projects / platform / core / ml / nntrainer.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 6c9e746) | patch
[Conv2d] Conv2d Padding Fix
authorJihoon Lee <jhoon.it.lee@samsung.com>
Wed, 15 Sep 2021 01:54:54 +0000 (10:54 +0900)
committerJijoong Moon <jijoong.moon@samsung.com>
Wed, 15 Sep 2021 10:04:19 +0000 (19:04 +0900)
commit334e5f865edfb0c6f3eff35f426b62c91dc11b06
treebd1146f91c9a273d252f8c9b6fdd23ed1d683b5etree | snapshot
parent6c9e746fd70200d1ecff60b84b7178d6aa2164d6commit | diff
[Conv2d] Conv2d Padding Fix

This patch resolves conv2d calculation is crooked in some cases

**Changes proposed in this PR:**
- Conv2d Fix
- Padding::Compute Fix
- Pooling2d Fix

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

Co-authored-by: Parichay Kapoor <pk.kapoor@samsung.com>
Signed-off-by: Jihoon Lee <jhoon.it.lee@samsung.com>
nntrainer/layers/common_properties.cpp diff | blob | history
nntrainer/layers/common_properties.h diff | blob | history
nntrainer/layers/conv2d_layer.cpp diff | blob | history
nntrainer/layers/pooling2d_layer.cpp diff | blob | history
test/unittest/unittest_common_properties.cpp diff | blob | history
Domain: Machine Learning / ML Framework;