projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 5dbedf5) | patch
[exo/tflite] Export Tensors after Allocation (#4199)
author박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 <jh1302.park@samsung.com>
Fri, 12 Jul 2019 05:13:09 +0000 (14:13 +0900)
committerGitHub Enterprise <noreply-CODE@samsung.com>
Fri, 12 Jul 2019 05:13:09 +0000 (14:13 +0900)
commit776f7ceea4c2123f6da7e9e1571243db16342d28
treedd25a9198337582f5248373d69a8af72a9aaf229tree | snapshot
parent5dbedf5884caec4ee8ac5eacd9bcc59f1e0ba798commit | diff
[exo/tflite] Export Tensors after Allocation (#4199)

This commit rewrites exportOpDefinedTensors as a 2-stage function. Now,
exportOpDefinedTensors first allocates a T/F Lite tensor first, and then
export allocated T/F Lite tensors.

The first phase iterates over loco nodes, but the second phase now
iterates over allocated T/F Lite tensors.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
contrib/exo-tflite/src/TensorExporter.cpp diff | blob | history
Domain: Machine Learning / ML Framework;