Christof Petig
Christof Petig
I just found that Register_CONV_2D,QUANTIZE,FULLY_CONNECTED,SOFTMAX,DEPTHWISE_CONV_2D are not declared in micro_ops.h I need to figure out how to fix the examples! PS: Sorry, I did not fall off the edge of...
This issue contains discussion about potential long term improvements of the compiler
See https://github.com/tensorflow/tensorflow/commit/fb5f4a4a67fb2f4922d85b59923172da61f19729 this sounds genuinely interesting!
Dear Rafael, I thought more about reshape operators (and their kind), what if ... if an operator's output has the same size as its first input and this input is...
Add comments to help debugging/understanding the generated code (was: Annotations missing in devel)
in devel the comments are gone (which inputs and outputs are used for each invoke call), also it is no longer visible which operation is called (fix by defining and...
Custom libraries might define operators which are known to tensorflow lite, but not lite micro. This will omit declaring the Register function (which is missing from micro_ops.h) and will also...
On some platforms or with some optimizations tensors need to be 8 to 16 byte aligned. This should be configurable in a central place (#define). Maybe a different alignment for...
E.g. dimensions, opdata in Alex' example https://github.com/alxhoff/STM3240G-EVAL-TensorFlow-Hello-World/blob/compiler/Src/sine.cpp Sharing these data structures (when identical) will reduce the code size of the compiled binary (especially helpful for low dimensional models).
some ti compilers and gcc provide the option to not zero bss to speed up boot time on embedded hardware __attribute__ ((section (".noinit"))) Provide an option to zero all of...
I have been working on a C++ bindings generator in a fork at https://github.com/cpetig/wit-bindgen for some time. After a rewrite the code is less clumsy and could be considered for...