[nnpackge_tools] introduce gen_golden.py (#8719)
author이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 <sg5.lee@samsung.com>
Tue, 5 Nov 2019 08:12:30 +0000 (17:12 +0900)
committer오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 <hseok82.oh@samsung.com>
Tue, 5 Nov 2019 08:12:30 +0000 (17:12 +0900)
commit13a39fae36bb4323b3460549e8b49a3beabe621f
treef33f63ef9662efc4733cf3aebac2a6cf9262211f
parent1f37278d72fc65f853351adfcf2ad77dd7796360
[nnpackge_tools] introduce gen_golden.py (#8719)

It introduces `gen_golden.py` tool.
You can generate golden data with

```
$ gen_golden.py -o out_dir /your/path/to/pb
```

Then, you will get out_dir/{input,expected}.h5.

No need to specify inputs and outputs.
No need to build nncc.

Prerequisite: tensorflow running environment.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
tools/nnpackage_tool/gen_golden/README.md [new file with mode: 0644]
tools/nnpackage_tool/gen_golden/gen_golden.py [new file with mode: 0644]