> -Original Message-
> From: Guo, Yejun
> Sent: 2021年1月22日 10:55
> To: ffmpeg-devel@ffmpeg.org
> Cc: Guo, Yejun
> Subject: [PATCH 2/2] dnn_backend_native.c: Add missing static to local
> variable
>
> From: Mark Thompson
>
> ---
> libavfilter/
From: Mark Thompson
---
libavfilter/dnn/dnn_backend_native.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/libavfilter/dnn/dnn_backend_native.c
b/libavfilter/dnn/dnn_backend_native.c
index 2c0b938839..be43081170 100644
--- a/libavfilter/dnn/dnn_backend_native.c
+++ b/libav
---
tests/dnn/dnn-layer-conv2d-test.c | 6 ++
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/tests/dnn/dnn-layer-conv2d-test.c
b/tests/dnn/dnn-layer-conv2d-test.c
index 378a05eafc..b623ddac0d 100644
--- a/tests/dnn/dnn-layer-conv2d-test.c
+++ b/tests/dnn/dnn-layer-conv2d-test.c
> -Original Message-
> From: ffmpeg-devel On Behalf Of Mark
> Thompson
> Sent: 2021年1月22日 5:40
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH 2/5] dnn: Add missing static to local variable
>
> ---
> libavfilter/dnn/dnn_backend_native.c | 2 +-
> 1 file changed, 1 insert
> -Original Message-
> From: ffmpeg-devel On Behalf Of Mark
> Thompson
> Sent: 2021年1月22日 5:40
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH 1/5] dnn: Delete unused global variable
>
> ---
> libavfilter/dnn/dnn_backend_native_layer_mathbinary.c | 1 -
> 1 file changed,
> -Original Message-
> From: ffmpeg-devel On Behalf Of Mark
> Thompson
> Sent: 2021年1月22日 5:43
> To: ffmpeg-devel@ffmpeg.org
> Subject: Re: [FFmpeg-devel] [PATCH 3/6] libavfilter/dnn: add prefix ff_ for
> internal functions
>
> On 18/01/2021 12:52,
Signed-off-by: Guo, Yejun
---
.../dnn/dnn_backend_native_layer_conv2d.c | 20 +--
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/libavfilter/dnn/dnn_backend_native_layer_conv2d.c
b/libavfilter/dnn/dnn_backend_native_layer_conv2d.c
index 7c6d96e916
Signed-off-by: Guo, Yejun
---
.../dnn/dnn_backend_native_layer_conv2d.c | 18 +-
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/libavfilter/dnn/dnn_backend_native_layer_conv2d.c
b/libavfilter/dnn/dnn_backend_native_layer_conv2d.c
index 0fb968a1fc..7c6d96e916
we don't need FF prefix for internal data struct
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_openvino.c | 4 +-
libavfilter/dnn/queue.c| 58 +-
libavfilter/dnn/queue.h| 20 -
libavfilter/dnn/safe_qu
from proc_from_frame_to_dnn to ff_proc_from_frame_to_dnn, and
from proc_from_dnn_to_frame to ff_proc_from_dnn_to_frame.
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_native.c | 4 ++--
libavfilter/dnn/dnn_backend_openvino.c | 4 ++--
libavfilter/dnn/dnn_backend_tf.c | 4
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_native.c | 2 +-
libavfilter/dnn/dnn_backend_openvino.c | 4 ++--
libavfilter/dnn/dnn_backend_tf.c | 4 ++--
libavfilter/dnn/dnn_io_proc.c | 10 --
libavfilter/vf_dnn_processing.c| 4 ++--
5 files
The OpenVINO model file format changes when OpenVINO goes to a new
release, it does not work if the versions between model file and
runtime are mismatched.
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_openvino.c | 9 -
1 file changed, 8 insertions(+), 1 deletion(-)
diff
> -Original Message-
> From: ffmpeg-devel On Behalf Of Ting Fu
> Sent: 2021年1月18日 11:42
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH V3 3/3] dnn/openvino: support model input
> resize
>
> OpenVINO APIs require specify input size to run the model, while some
> OpenVINO
> -Original Message-
> From: ffmpeg-devel On Behalf Of Ting Fu
> Sent: 2021年1月15日 16:43
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH V2 2/3] dnn/openvino: refine code for better
> model initialization
>
> Move openvino model/inference request creation and initializatio
> -Original Message-
> From: Steven Liu
> Sent: 2021年1月15日 11:34
> To: FFmpeg development discussions and patches
> Cc: Steven Liu ; Guo, Yejun
> Subject: Re: [FFmpeg-devel] [PATCH V2] libavfilter/dnn: add batch mode for
> async execution
>
>
>
> &
-Original Message-
> > From: ffmpeg-devel On Behalf Of Guo,
> > Yejun
> > Sent: Sunday, January 10, 2021 09:16 PM
> > To: ffmpeg-devel@ffmpeg.org
> > Cc: Guo, Yejun
> > Subject: [FFmpeg-devel] [PATCH V2] libavfilter/dnn: add batch mode for
> > async
the default number of batch_size is 1
Signed-off-by: Xie, Lin
Signed-off-by: Wu Zhiwen
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_openvino.c | 187 -
libavfilter/dnn/dnn_backend_openvino.h | 1 +
libavfilter/dnn/dnn_interface.c| 1
> -Original Message-
> From: Guo, Yejun
> Sent: 2021年1月8日 16:37
> To: ffmpeg-devel@ffmpeg.org
> Cc: Guo, Yejun
> Subject: [PATCH] libavfilter/dnn: add batch mode for async execution
>
> the default number of batch_size is 1
>
> Signed-off-by: Xie, L
the default number of batch_size is 1
Signed-off-by: Xie, Lin
Signed-off-by: Wu Zhiwen
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_openvino.c | 157 +
libavfilter/dnn/dnn_backend_openvino.h | 1 +
libavfilter/dnn/dnn_interface.c| 1
> -Original Message-
> From: ffmpeg-devel On Behalf Of Anton
> Khirnov
> Sent: 2021年1月4日 1:31
> To: FFmpeg development discussions and patches
> Subject: Re: [FFmpeg-devel] [PATCH V2 1/3] dnn: fix redefining typedefs and
> also refine naming with correct prefix
&g
> -Original Message-
> From: ffmpeg-devel On Behalf Of
> Andreas Rheinhardt
> Sent: 2020年12月31日 7:31
> To: ffmpeg-devel@ffmpeg.org
> Cc: Andreas Rheinhardt
> Subject: [FFmpeg-devel] [PATCH 02/30] avfilter/vf_addroi: Use chars instead of
> strings for one-char strings
>
> Signed-off-by:
Signed-off-by: Guo, Yejun
---
will push soon
libavfilter/dnn_interface.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/libavfilter/dnn_interface.h b/libavfilter/dnn_interface.h
index 1e2842425a..9533c88829 100644
--- a/libavfilter/dnn_interface.h
+++ b/libavfilter
efix
>
> On Wed, Dec 30, 2020 at 11:35:06PM +0800, Guo, Yejun wrote:
> > The prefix for symbols not exported from the library and not local to
> > one translation unit is ff_ (or FF for types).
> >
> > Signed-off-by: Guo, Yejun
> > ---
> > libavfilter/dnn
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_openvino.c | 16 ---
libavfilter/dnn/queue.c| 28 --
libavfilter/dnn/queue.h| 4 ++--
libavfilter/dnn/safe_queue.c | 16 ++-
libavfilter/dnn
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/safe_queue.c| 50 ++---
libavfilter/vf_dnn_processing.c | 7 +
2 files changed, 41 insertions(+), 16 deletions(-)
diff --git a/libavfilter/dnn/safe_queue.c b/libavfilter/dnn/safe_queue.c
index 52a60982b5
The prefix for symbols not exported from the library and not
local to one translation unit is ff_ (or FF for types).
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_openvino.c | 32 ++---
libavfilter/dnn/queue.c| 66 +-
libavfilter/dnn
> -Original Message-
> From: ffmpeg-devel On Behalf Of
> Andreas Rheinhardt
> Sent: 2020年12月30日 21:03
> To: ffmpeg-devel@ffmpeg.org
> Subject: Re: [FFmpeg-devel] [PATCH 1/3] dnn/queue: fix redefining typedefs
>
> Guo, Yejun:
> >
> >
> >>
> -Original Message-
> From: ffmpeg-devel On Behalf Of Guo,
> Yejun
> Sent: 2020年12月30日 20:58
> To: FFmpeg development discussions and patches
> Subject: Re: [FFmpeg-devel] [PATCH 1/3] dnn/queue: fix redefining typedefs
>
>
>
> > -Original Messag
> -Original Message-
> From: ffmpeg-devel On Behalf Of
> Andreas Rheinhardt
> Sent: 2020年12月30日 18:04
> To: ffmpeg-devel@ffmpeg.org
> Subject: Re: [FFmpeg-devel] [PATCH 1/3] dnn/queue: fix redefining typedefs
>
> Guo, Yejun:
> > Signed-off-by: Guo, Yejun
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_openvino.c | 16 ---
libavfilter/dnn/queue.c| 28 --
libavfilter/dnn/queue.h| 4 ++--
libavfilter/dnn/safe_queue.c | 16 ++-
libavfilter/dnn
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/safe_queue.c| 50 ++---
libavfilter/vf_dnn_processing.c | 7 +
2 files changed, 41 insertions(+), 16 deletions(-)
diff --git a/libavfilter/dnn/safe_queue.c b/libavfilter/dnn/safe_queue.c
index 4298048454
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/queue.c | 8
libavfilter/dnn/safe_queue.c | 4 ++--
2 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/libavfilter/dnn/queue.c b/libavfilter/dnn/queue.c
index 0a07c5473d..da0517968d 100644
--- a/libavfilter/dnn/queue.c
+++ b
n Tue, Dec 29, 2020 at 05:42:46AM +, Xie, Lin wrote:
> >> ffmpeg | branch: master | Xie, Lin | Mon Nov 9
> >> 14:09:13 2020 +0800| [6506ab8b03dd6747f6ad6b836a347a6fc346708b]
> |
> >> committer: Guo, Yejun
> >>
> >> dnn/queue: add queue and sa
> -Original Message-
> From: Guo, Yejun
> Sent: 2020年12月22日 15:48
> To: ffmpeg-devel@ffmpeg.org
> Cc: Guo, Yejun
> Subject: [PATCH 8/8] vf_dnn_processing.c: add async support
>
> Signed-off-by: Xie, Lin
> Signed-off-by: Wu Zhiwen
> Signed-of
Signed-off-by: Xie, Lin
Signed-off-by: Wu Zhiwen
Signed-off-by: Guo, Yejun
---
doc/filters.texi| 4 ++
libavfilter/vf_dnn_processing.c | 78 -
2 files changed, 81 insertions(+), 1 deletion(-)
diff --git a/doc/filters.texi b/doc/filters.texi
'void *' is too flexible, since we can derive info from
AVFilterContext*, so we just unify the interface with this data
structure.
Signed-off-by: Xie, Lin
Signed-off-by: Wu Zhiwen
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_native.c | 8
libav
Signed-off-by: Xie, Lin
Signed-off-by: Wu Zhiwen
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_openvino.c | 162 +++--
libavfilter/dnn/dnn_backend_openvino.h | 3 +
libavfilter/dnn/dnn_interface.c| 2 +
libavfilter/dnn_interface.h| 2
Signed-off-by: Xie, Lin
Signed-off-by: Wu Zhiwen
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_interface.c | 2 +-
libavfilter/dnn_interface.h | 12
2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/libavfilter/dnn/dnn_interface.c b/libavfilter/dnn
Signed-off-by: Xie, Lin
Signed-off-by: Wu Zhiwen
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_openvino.c | 22 ++
1 file changed, 6 insertions(+), 16 deletions(-)
diff --git a/libavfilter/dnn/dnn_backend_openvino.c
b/libavfilter/dnn/dnn_backend_openvino.c
function fill_model_input_ov and infer_completion_callback are
extracted, it will help the async execution for reuse.
Signed-off-by: Xie, Lin
Signed-off-by: Wu Zhiwen
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_openvino.c | 292 +++--
1 file changed, 175
From: "Xie, Lin"
Signed-off-by: Xie, Lin
Signed-off-by: Wu Zhiwen
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/Makefile | 2 +
libavfilter/dnn/queue.c | 176 +++
libavfilter/dnn/queue.h | 41
libavfilter/dnn/safe_que
with this change, dnn_processing can use DNN async interface later.
Signed-off-by: Xie, Lin
Signed-off-by: Wu Zhiwen
Signed-off-by: Guo, Yejun
---
libavfilter/vf_dnn_processing.c | 49 +++--
1 file changed, 47 insertions(+), 2 deletions(-)
diff --git a/libavfilter
> -Original Message-
> From: ffmpeg-devel On Behalf Of Ting Fu
> Sent: 2020年12月18日 16:08
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH] dnn: add NV12 pixel format support
>
> Signed-off-by: Ting Fu
> ---
> libavfilter/dnn/dnn_io_proc.c | 2 ++
> libavfilter/vf_dnn_
> -Original Message-
> From: ffmpeg-devel On Behalf Of Jun
> Zhao
> Sent: 2020年12月9日 17:53
> To: ffmpeg-devel@ffmpeg.org
> Cc: Jun Zhao
> Subject: [FFmpeg-devel] [PATCH 3/3] lavfi/dnn: check the return value from
> sws_getContext
>
> From: Jun Zhao
>
> sws_getContext may be return NU
> -Original Message-
> From: ffmpeg-devel On Behalf Of Guo,
> Yejun
> Sent: 2020年10月23日 14:41
> To: ffmpeg-devel@ffmpeg.org
> Subject: Re: [FFmpeg-devel] [PATCH] fftools/ffmpeg: add option fps_skip_frames
>
>
>
> > -Original Message-
> >
> -Original Message-
> From: Guo, Yejun
> Sent: 2020年10月15日 16:43
> To: ffmpeg-devel@ffmpeg.org
> Cc: Guo, Yejun
> Subject: [PATCH] fftools/ffmpeg: add option fps_skip_frames
>
> When dnn based filter is used with GPU as the underlying hardware, it is
> ex
> -Original Message-
> From: Guo, Yejun
> Sent: 2020年10月15日 21:17
> To: ffmpeg-devel@ffmpeg.org
> Cc: Guo, Yejun
> Subject: [PATCH V2] dnn_backend_tf.c: add option sess_config for tf backend
>
> TensorFlow C library accepts config for session options to set di
> From: Chris Miceli
> Sent: 2020年10月14日 6:15
> To: FFmpeg development discussions and patches
> Cc: Guo, Yejun
> Subject: Re: [FFmpeg-devel] [PATCH] dnn_backend_tf.c: add option sess_config
> for tf backend
>
> Hi!
>
> With proto files they can be serialised
> -Original Message-
> From: ffmpeg-devel On Behalf Of Chris
> Miceli
> Sent: 2020年10月14日 9:00
> To: ffmpeg-devel@ffmpeg.org
> Cc: Chris Miceli
> Subject: [FFmpeg-devel] [PATCH] libavfilter/dnn/dnn_backend{openvino, tf}:
> check memory alloc non-NULL
>
> These previously would not chec
> -Original Message-
> From: ffmpeg-devel On Behalf Of Chris
> Miceli
> Sent: 2020年10月14日 8:20
> To: ffmpeg-devel@ffmpeg.org
> Cc: Chris Miceli
> Subject: [FFmpeg-devel] [PATCH] libavfilter/dnn_backend_native: check mem
> allocation
>
> check that frame allocations return non-null.
> -
o which specifies one GPU:
import tensorflow as tf
gpu_options = tf.GPUOptions(visible_device_list='0')
config = tf.ConfigProto(gpu_options=gpu_options)
s = config.SerializeToString()
b = ''.join("%02x" % int(ord(b)) for b in s[::-1])
print(&#
> -Original Message-
> From: ffmpeg-devel On Behalf Of Chris
> Miceli
> Sent: 2020年10月13日 13:16
> To: ffmpeg-devel@ffmpeg.org
> Cc: Chris Miceli
> Subject: [FFmpeg-devel] [PATCH] libavfilter/dnn_backend_native: check mem
> allocation
>
> check that frame allocations return non-null.
>
> -Original Message-
> From: ffmpeg-devel On Behalf Of Peter
> Ross
> Sent: 2020年10月8日 19:01
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH] FATE/dnn: only run unit test when
> CONFIG_DNN enabled
>
> Signed-off-by: Peter Ross
> ---
> tests/fate/dnn.mak | 2 +-
> 1 file
> -Original Message-
> From: ffmpeg-devel On Behalf Of Mingyu
> Yin
> Sent: 2020年9月22日 15:11
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH V2] dnn/native: add native support for dense
>
> Signed-off-by: Mingyu Yin
> ---
> libavfilter/dnn/Makefile
> -Original Message-
> From: ffmpeg-devel On Behalf Of
> xuju...@sjtu.edu.cn
> Sent: 2020年9月19日 23:24
> To: ffmpeg-devel@ffmpeg.org
> Cc: xuju...@sjtu.edu.cn
> Subject: [FFmpeg-devel] [PATCH] dnn_backend_native_layer_conv2d.c: fix bug
> of loop boundary in single thread mode.
>
> From:
> -Original Message-
> From: Guo, Yejun
> Sent: 2020年9月14日 14:29
> To: ffmpeg-devel@ffmpeg.org
> Cc: Guo, Yejun
> Subject: [PATCH 4/4] dnn: add a new interface DNNModel.get_output
>
> for some cases (for example, super resolution), the DNN model changes the
&g
> >
> > > Subject: Re: [FFmpeg-devel] [PATCH v3 2/2]
> > > dnn_backend_native_layer_conv2d.c: refine code.
> > >
> > > On Thu, Sep 17, 2020 at 4:07 AM Guo, Yejun wrote:
> > > >
> > > >
> > > >
> > > > > ---
> -Original Message-
> From: ffmpeg-devel On Behalf Of Hendrik
> Leppkes
> Sent: 2020年9月17日 19:21
> To: FFmpeg development discussions and patches
> Subject: Re: [FFmpeg-devel] [PATCH v3 2/2]
> dnn_backend_native_layer_conv2d.c: refine code.
>
> On Thu,
> -Original Message-
> From: ffmpeg-devel On Behalf Of
> xuju...@sjtu.edu.cn
> Sent: 2020年9月16日 18:07
> To: ffmpeg-devel@ffmpeg.org
> Cc: xuju...@sjtu.edu.cn
> Subject: [FFmpeg-devel] [PATCH v3 2/2] dnn_backend_native_layer_conv2d.c:
> refine code.
>
> From: Xu Jun
>
> Move thread are
> -Original Message-
> From: ffmpeg-devel On Behalf Of
> xuju...@sjtu.edu.cn
> Sent: 2020年9月14日 19:32
> To: ffmpeg-devel@ffmpeg.org
> Cc: xuju...@sjtu.edu.cn
> Subject: [FFmpeg-devel] [PATCH 2/2] dnn_backend_native_layer_conv2d.c:
> refine code.
>
> From: Xu Jun
>
> Move thread area a
interface perspective, so add
a new explict interface DNNModel.get_output for such query.
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_native.c | 66 ++
libavfilter/dnn/dnn_backend_openvino.c | 66 ++
libavfilter/dnn/dnn_backend_tf.c
the userdata will be used for the interaction between AVFrame and DNNData
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_native.c | 3 ++-
libavfilter/dnn/dnn_backend_native.h | 2 +-
libavfilter/dnn/dnn_backend_openvino.c | 3 ++-
libavfilter/dnn/dnn_backend_openvino.h | 2
function pointer pre_proc and post_proc
in struct DNNModel, just in case that a filter has its special logic
to transfer data between AVFrame* and DNNData*. The default implementation
within DNN module is used if the filter does not set pre/post_proc.
Signed-off-by: Guo, Yejun
---
configure
inference. It also makes easy to support BBox async inference.
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_native.c | 119 +++--
libavfilter/dnn/dnn_backend_native.h | 3 +-
libavfilter/dnn/dnn_backend_openvino.c | 85 --
libavfilter/dnn
> -Original Message-
> From: ffmpeg-devel On Behalf Of Ting Fu
> Sent: 2020年9月9日 9:52
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH 2/2] dnn/openvino: add input/output name info
>
> show all input/output names when the input or output name not correct
>
> Signed-off-by
> -Original Message-
> From: ffmpeg-devel On Behalf Of
> Andreas Rheinhardt
> Sent: 2020年9月9日 20:12
> To: ffmpeg-devel@ffmpeg.org
> Cc: Andreas Rheinhardt
> Subject: [FFmpeg-devel] [PATCH] dnn/dnn_backend_native_layer_conv2d: Fix
> allocation size
>
> Found via ASAN with the dnn-layer-
> -Original Message-
> From: ffmpeg-devel On Behalf Of
> xuju...@sjtu.edu.cn
> Sent: 2020年9月6日 20:29
> To: ffmpeg-devel@ffmpeg.org
> Cc: xuju...@sjtu.edu.cn
> Subject: [FFmpeg-devel] [PATCH v5 2/2]
> dnn_backend_native_layer_conv2d.c:Add mutithread function
>
> From: Xu Jun
>
> Use pt
> -Original Message-
> From: ffmpeg-devel On Behalf Of
> xuju...@sjtu.edu.cn
> Sent: 2020年9月4日 20:46
> To: ffmpeg-devel@ffmpeg.org
> Cc: xuju...@sjtu.edu.cn
> Subject: [FFmpeg-devel] [PATCH v2 2/2]
> dnn_backend_native_layer_conv2d.c:Add mutithread function
>
> From: Xu Jun
>
> v2: ad
> -Original Message-
> From: ffmpeg-devel On Behalf Of
> xuju...@sjtu.edu.cn
> Sent: 2020年9月4日 20:46
> To: ffmpeg-devel@ffmpeg.org
> Cc: xuju...@sjtu.edu.cn
> Subject: [FFmpeg-devel] [PATCH v2 1/2] dnn_backend_native.c: parse options in
> native backend
>
> From: Xu Jun
>
> v2: use av
> -Original Message-
> From: ffmpeg-devel On Behalf Of Ting Fu
> Sent: 2020年8月27日 12:17
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH 2/2] dnn/tensorflow: add log error message
>
> Signed-off-by: Ting Fu
> ---
> libavfilter/dnn/dnn_backend_tf.c | 59 ++
> -Original Message-
> From: ffmpeg-devel On Behalf Of Ting Fu
> Sent: 2020年8月25日 11:48
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH V5 2/2] dnn/native: add log error message
>
> Signed-off-by: Ting Fu
> ---
> libavfilter/dnn/dnn_backend_native.c | 55 ++
dule.execute_model
>
>
>
> > -Original Message-
> > From: ffmpeg-devel On Behalf Of Guo,
> > Yejun
> > Sent: Friday, August 21, 2020 01:34 PM
> > To: ffmpeg-devel@ffmpeg.org
> > Subject: [FFmpeg-devel] [PATCH V2] dnn: move output name from
> > DNNModel.set_inp
> -Original Message-
> From: ffmpeg-devel On Behalf Of Mingyu
> Yin
> Sent: 2020年8月23日 23:12
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH V5 2/2] dnn_backend_native_layer_mathbinary:
> add floormod support
>
> Signed-off-by: Mingyu Yin
> ---
> libavfilter/dnn/dnn_bac
> -Original Message-
> From: ffmpeg-devel On Behalf Of Mingyu
> Yin
> Sent: 2020年8月21日 21:22
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH V4 1/2] dnn_backend_native_layer_mathbinary:
> change to function pointer
>
> Signed-off-by: Mingyu Yin
> ---
> .../dnn/dnn_backe
> -Original Message-
> From: ffmpeg-devel On Behalf Of
> Andreas Rheinhardt
> Sent: 2020年8月21日 22:21
> To: ffmpeg-devel@ffmpeg.org
> Subject: Re: [FFmpeg-devel] [PATCH] dnn_backend_native_layer_avgpool: Fix
> invalid assignment, use av_assert
>
> Guo, Yejun:
> -Original Message-
> From: ffmpeg-devel On Behalf Of
> Andreas Rheinhardt
> Sent: 2020年8月21日 19:47
> To: ffmpeg-devel@ffmpeg.org
> Cc: Andreas Rheinhardt
> Subject: [FFmpeg-devel] [PATCH] dnn_backend_native_layer_avgpool: Fix invalid
> assignment, use av_assert
>
> dnn_execute_layer_
> -Original Message-
> From: ffmpeg-devel On Behalf Of Ting Fu
> Sent: 2020年8月21日 11:47
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH V3 2/2] dnn/native: add log error message
>
> Signed-off-by: Ting Fu
> ---
> V3:
> 1. modify log_ctx of NativeModel to non-pointer
> -Original Message-
> From: ffmpeg-devel On Behalf Of Ting Fu
> Sent: 2020年8月21日 11:47
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH V3 1/2] dnn/native: unify error return to
> DNN_ERROR
>
> Unify all error return as DNN_ERROR, in order to cease model executing
> when
> -Original Message-
> From: ffmpeg-devel On Behalf Of Mingyu
> Yin
> Sent: 2020年8月21日 16:52
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH V3 1/2] dnn_backend_native_layer_mathbinary:
> add floormod support
>
> Signed-off-by: Mingyu Yin
> ---
> .../dnn/dnn_backend_nat
> -Original Message-
> From: ffmpeg-devel On Behalf Of Mingyu
> Yin
> Sent: 2020年8月21日 16:52
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH V3 2/2] dnn_backend_native_layer_mathbinary:
> change to function pointer
>
> Signed-off-by: Mingyu Yin
> ---
> .../dnn/dnn_backe
currently, output is set both at DNNModel.set_input_output and
DNNModule.execute_model, it makes sense that the output name is
provided at model inference time so all the output info is set
at a single place.
and so DNNModel.set_input_output is renamed to DNNModel.set_input
Signed-off-by: Guo
> > Subject: Re: [FFmpeg-devel] [PATCH V4] dnn_backend_openvino.c: parse
> > > options in openvino backend
> > >
> > > On 2020-08-18 23:08 +0800, Guo, Yejun wrote:
> > > > Signed-off-by: Guo, Yejun
> >
currently, output is set both at DNNModel.set_input_output and
DNNModule.execute_model, it makes sense that the output name is
provided at model inference time so all the output info is set
at a single place.
and so DNNModel.set_input_output is renamed to DNNModel.set_input
Signed-off-by: Guo
> -Original Message-
> From: ffmpeg-devel On Behalf Of Ting Fu
> Sent: 2020年8月19日 21:43
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH] dnn/native: rename struct
> ConvolutionalNetwork to NativeModel
>
> Signed-off-by: Ting Fu
> ---
> libavfilter/dnn/dnn_backend_native
ejun!
>
> On 2020-08-18 23:08 +0800, Guo, Yejun wrote:
> > Signed-off-by: Guo, Yejun
> > ---
> > v3: use AVOption
> > v4: don't add new file dnn_common.h/c
> >
> > libavfilter/dnn/dnn_backend_openvino.c | 50
> >
Signed-off-by: Guo, Yejun
---
v3: use AVOption
v4: don't add new file dnn_common.h/c
libavfilter/dnn/dnn_backend_openvino.c | 50 +-
1 file changed, 49 insertions(+), 1 deletion(-)
diff --git a/libavfilter/dnn/dnn_backend_openvino.c
b/libavfilte
> -Original Message-
> From: ffmpeg-devel On Behalf Of Paul B
> Mahol
> Sent: 2020年8月18日 17:20
> To: FFmpeg development discussions and patches
> Subject: Re: [FFmpeg-devel] [PATCH V3] dnn_backend_openvino.c: parse options
> in openvino backend
>
> On
Signed-off-by: Guo, Yejun
---
v3: change to AVOption method
libavfilter/dnn/Makefile | 1 +
libavfilter/dnn/dnn_backend_openvino.c | 35 ++-
libavfilter/dnn/dnn_common.c | 43 ++
libavfilter/dnn/dnn_common.h
> -Original Message-
> From: ffmpeg-devel On Behalf Of Ting Fu
> Sent: 2020年8月17日 13:35
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH V2] dnn/native: add log error message
>
> Signed-off-by: Ting Fu
> ---
> V2:
> Fix the issue in V1: make fate failed
>
> libavfil
t;
> Am 14. August 2020 14:07:23 MESZ schrieb "Xu, Guangxin"
> :
> >
> >
> >> -----Original Message-
> >> From: ffmpeg-devel On Behalf Of
> >Guo,
> >> Yejun
> >> Sent: Friday, August 14, 2020 9:50 AM
> >> To: ffm
gt;
> > -Original Message-
> > From: ffmpeg-devel On Behalf Of Guo,
> > Yejun
> > Sent: Friday, August 14, 2020 9:50 AM
> > To: ffmpeg-devel@ffmpeg.org
> > Subject: [FFmpeg-devel] [PATCH V2] dnn_backend_openvino.c: parse
> > options in openvino
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_openvino.c | 37 +-
1 file changed, 36 insertions(+), 1 deletion(-)
diff --git a/libavfilter/dnn/dnn_backend_openvino.c
b/libavfilter/dnn/dnn_backend_openvino.c
index d343bf2..478e151 100644
--- a
> -Original Message-
> From: ffmpeg-devel On Behalf Of Guo,
> Yejun
> Sent: 2020年8月13日 22:47
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH 1/2] dnn: fix build issue for tensorflow
> backend
>
> Signed-off-by: Guo, Yejun
> ---
> lib
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_openvino.c | 40 +-
1 file changed, 39 insertions(+), 1 deletion(-)
diff --git a/libavfilter/dnn/dnn_backend_openvino.c
b/libavfilter/dnn/dnn_backend_openvino.c
index d343bf2..030670b 100644
--- a
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_tf.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/libavfilter/dnn/dnn_backend_tf.c b/libavfilter/dnn/dnn_backend_tf.c
index 86da991..9099d2b 100644
--- a/libavfilter/dnn/dnn_backend_tf.c
+++ b/libavfilter/dnn
> -Original Message-
> From: ffmpeg-devel On Behalf Of Mingyu
> Yin
> Sent: 2020年8月10日 19:06
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH] dnn_backend_native_layer_mathunary: add
> round support
>
> Signed-off-by: Mingyu Yin
> ---
> libavfilter/dnn/dnn_backend_native
> -Original Message-
> From: ffmpeg-devel On Behalf Of
> Guo, Yejun
> Sent: Friday, August 7, 2020 3:00 PM
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH] dnn: add backend options when load the
> model
>
> different backend might need dif
> -Original Message-
> From: ffmpeg-devel On Behalf Of Ting Fu
> Sent: 2020年8月10日 0:33
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH V7 2/2] FATE/dnn: add unit test for dnn avgpool
> layer
>
> 'make fate-dnn-layer-avgpool' to run the test
>
> Signed-off-by: Ting Fu
>
different backend might need different options for a better performance,
so, add the parameter into dnn interface, as a preparation.
Signed-off-by: Guo, Yejun
---
libavfilter/dnn/dnn_backend_native.c | 3 ++-
libavfilter/dnn/dnn_backend_native.h | 2 +-
libavfilter/dnn
> -Original Message-
> From: ffmpeg-devel On Behalf Of Mingyu
> Yin
> Sent: 2020年8月6日 14:47
> To: ffmpeg-devel@ffmpeg.org
> Subject: [FFmpeg-devel] [PATCH] dnn_backend_native_layer_mathunary: add
> floor support
>
> It can be tested with the model generated with below python script:
>
301 - 400 of 838 matches
Mail list logo
