[Recorder] Add Input map generation
authorJihoon Lee <jhoon.it.lee@samsung.com>
Wed, 26 May 2021 12:09:29 +0000 (21:09 +0900)
committerJijoong Moon <jijoong.moon@samsung.com>
Tue, 8 Jun 2021 05:54:30 +0000 (14:54 +0900)
commit6244a6fa6b740b0268e8e6efe8b8d60b35c4c89b
treeffd6996d99ef384cec69fdabfbd16d616cdb04bf
parent31fb804174aa3735171da1b5f64b951bbc54c5ab
[Recorder] Add Input map generation

There was a bug that layer input is directly from the previous layer.
If the model is not sequential, this assumption is not true, making
Addition test fail.

This patch build `model.recoder__input_maps` to correctly locate
 the input tensor with some minor clean ups

**Self evaluation:**
1. Build test: [X]Passed [ ]Failed [ ]Skipped
2. Run test: [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: Jihoon Lee <jhoon.it.lee@samsung.com>
test/input_gen/recorder.py