projects / platform / core / ml / nntrainer.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 0328879) | patch
[Layer] Improve forwarding logic of ConcatLayer
authorDonghyeon Jeong <dhyeon.jeong@samsung.com>
Thu, 8 Aug 2024 08:27:20 +0000 (17:27 +0900)
committerJijoong Moon <jijoong.moon@samsung.com>
Mon, 12 Aug 2024 01:23:22 +0000 (10:23 +0900)
commit3b11453bde0c6743c776c5f7f021e31ed074e82c
treefca5d4b677d3d64d0386d217b31db61e702eded0tree | snapshot
parent0328879fede8554c88872dc9fd0c3c6d0e4fe0f9commit | diff
[Layer] Improve forwarding logic of ConcatLayer

This PR updates current ConcatLayer forwarding for faster computation.

**Changes proposed in this PR:**
- Utilize the Tensor::concat() operation to perform forwarding and replace manual mapping and copying.

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

Signed-off-by: Donghyeon Jeong <dhyeon.jeong@samsung.com>
nntrainer/layers/concat_layer.cpp diff | blob | history
Domain: Machine Learning / ML Framework;