review.tizen.org Git - platform/core/ml/nnfw.git/commit

projects / platform / core / ml / nnfw.git / commit

author	김수진/동작제어Lab(SR)/Engineer/삼성전자 <sjsujin.kim@samsung.com>
	Fri, 13 Jul 2018 07:10:12 +0000 (16:10 +0900)
committer	오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 <hseok82.oh@samsung.com>
	Fri, 13 Jul 2018 07:10:12 +0000 (16:10 +0900)
commit	827eea250e2c8b15fef841b3b3911edce4339fa7
tree	d238b7249cca2018ac3fbf4cbc9ad75f87443380	tree \| snapshot
parent	47496db0bd56eef62343c3eae7fd6b4b3d9fdca1	commit \| diff

[newrt] Implement FullyConnected kernel for CPU (#1943)

* [newrt] Implement FullyConnected kernel for CPU

This commit implements FullyConnected kernel for CPU in new runtime.

- Other jobs
  - Add getNumberOfElements
  - Add zeroPoint(offset)
  - Add QuantizeMultiplierSmallerThanOne, GetQuantizedConvolutionMultipler

Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
* Add TODO, Add weight/bias for quant8_asymm

* Add comment for GetQuantizedConvolutionMultipler

Domain: Machine Learning / ML Framework;

RSS Atom

runtimes/new_runtime/src/internal/Model.h		diff \| blob \| history
runtimes/new_runtime/src/internal/cpu/InitializerGenerator.cc		diff \| blob \| history
runtimes/new_runtime/src/internal/cpu/StageGenerator.cc		diff \| blob \| history
runtimes/new_runtime/src/internal/kernels/cpufallback/FullyConnectedLayer.cc	[new file with mode: 0644]	blob
runtimes/new_runtime/src/internal/kernels/cpufallback/FullyConnectedLayer.h	[new file with mode: 0644]	blob
runtimes/new_runtime/src/internal/kernels/cpufallback/OperationUtils.cc		diff \| blob \| history
runtimes/new_runtime/src/internal/kernels/cpufallback/OperationUtils.h		diff \| blob \| history
runtimes/new_runtime/src/internal/nnapi/kernel/Reader.h		diff \| blob \| history
runtimes/new_runtime/src/model.cc		diff \| blob \| history