[FFmpeg-devel] [PATCH v2] doc: Add libtoch backend option to dnn_processing

* [FFmpeg-devel] [PATCH v2] doc: Add libtoch backend option to dnn_processing
@ 2024-03-25  2:15 wenbin.chen-at-intel.com
  2024-03-25 11:16 ` Guo, Yejun
  0 siblings, 1 reply; 4+ messages in thread
From: wenbin.chen-at-intel.com @ 2024-03-25  2:15 UTC (permalink / raw)
  To: ffmpeg-devel

From: Wenbin Chen <wenbin.chen@intel.com>

Signed-off-by: Wenbin Chen <wenbin.chen@intel.com>
---
 doc/filters.texi | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/doc/filters.texi b/doc/filters.texi
index 18f0d1c5a7..bfa8ccec8b 100644
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -12073,11 +12073,21 @@ need to build and install the OpenVINO for C library (see
 @code{--enable-libopenvino} (--extra-cflags=-I... --extra-ldflags=-L... might
 be needed if the header files and libraries are not installed into system path)
 
+@item torch
+Libtorch backend. To enable this backend you need to build and install Libtroch
+for C++ library. Please download cxx11 ABI version (see
+@url{https://pytorch.org/get-started/locally})
+and configure FFmpeg with @code{--enable-libtorch
+--extra-cflags=-I/libtorch_root/libtorch/include
+--extra-cflags=-I/libtorch_root/libtorch/include/torch/csrc/api/include
+--extra-ldflags=-L/libtorch_root/libtorch/lib/}
+
 @end table
 
 @item model
 Set path to model file specifying network architecture and its parameters.
-Note that different backends use different file formats. TensorFlow, OpenVINO backend can load files for only its format.
+Note that different backends use different file formats. TensorFlow, OpenVINO
+and Libtorch backend can load files for only its format.
 
 @item input
 Set the input name of the dnn network.
-- 
2.34.1

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".

^ permalink raw reply	[flat|nested] 4+ messages in thread