diff options
| author | Guo, Yejun <yejun.guo@intel.com> | 2019-10-21 20:38:03 +0800 |
|---|---|---|
| committer | Pedro Arthur <bygrandao@gmail.com> | 2019-10-30 10:31:55 -0300 |
| commit | dff39ea9f0154ec52b7548b122a4a5332df3c2c6 (patch) | |
| tree | a435c8d24d80bc9c38ecd4b93c51113c47acad05 /tools/python/convert_header.py | |
| parent | a269fa044b1364af1654456c33b7d45407822876 (diff) | |
| download | ffmpeg-streaming-dff39ea9f0154ec52b7548b122a4a5332df3c2c6.zip ffmpeg-streaming-dff39ea9f0154ec52b7548b122a4a5332df3c2c6.tar.gz | |
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>
Diffstat (limited to 'tools/python/convert_header.py')
| -rw-r--r-- | tools/python/convert_header.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/tools/python/convert_header.py b/tools/python/convert_header.py index 3c2acd5..67672b2 100644 --- a/tools/python/convert_header.py +++ b/tools/python/convert_header.py @@ -20,7 +20,7 @@ str = 'FFMPEGDNNNATIVE' # increase major and reset minor when we have to re-convert the model file -major = 0 +major = 1 # increase minor when we don't have to re-convert the model file -minor = 2 +minor = 0 |
