| commit | 2d33b3f144ba2365b620cbe9dcf18f51d594e39a | [log] [tgz] |
|---|---|---|
| author | Xusong Wang <xusongw@google.com> | Tue Jun 11 14:42:56 2019 -0700 |
| committer | Xusong Wang <xusongw@google.com> | Wed Jun 12 16:05:59 2019 -0700 |
| tree | 553a8cdc135f70197f7aeadce995db415ab7282b | |
| parent | 0e556ab7ea52c319cc41e75a0076f6357381d86a [diff] |
Fix PRELU underflow/overflow issue. The quant8 results should be clamped by 0 and 255 before static casting to uint8_t. Bug: 134800353 Test: NeuralNetworksTest_static_fuzzing Change-Id: I1bc8f386782c67158edd3da2f663fee5746dda48 Merged-In: I1bc8f386782c67158edd3da2f663fee5746dda48 (cherry picked from commit 3ca1c4d963d0007fe2b90dc5ef97bfee4b3f805a)