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

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

author	Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 <s.barannikov@samsung.com>
	Thu, 17 Jan 2019 08:36:29 +0000 (11:36 +0300)
committer	Efimov Alexander/AI Tools Lab/./Samsung Electronics <a.efimov@samsung.com>
	Thu, 17 Jan 2019 08:36:29 +0000 (11:36 +0300)
commit	e1bf2aa982c87b1a443b1742a592890c44b459f2
tree	96e090551c12a608253c6dc33a655bbb53bfa4a5	tree \| snapshot
parent	ddeabab0ce9dfd6d8c86931c5c42f2e95d761f35	commit \| diff

[nnc] Make convolution operations treat the second tensor as ordinary argument (#2869)

* Change the signatures of Conv2DOp, DepthwiseConv2DOp and DeConv2DOp to identically handle both input parameters.
* Refactor uses of Conv2DOp, DepthwiseConv2DOp and DeConv2DOp.
* Rename corresponding files in interpreter backend according to coding style.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>

34 files changed:

contrib/nnc/core/modelIR/IrDotDumper.cpp		diff \| blob \| history
contrib/nnc/core/modelIR/ir_dot_node_info.cpp		diff \| blob \| history
contrib/nnc/core/modelIR/operations/Conv2DOp.cpp		diff \| blob \| history
contrib/nnc/core/modelIR/operations/DeConv2DOp.cpp		diff \| blob \| history
contrib/nnc/core/modelIR/operations/DepthwiseConv2DOp.cpp		diff \| blob \| history
contrib/nnc/include/core/modelIR/ir_dot_node_info.h		diff \| blob \| history
contrib/nnc/include/core/modelIR/operations/Conv2DOp.h		diff \| blob \| history
contrib/nnc/include/core/modelIR/operations/Deconv2DOp.h		diff \| blob \| history
contrib/nnc/include/core/modelIR/operations/DepthwiseConv2DOp.h		diff \| blob \| history
contrib/nnc/passes/acl_soft_backend/AclCppOpGenerator.cpp		diff \| blob \| history
contrib/nnc/passes/caffe2_frontend/caffe2_op_creator.cpp		diff \| blob \| history
contrib/nnc/passes/caffe_frontend/caffe_op_creator.cpp		diff \| blob \| history
contrib/nnc/passes/interpreter/Interpreter.cpp		diff \| blob \| history
contrib/nnc/passes/interpreter/ops/Conv2D.cpp	[moved from contrib/nnc/passes/interpreter/ops/conv_2D.cpp with 92% similarity]	diff \| blob \| history
contrib/nnc/passes/interpreter/ops/Conv2D.h	[moved from contrib/nnc/passes/interpreter/ops/conv_2D.h with 81% similarity]	diff \| blob \| history
contrib/nnc/passes/interpreter/ops/DeConv2D.cpp		diff \| blob \| history
contrib/nnc/passes/interpreter/ops/DeConv2D.h		diff \| blob \| history
contrib/nnc/passes/interpreter/ops/DepthwiseConv2D.cpp	[moved from contrib/nnc/passes/interpreter/ops/Depthwise_conv_2D.cpp with 86% similarity]	diff \| blob \| history
contrib/nnc/passes/interpreter/ops/DepthwiseConv2D.h	[moved from contrib/nnc/passes/interpreter/ops/Depthwise_conv_2D.h with 72% similarity]	diff \| blob \| history
contrib/nnc/passes/interpreter/ops/conv_FFT.cpp		diff \| blob \| history
contrib/nnc/passes/interpreter/ops/conv_FFT.h		diff \| blob \| history
contrib/nnc/passes/onnx_frontend/ONNXImporterImpl.cpp		diff \| blob \| history
contrib/nnc/passes/onnx_frontend/ONNXOpCreator.cpp		diff \| blob \| history
contrib/nnc/passes/soft_backend/ModelAnalyzer.cpp		diff \| blob \| history
contrib/nnc/passes/soft_backend/SBSerializer.cpp		diff \| blob \| history
contrib/nnc/passes/soft_backend/code_snippets/cpp_operations.def		diff \| blob \| history
contrib/nnc/passes/tflite_frontend/tflite_op_creator.cpp		diff \| blob \| history
contrib/nnc/tests/interpreter/gen/gen_test_data.py		diff \| blob \| history
contrib/nnc/tests/interpreter/graph_creator.cpp		diff \| blob \| history
contrib/nnc/tests/interpreter/op_info_util.cpp		diff \| blob \| history
contrib/nnc/tests/interpreter/op_info_util.h		diff \| blob \| history
contrib/nnc/tests/interpreter/test_data/test_description.txt		diff \| blob \| history
contrib/nnc/unittests/acl_backend/MIRToDOM.cpp		diff \| blob \| history
contrib/nnc/unittests/soft_backend/CPPOperations.cpp		diff \| blob \| history

Domain: Machine Learning / ML Framework;

RSS Atom