- 06 7月, 2023 1 次提交
-
-
由 David Davis 提交于
@tensorflow/micro Flatten namespace for kernel operator RESHAPE Update unit tests namespace usage Update MicroOpResolver namespace usage bug=fixes #2105
-
- 20 6月, 2023 1 次提交
-
-
由 David Davis 提交于
@tensorflow/micro Remove conditional compilation for kernel tests for the following platforms: Xtensa Add optimized kernel reference fallback code for the following platforms: Xtensa Resolves: `TODO(b/237407410): Re-enable for Vision P6 when the issue is resolved` The following table shows the size changes for each benchmark binary as a result of this PR: | Platform | Benchmark | Build | Text | Data | BSS | | --- | --- | --- | --- | --- | --- | | hifi4 | keyword | default | 0 | 0 | 0 | | hifi5 | keyword | default | 0 | 0 | 0 | | p6 | keyword | default | 0 | 0 | 0 | | hifi4 | person detection | default | +40 | +32 | 0 | | hifi5 | person detection | default | +16 | +32 | 0 | | p6 | person detection | default | +64 | +0 | 0 | bug=fixes #1770
-
- 11 6月, 2022 1 次提交
-
-
由 psharath1 提交于
* Added Support for Reshape int8 on Vision P6 Added Support for Reshape int8 on Vision P6 * Use C++ style comments Co-authored-by: NTing Yan <94130036+tingyan19@users.noreply.github.com> Co-authored-by: Nmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
-
- 03 6月, 2022 1 次提交
-
-
由 psharath1 提交于
* Added Support for INT8 pad BUG= Added support for INT8 Pad Fixed padding issues in conv for larger tiles * Reverted submits to main * Revert "Added Support for INT8 pad" This reverts commit fdc6e1d624609041b8b743563613339948ff70da. * Added Support for INT8 Pad BUG= Added support for INT8 Pad. Fixed padding issue in conv. * TFLITE_DCHECK xiPadGetMemReqd_Context() status Co-authored-by: NTing Yan <94130036+tingyan19@users.noreply.github.com>
-
- 26 5月, 2022 1 次提交
-
-
由 Advait Jain 提交于
* Refactor to share code between reference and optimized kernels. The goal is to reduce code duplication, improve readability of the optimized kernels and reduce the maintenance overhead. * Fix bazel build (and hopefully others as well). Co-authored-by: NPauline Sho <psho@google.com>
-
- 17 5月, 2022 1 次提交
-
-
由 psharath1 提交于
* BUG= Added Support for ReduceMax on Vision P6 * BUG= Updated for namespace use * BUG= Fixed build issue for non VP6 cores * updated as per the review comments Co-authored-by: NTing Yan <94130036+tingyan19@users.noreply.github.com>
-