Guo, Yejun dff39ea9f0 dnn: add tf.nn.conv2d support for native model ... Unlike other tf.*.conv2d layers, tf.nn.conv2d does not create many nodes (within a scope) in the graph, it just acts like other layers. tf.nn.conv2d only creates one node in the graph, and no internal nodes such as 'kernel' are created. The format of native model file is also changed, a flag named has_bias is added, so change the version number. Signed-off-by: Guo, Yejun <yejun.guo@intel.com> Signed-off-by: Pedro Arthur <bygrandao@gmail.com>		2019-10-30 10:31:55 -03:00
..
.gitignore	FATE/dnn: add .gitignore	2019-10-23 09:58:17 -03:00
dnn-layer-conv2d-test.c	dnn: add tf.nn.conv2d support for native model	2019-10-30 10:31:55 -03:00
dnn-layer-depth2space-test.c	avfilter/dnn: unify the layer execution function in native mode	2019-10-15 18:56:25 -03:00
dnn-layer-maximum-test.c	FATE/dnn: add unit test for layer maximum	2019-09-20 10:57:23 -03:00
dnn-layer-pad-test.c	FATE/dnn: fix stack buffer overflow	2019-10-04 09:58:22 -03:00
Makefile	FATE/dnn: add unit test for layer maximum	2019-09-20 10:57:23 -03:00