@@ -10162,6 +10162,9 @@ The label id is considered as name if the label file is not provided.
@item options
Set the configs to be passed into backend
+For tensorflow backend, you can set its configs with @option{sess_config} options,
+please use tools/python/tf_sess_config.py to get the configs
+
@item async
use DNN async execution if set (default: set),
roll back to sync execution if the backend does not support async.
@@ -10219,6 +10222,9 @@ Set the output name of the dnn network.
@item options
Set the configs to be passed into backend
+For tensorflow backend, you can set its configs with @option{sess_config} options,
+please use tools/python/tf_sess_config.py to get the configs
+
@item async
use DNN async execution if set (default: set),
roll back to sync execution if the backend does not support async.
@@ -10247,9 +10253,10 @@ Handle the Y channel with srcnn.pb (see @ref{sr} filter) for frame with yuv420p
@end example
@item
-Handle the Y channel with espcn.pb (see @ref{sr} filter), which changes frame size, for format yuv420p (planar YUV formats supported):
+Handle the Y channel with espcn.pb (see @ref{sr} filter), which changes frame size, for format yuv420p (planar YUV formats supported), please
+use tools/python/tf_sess_config.py to get the configs for your system.
@example
-./ffmpeg -i 480p.jpg -vf format=yuv420p,dnn_processing=dnn_backend=tensorflow:model=espcn.pb:input=x:output=y -y tmp.espcn.jpg
+./ffmpeg -i 480p.jpg -vf format=yuv420p,dnn_processing=dnn_backend=tensorflow:model=espcn.pb:input=x:output=y:options=sess_config=0x10022805320e09cdccccccccccec3f20012a01303801 -y tmp.espcn.jpg
@end example
@end itemize
@@ -18914,6 +18921,9 @@ its format.
@item options
Set the configs to be passed into backend
+For tensorflow backend, you can set its configs with @option{sess_config} options,
+please use tools/python/tf_sess_config.py to get the configs.
+
@item scale_factor
Set scale factor for SRCNN model. Allowed values are @code{2}, @code{3} and @code{4}.
Default value is @code{2}. Scale factor is necessary for SRCNN model, because it accepts