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/common/operations/SVDF.cpp | |
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/common/operations/SVDF.cpp')
0 files changed, 0 insertions, 0 deletions