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
..
api	tests/api/api-h264-test: Add AV_NOPTS_VALUE check for AVFrame.pkt_dts/pts	2019-02-12 22:28:15 +08:00
checkasm	checkasm/vf_eq: add test for vf_eq	2019-09-26 08:10:31 +08:00
dnn	dnn: add tf.nn.conv2d support for native model	2019-10-30 10:31:55 -03:00
fate	avfilter/af_silencedetect: use AV_OPT_TYPE_DURATION	2019-10-21 15:42:04 +05:30
filtergraphs	lavfi/concat: allow to support inputs with different frame rates	2019-09-08 16:48:28 +02:00
ref	avcodec/cavsdec: Set ret on errors in decode_pic()	2019-10-17 13:17:18 +02:00
.gitignore
audiogen.c	tests/audiogen: raise channel count limit to 12	2018-07-30 10:46:10 +02:00
audiomatch.c
base64.c
copycooker.sh
extended.ffconcat
fate-run.sh	tests: Fix bash errors in lavf_container tests.	2019-09-09 18:16:06 +02:00
fate-valgrind.supp
fate.sh
Makefile	fate: add unit test for dnn-layer-pad	2019-07-29 12:34:19 -03:00
md5.sh
refcmp-metadata.awk
reference.pnm
rotozoom.c
simple1.ffconcat
simple2.ffconcat
test.ffmeta
tiny_psnr.c
tiny_ssim.c
utils.c
videogen.c