mirror of
https://github.com/apache/nuttx-apps.git
synced 2026-10-04 12:48:20 +00:00
00b6e59123
The tflm tool could only allocate a model: it knew nine operators, ran Invoke() on uninitialized input, and never printed the result. The 64 KB MicroProfiler also lived on the 4 KB task stack. Register the operators a model uses (about 90 builtins), verify the file with the FlatBuffers verifier, and add: -I print operators, input/output tensors and arena usage -d comma separated input values, quantized automatically -x raw input tensor file -n repeat inference and print the average Invoke() time Outputs are printed dequantized with argmax. Inputs are restored before every run because the planner may reuse their buffers. The resolver, profiler and interpreter are allocated on the heap. Signed-off-by: Abhishek Mishra <mishra.abhishek2808@gmail.com> |
||
|---|---|---|
| .. | ||
| operators/neon | ||
| .gitignore | ||
| 0001-dequantize-int8.patch | ||
| 0002-quantize-int8.patch | ||
| 0003-mean-int8.patch | ||
| 0004-tflite-add-extern-C-to-main-function-to-avoid-c-mang.patch | ||
| CMakeLists.txt | ||
| Kconfig | ||
| Make.defs | ||
| Makefile | ||
| tflite-micro.patch | ||
| tflm_syslog.cc | ||
| tflm_tool.cc | ||