chunseoklee

After investigation via web docs, IMHO compilation in coreml is like compilation(nnfw_prepare in nnfw.h) in onert, not on-device compilation for npu. https://github.com/hollance/neural-engine repo shows many details(though they are just guess)....

> "1:10:sqrt" I also have this kind of expression in mind : (subgraph id, tensor idx, strong name) triple. But, it is not clear how to represent the connectivity between...

> circle-partitioner does not support partitioning other sub graphs than 0 (the main). I'm not sure I could develop to support this in this year cause of my schedule. If...

Here is a proposal for connection info spec : - Suppose that Net_Sqrt_Rsqrt_001.part.00001_trix.circle is compiled into tvn named 'Net_Sqrt_Rsqrt_001.part.00001_trix.tvn' - Proposal 1. Tensor : "model idx:subgraph idx:I/O idx" idx triple...

>Q2. Do we need to consider multiple original graphs ? Not for now. My proposal assumes a single original model. For multiple original graph, need to extend it > Q3....

> In "conn", what does "1:0:0" : "0:0:1", mean? "1:0:0" (2nd model's first input as key) comes from "0:0:1" (1st model's second output as value).

Here is a new updated connection info file : ``` { "source" : { "inputs" : [ "0:0:0" ], "outputs" : [ "0:0:1", "1:0:1", "1:0:0" ] }, "conn" : [...

| module | one | tizen | | |---------------------------| --------|-------|---| | ABSEIL | [df3ea785](https://github.com/abseil/abseil-cpp/commits/df3ea785d8c30a9503321a3d35ee7d35808f190d) | [20210324.2](https://github.com/abseil/abseil-cpp/releases/tag/20210324.2) | one uses no tag | | ARMCOMPUTE | | | | | BOOST...

gtest patch : https://github.com/Samsung/ONE/issues/8567

@ragmani FYI, how to check dynamic shape infer on nnpackage_run: ``` adb shell /data/local/Product/out/bin/nnpackage_run /data/local/tmp/model_nnpkg --shape_run="[0,[1,64],3,[1],2,[1,64],1,[1,64,882],4,[1,64]]" --output_sizes="[2,256]" -r 1 -l /data/local/tmp/input.h5 -d /data/local/tmp/output.h5' ```