- 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
-
- 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
-
- 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
-
- 04 2月, 2022 1 次提交
-
-
由 deqiangc 提交于
* Clean up GetInput/GetOutput api usage in squeeze, transpose, strided_slice op Clean up api usage in squeeze, transpose, strided_slice op by replacing GetInput/GetOutput with AllocateTempXXX/DeallocateTempXXX in micro context api in squeeze, transpose, strided_slice op Additionally, squeeze and transpose is using TfLiteTensor in Invoke, which is againts the recommendation and unnecessary. Replace them with the usage of TfLiteEvalTensor. This is a continuation of pr #894 to improve both readability and safety of getting tensors. The next step is to clean the GetInput/GetOutput in test_helpers.cc before enforcing the pair of AllocateTempXXX and DeallocateTemp globally. BUG=https://b/209453859 * Fix bluepill test: need to explictly use int32_t so that the right templated typeToTfLiteType is chosen and return the right type * Remove redundant include * Clean GetInput/GetOutput api usage in test_helpers * Enforce the pairing of AllocateTemp/DeallocateTemp for all kernel tests * Fix svdf/full_connected in cmsis_nn variant and conv in xtensa variant * Fix xtensa * Fix depthwise_conv in xtensa * Fix xtensa again * Fix compilation. Xtensa local test pass * Fix xtensa/full_connected not showing up locally * update cmsis_nn svdf * Fix pooling for hifi5 * hif5 errors seen only on server * Fix hifi5 again
-
- 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
-
- 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 ```
-