rockzhan 1187a7fa34 Merge pull request #11649 from rockzhan:dnn_dw_prelu ... dnn: Fix output mismatch when forward dnn model contain [depthwise conv(group=1) + bn + prelu] (#11649) * this can make sure [depthwise conv(group=1) + bn + prelu] output not shift * add TEST to show the output mismatch in [DWconv+Prelu] * fix typo * change loading image to init cvMat directly * build runtime model, without loading external model * remove whitespace * change way to create a cvmat * add bias_term, add target output * fix [dwconv + prelu] value mismatch when no optimizations * fix Test error when change output channels * add parametric test * change num_output to group value * change conv code and change test back		2018-06-07 13:45:54 +00:00
..
caffe	Fuse multipliers but not convolution layers weights	2018-05-10 19:24:38 +03:00
darknet	Added ResizeBilinear op for tf (#11050)	2018-06-07 16:29:04 +03:00
layers	Merge pull request #11649 from rockzhan:dnn_dw_prelu	2018-06-07 13:45:54 +00:00
ocl4dnn	fix doc.	2018-06-03 17:44:24 +08:00
opencl	make ocl4dnn available to run on other platform than Intel GPU	2018-05-29 19:18:10 +09:00
tensorflow	Added ResizeBilinear op for tf (#11050)	2018-06-07 16:29:04 +03:00
torch	fix doc.	2018-06-03 17:44:24 +08:00
dnn.cpp	Wrap Inference Engine init to try-catch	2018-06-07 12:55:52 +03:00
halide_scheduler.cpp	fix doc.	2018-06-03 17:44:24 +08:00
halide_scheduler.hpp
init.cpp	Added ResizeBilinear op for tf (#11050)	2018-06-07 16:29:04 +03:00
nms.cpp	Return a convex hull from rotatedRectangleIntersection	2018-05-18 14:20:17 +03:00
nms.inl.hpp	dnn: add an accuracy test for NMS	2017-10-25 13:40:56 +03:00
op_halide.cpp	core: added MatSize::dims() method	2018-04-27 16:57:29 +03:00
op_halide.hpp	dnn: apply CV_OVERRIDE/CV_FINAL	2018-03-28 18:43:27 +03:00
op_inf_engine.cpp	Wrap Inference Engine init to try-catch	2018-06-07 12:55:52 +03:00
op_inf_engine.hpp	Fix multiple networks with Intel's Inference Engine backend	2018-06-01 14:10:32 +03:00
precomp.hpp	dnn fp16 support	2018-05-16 22:44:39 +08:00