diff options
| author | Guo, Yejun <yejun.guo@intel.com> | 2019-04-25 10:14:33 +0800 |
|---|---|---|
| committer | Pedro Arthur <bygrandao@gmail.com> | 2019-05-08 12:33:00 -0300 |
| commit | 25c1cd909fa6c8b6b778dc24192dc3ec780324b0 (patch) | |
| tree | b428c01522b2935d0b6af414580edcdf39370093 /libavformat/voc_packet.c | |
| parent | 7adfb6132e0823de06f92ecbcb485eeb4260d407 (diff) | |
| download | ffmpeg-25c1cd909fa6c8b6b778dc24192dc3ec780324b0.tar.gz | |
libavfilter/dnn: support multiple outputs for tensorflow model
some models such as ssd, yolo have more than one output.
the clean up code in this patch is a little complex, it is because
that set_input_output_tf could be called for many times together
with ff_dnn_execute_model_tf, we have to clean resources for the
case that the two interfaces are called interleaved.
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
Diffstat (limited to 'libavformat/voc_packet.c')
0 files changed, 0 insertions, 0 deletions