- 26 5月, 2023 1 次提交
-
-
由 TANMAY DAS 提交于
TFLM swapping TfLiteRegistration_V1 struct to a new more embedded friendly api in the TFLMRegistration struct (#2001) BUG=http://b/279811848
-
- 11 3月, 2023 1 次提交
-
-
由 Advait Jain 提交于
Change generated with the following command: ```bash cd tensorflow/lite/micro/ sed -i 's/TfLiteRegistration/TfLiteRegistration_V1/g' `find . -name "*.h" -o -name "*.cc"` cd - cd third_party/hexagon/ sed -i 's/TfLiteRegistration/TfLiteRegistration_V1/g' `find . -name "*.h" -o -name "*.cc"` cd - tensorflow/lite/micro/tools/ci_build/test_code_style.sh --fix_formatting ``` BUG=http://b/272808609
-
- 16 2月, 2023 1 次提交
-
-
由 Pauline Sho 提交于
INT4 unpacking was previously added to the generic `Eval()` functions, but left out in specialized eval functions with specific types (e.g. `EvalInt8()`). These were created to drop unused symbols during linking. This PR adds such support for those functions. 16a8w support is out of scope at the moment. BUG=b/269348526
-
- 10 2月, 2023 1 次提交
-
-
由 Steven Toribio 提交于
-Refactors unpacking outside of deptwise_conv and fully_connected reference kernel for 4bit test case -allows 4 bit filters to be used with optimized kernels in TfLite for depthwise_conv and fully_connected ops -test for correctness by running fully_connected and depthwise_conv in TfLite and TFLM Corresponding g3 cl - [cl/504384976](https://critique.corp.google.com/cl/504384976) BUG=[265045979](https://b.corp.google.com/issues/265045979)
-
- 23 11月, 2022 1 次提交
-
-
由 Pauline Sho 提交于
BUG=b/250680652 This PR adds INT4 filter support and tests for DepthwiseConv and FullyConnected operators.
-
- 27 10月, 2022 1 次提交
-
-
由 Måns Nilsson 提交于
Adding new download of CMSIS-NN since it is moving to its own repository. Also updates some lint errors. BUG=CMSIS-NN is moving to its own repo
-
- 27 9月, 2022 1 次提交
-
-
由 hmogensen-arm 提交于
Add check that input and output tensors with int16 have offset zero BUG=Fixes https://github.com/tensorflow/tflite-micro/issues/1364
-
- 21 9月, 2022 1 次提交
-
-
由 Vamsi Krishna Manchala 提交于
This PR updates remainder of the TFLM examples, all the kernels and integration tests to remove the usage of ErrorReporter as per the changes made to the TFLM Framework API in https://github.com/tensorflow/tflite-micro/pull/1415; replaces TF_LITE_REPORT_ERROR with MicroPrintf. BUG=http://b/192091017, http://b/245802069
-
- 04 8月, 2022 1 次提交
-
-
由 Steven Toribio 提交于
-
- 22 7月, 2022 1 次提交
-
-
由 felix-johnny 提交于
Bias is optional and using GetTensorData() will result in an ASSERT as it does not handle NULL pointers. GetOptionalTensorData API is used instead. BUG=CMSIS-NN fix for b/232005813 Change-Id: If7ecbaaccab12bdc7f2944b0adad64a8e9cfdb97
-
- 12 5月, 2022 1 次提交
-
-
由 Måns Nilsson 提交于
* Quantization specific registration for CMSIS-NN Adds int8 and int16x8 specific registrations for depthwise conv kernel. Change-Id: I649c65f642777b310318cbb535bec69e41d20314 * CMSIS-NN: Initialize common DW conv parameters in macro * Switch from macro to function * Fix automatic merge issue Co-authored-by: Nmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
-
- 11 5月, 2022 1 次提交
-
-
由 Måns Nilsson 提交于
Change-Id: I5d52a728dbb22a3bf838834948e4f0cf8fa6ba41 Co-authored-by: Nmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
-
- 04 5月, 2022 1 次提交
-
-
由 Pauline Sho 提交于
* Enable -Wmissing-field-initializers and update all registration references In https://github.com/tensorflow/tflite-micro/pull/1082/, we disabled the compiler error as a workaround for a successful upstream sync from TFLite. This PR re-enables the error after addressing all errors. A new `RegisterOp` API is added, and all prior TfLiteRegistration struct initializations are updated to use the new API. At the minimum, this ensures that such additions in future will only require an update to RegisterOp if TFLM doesn't use that field. BUG=b/230507399 * Added new RegisterOpWithFree for LSTM * Remove LSTM Free * Changed inline to normal function to save code size * Changed inline to normal function to save code size * Replace cmsis_nn static initialization with RegisterOp * Removed extra code * Add dropped namespace in hard_swish
-
- 02 2月, 2022 1 次提交
-
-
由 deqiangc 提交于
Replace (almost) all kernel's GetInput/GetOutput with AllocateTempXXx and DeallocateTempXxx micro context api (#894) * Replace GetInput/GetOutput with micro context api * Replace GetInput/GetOutput in kernels with micro_context api. Ther are three kernels (strided_slice, squeeze, transpose)that are not changed yet because: they put the returned value of GetInput/GetOutput in an OpData structure that is persistent. It is better to have separate change to opdata of those kernels * Fix corner case in pad * Fix cmsis-nn * Fix xtensa, cmsis_nn, hexagon
-
- 28 1月, 2022 1 次提交
-
-
由 Måns Nilsson 提交于
Change-Id: I5a55e436110321adb0133bf85c1ba22e20187cc3
-
- 31 12月, 2021 1 次提交
-
-
由 Måns Nilsson 提交于
* Removes calls to reference kernel function in depthwise and conv kernels. * Updates downloaded CMSIS version. * Fix bug in prepare for depthwise where dilation was not set in call to get buffer size. Change-Id: Ida0f0cf9051a30225bf4ea67647e627fdfb163cb Co-authored-by: Nmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
-
- 09 6月, 2021 1 次提交
-
-
由 Måns Nilsson 提交于
* Revert "Revert: PR #48758: TFLM: Remove uint8 support for CMSIS-NN kernels" This reverts commit 6d8a184710164c7bcc41d3bd29fe4ef46836b6c9. * TFLM: Increase stack size for bluepill Change-Id: Ie278c6fff55cc620104c69167273a92a2d8e639a * Update PPD unit test * Remove leftovers from when PPD supported dynamic output dimensions. * Correct number of output elements. * Correct number of input elements for last unit test. Change-Id: I66fd36d7eb48816986450033bc83c6b240d559b6 * Revert "TFLM: Increase stack size for bluepill" This reverts commit c7fc2a0e0f16d2ab10c44389033822503c178e69. With the fix to the PPD unit test from 6e39d12d7688143bd17acb2c5d422385baef9e0f, increasing the bluepill stack size should not be necessary. * Fix circular buffer formatting. The CI check for clang-format needs to be fixed. Co-authored-by: NAdvait Jain <advaitjain@google.com> Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com>
-
- 10 4月, 2021 1 次提交
-
-
由 Advait Jain 提交于
Confirmed that the following command passes: ``` ./tensorflow/lite/micro/tools/ci_build/test_all_new.sh GITHUB_PRESUBMIT ```
-