diff options
author | Ting Fu <ting.fu-at-intel.com@ffmpeg.org> | 2023-04-27 17:43:45 +0800 |
---|---|---|
committer | Guo Yejun <yejun.guo@intel.com> | 2023-04-28 11:07:41 +0800 |
commit | a9fb1417192d9922c891315350f96ef0f71726c4 (patch) | |
tree | 546dcde5fb052bf51e83a994b6f54dd19953da3a /doc | |
parent | 7ed6f28a7cee1344f8ae61737cbb8364dec8cb24 (diff) | |
download | ffmpeg-a9fb1417192d9922c891315350f96ef0f71726c4.tar.gz |
lavfi/dnn: Modified DNN native backend related tools and docs.
Will remove native backend, so change the default backend in filters,
and also remove the python scripts which generate native model file.
Signed-off-by: Ting Fu <ting.fu@intel.com>
Diffstat (limited to 'doc')
-rw-r--r-- | doc/filters.texi | 39 |
1 files changed, 4 insertions, 35 deletions
diff --git a/doc/filters.texi b/doc/filters.texi index 5022f96e46..01a71223a1 100644 --- a/doc/filters.texi +++ b/doc/filters.texi @@ -11403,9 +11403,6 @@ See @url{http://openaccess.thecvf.com/content_ECCV_2018/papers/Xia_Li_Recurrent_ Training as well as model generation scripts are provided in the repository at @url{https://github.com/XueweiMeng/derain_filter.git}. -Native model files (.model) can be generated from TensorFlow model -files (.pb) by using tools/python/convert.py - The filter accepts the following options: @table @option @@ -11426,21 +11423,16 @@ Specify which DNN backend to use for model loading and execution. This option ac the following values: @table @samp -@item native -Native implementation of DNN loading and execution. - @item tensorflow TensorFlow backend. To enable this backend you need to install the TensorFlow for C library (see @url{https://www.tensorflow.org/install/lang_c}) and configure FFmpeg with @code{--enable-libtensorflow} @end table -Default value is @samp{native}. @item model Set path to model file specifying network architecture and its parameters. -Note that different backends use different file formats. TensorFlow and native -backend can load files for only its format. +Note that different backends use different file formats. TensorFlow can load files for only its format. @end table To get full functionality (such as async execution), please use the @ref{dnn_processing} filter. @@ -11764,9 +11756,6 @@ Specify which DNN backend to use for model loading and execution. This option ac the following values: @table @samp -@item native -Native implementation of DNN loading and execution. - @item tensorflow TensorFlow backend. To enable this backend you need to install the TensorFlow for C library (see @@ -11782,14 +11771,9 @@ be needed if the header files and libraries are not installed into system path) @end table -Default value is @samp{native}. - @item model Set path to model file specifying network architecture and its parameters. -Note that different backends use different file formats. TensorFlow, OpenVINO and native -backend can load files for only its format. - -Native model file (.model) can be generated from TensorFlow model file (.pb) by using tools/python/convert.py +Note that different backends use different file formats. TensorFlow, OpenVINO backend can load files for only its format. @item input Set the input name of the dnn network. @@ -11816,12 +11800,6 @@ Remove rain in rgb24 frame with can.pb (see @ref{derain} filter): @end example @item -Halve the pixel value of the frame with format gray32f: -@example -ffmpeg -i input.jpg -vf format=grayf32,dnn_processing=model=halve_gray_float.model:input=dnn_in:output=dnn_out:dnn_backend=native -y out.native.png -@end example - -@item Handle the Y channel with srcnn.pb (see @ref{sr} filter) for frame with yuv420p (planar YUV formats supported): @example ./ffmpeg -i 480p.jpg -vf format=yuv420p,scale=w=iw*2:h=ih*2,dnn_processing=dnn_backend=tensorflow:model=srcnn.pb:input=x:output=y -y srcnn.jpg @@ -21878,9 +21856,6 @@ Training scripts as well as scripts for model file (.pb) saving can be found at @url{https://github.com/XueweiMeng/sr/tree/sr_dnn_native}. Original repository is at @url{https://github.com/HighVoltageRocknRoll/sr.git}. -Native model files (.model) can be generated from TensorFlow model -files (.pb) by using tools/python/convert.py - The filter accepts the following options: @table @option @@ -21889,9 +21864,6 @@ Specify which DNN backend to use for model loading and execution. This option ac the following values: @table @samp -@item native -Native implementation of DNN loading and execution. - @item tensorflow TensorFlow backend. To enable this backend you need to install the TensorFlow for C library (see @@ -21899,13 +21871,10 @@ need to install the TensorFlow for C library (see @code{--enable-libtensorflow} @end table -Default value is @samp{native}. - @item model Set path to model file specifying network architecture and its parameters. -Note that different backends use different file formats. TensorFlow backend -can load files for both formats, while native backend can load files for only -its format. +Note that different backends use different file formats. TensorFlow, OpenVINO backend +can load files for only its format. @item scale_factor Set scale factor for SRCNN model. Allowed values are @code{2}, @code{3} and @code{4}. |