Kohei Yoshida 3bcff7f941 Make use of explicit output shape for the de-convolution layer. ... This is relevant to cases where the net is loaded from an ONNX model containing ConvTranspose layers, which may include the output_shape attribute. c.f. https://github.com/onnx/onnx/blob/master/docs/Operators.md#ConvTranspose		2019-03-26 10:46:09 -04:00
..
cmake/hooks	dnn: make OpenCL DNN code optional	2018-03-01 12:12:40 +03:00
include/opencv2	Batch normalization in training phase from Torch	2018-12-21 14:36:55 +03:00
misc	dnn(tensorflow): re-generate files using protoc	2018-09-12 21:33:45 +03:00
perf	Make Inference Engine R3 as a minimal supported version	2019-02-21 09:32:26 +03:00
src	Make use of explicit output shape for the de-convolution layer.	2019-03-26 10:46:09 -04:00
test	Extend LRN layer support with IE backend	2019-03-25 12:53:34 +03:00
CMakeLists.txt	dnn: reduce set of ignored warnings	2018-11-15 13:15:59 +03:00