1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-11-21 10:55:51 +02:00
FFmpeg/tools/python
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
..
convert_from_tensorflow.py dnn: add tf.nn.conv2d support for native model 2019-10-30 10:31:55 -03:00
convert_header.py dnn: add tf.nn.conv2d support for native model 2019-10-30 10:31:55 -03:00
convert.py convert_from_tensorflow.py: add option to dump graph for visualization in tensorboard 2019-08-15 14:58:19 -03:00