diff options
author | Xusong Wang <xusongw@google.com> | 2020-06-02 14:47:55 -0700 |
---|---|---|
committer | Xusong Wang <xusongw@google.com> | 2020-06-02 14:47:55 -0700 |
commit | 54688b80e26325de12e1dd5112a31343f94d68ae (patch) | |
tree | 02341f58ada78cddcff535c7c609f78bc81d57b7 /nn/runtime/test/specs/V1_2/lsh_projection_float16.mod.py | |
parent | c7e4e604b2d4f1cf8f2bdbe11350a48c719148d3 (diff) | |
download | ml-54688b80e26325de12e1dd5112a31343f94d68ae.tar.gz |
Relaxed LSH_PROJECTION: do not convert the hash tensor as internal
LSH_PROJECTION is very sensitive to the value of the hash tensor. Prior
to this CL, AllInputsAsInternalCoverter will convert the hash tensor to
internal by introducing a dummy ADD operation. Under relaxed execution
mode, the small precision loss in ADD will result in a significant
difference in the final result. This CL prevents the hash tensor from
being converted to internal in relaxed precision tests.
Additionally, this CL removes a redundant variation in
lsh_projection_float16.
Fixes: 155962587
Test: NNT_static
Change-Id: Id5522b4949a4e3ab4801537e8eb747a25f0cd0e8
Diffstat (limited to 'nn/runtime/test/specs/V1_2/lsh_projection_float16.mod.py')
-rw-r--r-- | nn/runtime/test/specs/V1_2/lsh_projection_float16.mod.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/nn/runtime/test/specs/V1_2/lsh_projection_float16.mod.py b/nn/runtime/test/specs/V1_2/lsh_projection_float16.mod.py index ed19b17f7..4b22ad190 100644 --- a/nn/runtime/test/specs/V1_2/lsh_projection_float16.mod.py +++ b/nn/runtime/test/specs/V1_2/lsh_projection_float16.mod.py @@ -36,4 +36,4 @@ input0 = { } output0 = {output: [1, 1, 1, 1, 1, 0, 0, 0]} -Example((input0, output0)).AddVariations("float16"); +Example((input0, output0)) |