projects / platform / core / ml / nntrainer.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: dff6f8c) | patch
[ POOLING ] Fix global pooling dimensions
authorjijoong.moon <jijoong.moon@samsung.com>
Mon, 9 Nov 2020 13:01:40 +0000 (22:01 +0900)
committerJijoong Moon <jijoong.moon@samsung.com>
Wed, 11 Nov 2020 03:17:19 +0000 (12:17 +0900)
commit6cacd8bbaa5d85db063edea862d5b6320ef436d6
tree83c52fde0680d2678d5e59d884f27b446bbf5c1dtree | snapshot
parentdff6f8c511429ae44da204a683665f245aabececcommit | diff
[ POOLING ] Fix global pooling dimensions

For the global pooling, we need to set the output dimension on last
dimension, width.

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

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
nntrainer/layers/pooling2d_layer.cpp diff | blob | history
Domain: Machine Learning / ML Framework;