diff options
| author | Guo, Yejun <yejun.guo@intel.com> | 2019-07-30 09:26:18 +0800 |
|---|---|---|
| committer | Pedro Arthur <bygrandao@gmail.com> | 2019-08-15 14:58:19 -0300 |
| commit | ddd92ba2c6c6d0b5f3d5b4496ab07fbcf73b58a2 (patch) | |
| tree | 2a4b84aec32039c973241eddd187426fa5611a16 /doc/examples/encode_audio.c | |
| parent | 2c01434d60dbc607076a34d129e93a3585cbb277 (diff) | |
| download | ffmpeg-ddd92ba2c6c6d0b5f3d5b4496ab07fbcf73b58a2.tar.gz | |
convert_from_tensorflow.py: support conv2d with dilation
conv2d with dilation > 1 generates tens of nodes in graph, it is not
easy to parse each node one by one, so we do special tricks to parse
the conv2d layer.
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
Diffstat (limited to 'doc/examples/encode_audio.c')
0 files changed, 0 insertions, 0 deletions