On 2024/5/6 21:42, Zhao Zhili wrote:


On May 6, 2024, at 19:48, Guo, Yejun <yejun.guo-at-intel....@ffmpeg.org> wrote:

-----Original Message-----
From: ffmpeg-devel <ffmpeg-devel-boun...@ffmpeg.org> On Behalf Of Zhao
Zhili
Sent: Tuesday, April 30, 2024 3:12 PM
To: ffmpeg-devel@ffmpeg.org
Cc: Zhao Zhili <zhiliz...@tencent.com>
Subject: [FFmpeg-devel] [PATCH v3 01/10] avfilter/dnn: Refactor DNN
parameter configuration system

From: Zhao Zhili <zhiliz...@tencent.com>

This patch trying to resolve mulitiple issues related to parameter
configuration:

Firstly, each DNN filters duplicate DNN_COMMON_OPTIONS, which should
be the common options of backend.

Secondly, backend options are hidden behind the scene. It's a
AV_OPT_TYPE_STRING backend_configs for user, and parsed by each
backend. We don't know each backend support what kind of options
from the help message.

Third, DNN backends duplicate DNN_BACKEND_COMMON_OPTIONS.

Last but not the least, pass backend options via AV_OPT_TYPE_STRING
makes it hard to pass AV_OPT_TYPE_BINARY to backend, if not impossible.

This patch puts backend common options and each backend options inside
DnnContext to reduce code duplication, make options user friendly, and
easy to extend for future usecase.

There is a known issue that, for a filter which only support one or two
of the backends, the help message still show the option of all three
backends. Each DNN filter should be able to run on any backend. Current
issue is mostly due to incomplete implementation (e.g., libtorch only
support DFT_PROCESS_FRAME), and lack of maintenance on the filters.

This patch 01 basically looks good, two comments:
- it is possible that we add one dnn filter with one backend support first, and then other backends one by one some-time later. So, please adjust the help message
accordingly with only the supported backends.

I can’t figure out how to do that properly without duplicating some code for each
filter. Do you have any idea?

Fixed in patch v4.



- is it possible to split this patch into small patches for an easier detail review?

The configuration methods were scattered across filter common code, filters, backend common code and backend implementation. I have written six version, patch 1/10
is hard to split to small patches like patch 2-10.



For example,

./ffmpeg -h filter=dnn_processing

dnn_processing AVOptions:
  dnn_backend       <int>        ..FV....... DNN backend (from INT_MIN to
INT_MAX) (default tensorflow)
    tensorflow      1            ..FV....... tensorflow backend flag
    openvino        2            ..FV....... openvino backend flag
    torch           3            ..FV....... torch backend flag

dnn_base AVOptions:
  model             <string>     ..F........ path to model file
  input             <string>     ..F........ input name of the model
  output            <string>     ..F........ output name of the model
  backend_configs   <string>     ..F.......P backend configs (deprecated)   options           <string>     ..F.......P backend configs (deprecated)   nireq             <int>        ..F........ number of request (from 0 to INT_MAX)
(default 0)
  async             <boolean>    ..F........ use DNN async inference (default true)
  device            <string>     ..F........ device to run model

dnn_tensorflow AVOptions:
  sess_config       <string>     ..F........ config for SessionOptions

dnn_openvino AVOptions:
  batch_size        <int>        ..F........ batch size per request (from 1 to 1000)
(default 1)
  input_resizable   <boolean>    ..F........ can input be resizable or not (default
false)
  layout            <int>        ..F........ input layout of model (from 0 to 2) (default
none)
    none            0            ..F........ none
    nchw            1            ..F........ nchw
    nhwc            2            ..F........ nhwc
  scale             <float>      ..F........ Add scale preprocess operation. Divide each element of input by specified value. (from INT_MIN to INT_MAX) (default 0)   mean              <float>      ..F........ Add mean preprocess operation. Subtract
specified value from each element of input. (from INT_MIN to INT_MAX)
(default 0)

dnn_th AVOptions:
  optimize          <int>        ..F........ turn on graph executor optimization (from 0
to 1) (default 0)
---
libavfilter/dnn/dnn_backend_common.h   |  13 ++-
libavfilter/dnn/dnn_backend_openvino.c | 146 ++++++++++---------------
libavfilter/dnn/dnn_backend_tf.c       |  82 +++++---------
libavfilter/dnn/dnn_backend_torch.cpp  |  67 ++++--------
libavfilter/dnn/dnn_interface.c        |  89 +++++++++++++++
libavfilter/dnn_filter_common.c        |  38 ++++++-
libavfilter/dnn_filter_common.h        |  39 +++----
libavfilter/dnn_interface.h            |  67 +++++++++++-
libavfilter/vf_derain.c                |   6 +-
libavfilter/vf_dnn_classify.c          |   4 +-
libavfilter/vf_dnn_detect.c            |   4 +-
libavfilter/vf_dnn_processing.c        |   4 +-
libavfilter/vf_sr.c                    |   6 +-
13 files changed, 336 insertions(+), 229 deletions(-)
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

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


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

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

Reply via email to