- 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
-
- 19 11月, 2022 1 次提交
-
-
由 Vamsi Krishna Manchala 提交于
This PR will introduce tflite_bridge to hide MicroErrorReporter usage. BUG=[b/256646180](http://b/256646180)
-
- 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
-
- 30 8月, 2022 1 次提交
-
-
由 Steven Toribio 提交于
-
- 21 7月, 2022 1 次提交
-
-
由 Steven Toribio 提交于
* in kernal reinfornced the buffers apis that are availible as described in micro_interpreter.cc * fixing github style presubmit error * fixing github style presubmit error * fixing github style presubmit error * fixing github style presubmit error * fixing github style presubmit error * undoing change to line 101 kernal runner that was unintentional * fixed compilation issues * cleaning up some not needed lines * style fix * fixing x86 coredump : * x86 comple error revert * testing change * testing change * testing change * testing change * testing change * making changes more readable * style fix * style fix * style fix * style fix * style fix * final changes * bufferapi method setup * fixing scope issue for bufferapi setup function * testing changes * testing change\ * testing change\ * implement clearBufferAPI function * fixed clearBufferApi addition * fixing kernal runner * fixing kernal runner * fixing kernal runner * fixing kernal runner * fixing kernal runner * last check * last check * last check * last check * last check * testing * enum no longer needed * changing naming convention for c++ style * making sure it matches google3 changes * class is named something different on g3 had to change back * fixing style error Co-authored-by: Nmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
-
- 08 7月, 2022 1 次提交
-
-
由 deqiangc 提交于
* Rename the SimpleMemorAllocator to the more informative SingleArenaBufferAllocator * Rename RecordingSimpleMemoryAllocator to RecordingSingleArenaBufferAllocator * Fix Makefile * Format fix
-
- 26 4月, 2022 1 次提交
-
-
由 deqiangc 提交于
* Move simple_memory_allocator to a new folder * Fix makefile system * Fix format * Fix a typo in Makefile that cause project generation failure Co-authored-by: Nmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
-
- 20 4月, 2022 1 次提交
-
-
由 Ting Yan 提交于
Co-authored-by: Nmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
-
- 02 3月, 2022 1 次提交
-
-
由 deqiangc 提交于
* Ensure all allocate temp must be paired with decallocate After this CL, there will be an error if not all temp buffers are freed before ResetTempAllocations(). This is a way to enforce the TFLM's new paradigm: all AllocateTempXxx must be paired with DeallocateTemp() for better tracking of buffers. See go/tflm-pairing-allocatetemp-with-deallocatetemp for more info * Enable kernel runner check Co-authored-by: NNat Jeffries <natmjeffries@gmail.com>
-
- 04 2月, 2022 2 次提交
-
-
由 deqiangc 提交于
Temporarily disable the global default enforcement of pairing of AllocateTempXxx/DeallocateTemp (#908) * Temporarily disable the global enforcement of pairing of AllocateTemp/DeallocateTempXxx Temporarily disable the global enforcement of pairing of AllocateTemp/DeallocateTempXxx because there are some internal test that is using KernelRunner. BUG=https://b/217818824 * Disable default global enforcing of pair of AllocateTempXxx/DeallocateTemp * Revert xtensa svdf change
-
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
-
- 28 1月, 2022 1 次提交
-
-
由 deqiangc 提交于
Add AllocateTempInputTensor to replace GetInput() and Add AllocateTempOutputTensor to replace GetOutput() (#885) This corresonds to internal cl/424648139 Add more informative api AllocateTempInputTensor to replace GetInput() and AllocateTempOutputTensor to replace GetOutput(). These two new API call out the fact that what GetInput and GetOutput returns are in temporary buffer and need to call DeallocateTempTensor() afterwards. IF operator is the first OP to use these APIs. BUG=https://b/209453859Co-authored-by: Nmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
-
- 08 1月, 2022 1 次提交
-
-
由 deqiangc 提交于
* Prototype for MicroContext * MicroContext. We need a MockMicroContext for test to pass * Use virtual method so that mock directly return graph and also avoid virtual delete * Format fix * Address review comments directly calling micro context api instead of through a wrapper in kernel_util part of interpreter test is now micro_context_test; store reference instead of pointer; * Add todo * Add the new micro_context_test to MICROLITE_TEST target. This fix the test_generation failure on github presubmit * Use free function instead of static function inside micro_context for current existing api * Format fix * Remove static function from fake MicroContext. Have to use MicroErrorReport instead of MicroPrintf for error report. * Improve doc style * Fixing mysterious segmentation fault * Change graph in MicroContext to be reference and other changes such as using asssor function naming pattern
-
- 19 11月, 2021 1 次提交
-
-
由 deqiangc 提交于
-
- 19 5月, 2021 1 次提交
-
-
由 TFLM-bot 提交于
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 ```
-