review.tizen.org Git - platform/upstream/opencv.git/commit

projects / platform / upstream / opencv.git / commit

author	Zihao Mu <zihaomu@outlook.com>
	Tue, 5 Jul 2022 16:14:42 +0000 (00:14 +0800)
committer	GitHub <noreply@github.com>
	Tue, 5 Jul 2022 16:14:42 +0000 (19:14 +0300)
commit	a80fcacd90dec4b2a25faf8363811bc6566b80cd
tree	700b3f5ee229de4285339f265ee1a466af2572fc	tree \| snapshot
parent	16b5fd4bf2368e243bc3296da0ad9aabf67c3420	commit \| diff

Merge pull request #21372 from zihaomu:dnn_quantize_per_tensor

Add per_tensor_quantize to int8 quantize

* add per_tensor_quantize to dnn int8 module.

* change api flag from perTensor to perChannel, and recognize quantize type and onnx importer.

* change the default to hpp

13 files changed:

modules/dnn/include/opencv2/dnn/all_layers.hpp		diff \| blob \| history
modules/dnn/include/opencv2/dnn/dnn.hpp		diff \| blob \| history
modules/dnn/src/int8layers/convolution_layer.cpp		diff \| blob \| history
modules/dnn/src/int8layers/fully_connected_layer.cpp		diff \| blob \| history
modules/dnn/src/layers/convolution_layer.cpp		diff \| blob \| history
modules/dnn/src/layers/fully_connected_layer.cpp		diff \| blob \| history
modules/dnn/src/layers/layers_common.cpp		diff \| blob \| history
modules/dnn/src/layers/layers_common.hpp		diff \| blob \| history
modules/dnn/src/net.cpp		diff \| blob \| history
modules/dnn/src/net_impl.hpp		diff \| blob \| history
modules/dnn/src/net_quantization.cpp		diff \| blob \| history
modules/dnn/src/onnx/onnx_importer.cpp		diff \| blob \| history
modules/dnn/test/test_int8_layers.cpp		diff \| blob \| history

Domain: Multimedia / Media Vision;

RSS Atom