated the
documentation saying the lookup indices are integers, we need
update the implementaion and tests of this op to match the
documentation.
Also reverted the input order to match TF Lite.
Test: NeuralNetworksTest
Test: adb shell
/data/nativetest64/embedding_lookup_test/embedding_lookup_test
Change-Id: Ie0db884ca772e8fb388876c3cef609016e753bf1
/frameworks/ml/nn/runtime/test/specs/embedding_lookup.mod.py
|
| 0ab32cc5af1abff9e066d7a6eff7bdeaf6f7d3e2 |
|
13-Sep-2017 |
Yang Ni <yangni@google.com> |
Fix test spec for Embedding Lookup
Bug: 63905942
The order of the input tensors was wrong.
Test: adb shell /data/nativetest64/NeuralNetworksTest/NeuralNetworksTest
--gtest_filter=GeneratedTests.embedding_lookup
Change-Id: I1332632b5c8bee8206944749706f3bf93dbcb335
/frameworks/ml/nn/runtime/test/specs/embedding_lookup.mod.py
|
| 4a1a22f65431e2d58dbd189b217785efb35d0624 |
|
06-Sep-2017 |
Yang Ni <yangni@google.com> |
Test spec for the embedding lookup operation
Bug: 63905942
Test: run test_generator.py
Change-Id: I2bc2f5bcaf81ba0f07697075f7d9f1ffc9571afc
/frameworks/ml/nn/runtime/test/specs/embedding_lookup.mod.py
|