mirror of
https://github.com/vee1e/tflite-micro.git
synced 2026-09-02 02:07:27 +00:00
0965635467
@tensorflow/micro Set the alternate profiler in the benchmark tool prior to the `Prepare` phase (before calling `MicroInterpreter::AllocateTensors`). This is because the DECODE operator requires the alternate `MicroProfilerInterface` to already be initialized during the `Prepare` phase. Previously the alternate profiler was only required during the `Eval` phase with the legacy compression code. This fix does not change the functionality of the benchmark tool with respect to the legacy compression. bug=#3628 |
||
|---|---|---|
| .. | ||
| benchmarking | ||
| ci_build | ||
| dev_setup | ||
| gen_micro_mutable_op_resolver | ||
| github/arm | ||
| make | ||
| metrics | ||
| project_generation | ||
| BUILD | ||
| generate_cc_arrays.py | ||
| generate_test_for_model.py | ||
| layer_by_layer.cc | ||
| layer_by_layer_debugger.py | ||
| layer_by_layer_schema.fbs | ||
| layer_by_layer_schema_generated.h | ||
| Makefile.inc | ||
| model_transforms_utils.py | ||
| requantize_flatbuffer.py | ||
| requantize_flatbuffer_test.py | ||
| requantize_flatbuffer_utils.py | ||
| tflite_flatbuffer_align.py | ||
| tflite_flatbuffer_align_wrapper.cc | ||
| tflm_model_transforms.py | ||
| tflm_model_transforms_lib.py | ||
| tflm_model_transforms_test.py | ||