This patch removes all occurences of DNNReturnType from the DNN module.
This commit replaces DNN_SUCCESS by 0 (essentially the same), so the
functions with DNNReturnType now return 0 in case of success, the negative
values otherwise.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn
Switch to returning specific error codes or DNN_GENERIC_ERROR
when an error is encountered in the common DNN backend functions.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 35 ++--
libavfilter/dnn/dnn_backend_common.h | 22
Switch to returning specific error codes or DNN_GENERIC_ERROR
when an error is encountered.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_native.c | 82 +++-
libavfilter/dnn/dnn_backend_native.h | 4 +-
2 files changed, 45 insertions(+), 41 deletions
Switch to returning specific error codes or DNN_GENERIC_ERROR
when an error is encountered. For TensorFlow C API errors, currently
DNN_GENERIC_ERROR is returned.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 148 +--
libavfilter/dnn
Switch to returning specific error codes or DNN_GENERIC_ERROR
when an error is encountered. For OpenVINO API errors, currently
DNN_GENERIC_ERROR is returned.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_openvino.c | 138 +++--
libavfilter/dnn
This commit returns specific error codes from the functions in the
dnn_io_proc instead of DNN_ERROR.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_io_proc.c | 48 +++
libavfilter/dnn/dnn_io_proc.h | 8 +++---
2 files changed, 30 insertions(+), 26
This commit returns specific error codes from the execution
functions in the Native Backend layers instead of DNN_ERROR.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_native_layer_avgpool.c | 6 +++---
libavfilter/dnn/dnn_backend_native_layer_avgpool.h | 3 ++-
libavfilter
This commit prepares the filter side to handle specific error codes
from the DNN backends instead of current DNN_ERROR.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn_filter_common.c | 10 +-
libavfilter/dnn_filter_common.h | 10 +-
libavfilter/vf_derain.c | 4
This patch removes all occurences of DNNReturnType from the DNN module.
This commit replaces DNN_SUCCESS by 0 (essentially the same), so the
functions with DNNReturnType now return 0 in case of success, the negative
values otherwise.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn
Switch to returning specific error codes or DNN_GENERIC_ERROR
when an error is encountered in the common DNN backend functions.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 35 ++--
libavfilter/dnn/dnn_backend_common.h | 22
Switch to returning specific error codes or DNN_GENERIC_ERROR
when an error is encountered.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_native.c | 82 +++-
libavfilter/dnn/dnn_backend_native.h | 4 +-
2 files changed, 45 insertions(+), 41 deletions
Switch to returning specific error codes or DNN_GENERIC_ERROR
when an error is encountered. For TensorFlow C API errors, currently
DNN_GENERIC_ERROR is returned.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 147 +--
libavfilter/dnn
Switch to returning specific error codes or DNN_GENERIC_ERROR
when an error is encountered. For OpenVINO API errors, currently
DNN_GENERIC_ERROR is returned.
---
libavfilter/dnn/dnn_backend_openvino.c | 138 +++--
libavfilter/dnn/dnn_backend_openvino.h | 4 +-
libavfilter/dnn
This commit returns specific error codes from the functions in the
dnn_io_proc instead of DNN_ERROR.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_io_proc.c | 48 +++
libavfilter/dnn/dnn_io_proc.h | 8 +++---
2 files changed, 30 insertions(+), 26
This commit returns specific error codes from the execution
functions in the Native Backend layers instead of DNN_ERROR.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_native_layer_avgpool.c | 6 +++---
libavfilter/dnn/dnn_backend_native_layer_avgpool.h | 3 ++-
libavfilter
This commit prepares the filter side to handle specific error codes
from the DNN backends instead of current DNN_ERROR.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn_filter_common.c | 10 +-
libavfilter/dnn_filter_common.h | 10 +-
libavfilter/vf_derain.c | 4
Signed-off-by: Shubhanshu Saxena
---
doc/filters.texi | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/doc/filters.texi b/doc/filters.texi
index 7aff920311..4da1cdc2aa 100644
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -9982,7 +9982,7 @@ Note that different backends
Item
3. inference_queue -> lltask_queue
4. inference -> lltask
5. inference_count -> lltask_count
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.h | 4 +-
libavfilter/dnn/dnn_backend_native.c | 58 ++---
libavfilter/dnn/dnn_backend_native.h | 2 +-
Remove async flag from filter's perspective after the unification
of async and sync modes in the DNN backend.
Signed-off-by: Shubhanshu Saxena
---
doc/filters.texi | 14 --
libavfilter/dnn/dnn_backend_tf.c | 7 +++
libavfilter/dnn_filter_common.c
This commit removes the unused sync mode specific code from the DNN
filters since the sync and async mode are now unified from the
filters' perspective.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/vf_dnn_detect.c | 71 +---
libavfilter/vf_dnn_processing.c
nstead of
input frame to the DNN backends.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 4 +-
libavfilter/dnn/dnn_backend_common.h | 5 +-
libavfilter/dnn/dnn_backend_native.c | 59 ++-
libavfilter/dnn/dnn_backend_native.h | 6 ++
This commit rearranges the code in Native Backend to use the TaskItem
for inference.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_native.c | 176 ++-
libavfilter/dnn/dnn_backend_native.h | 2 +
2 files changed, 121 insertions(+), 57 deletions
This commit updates the following two filters to send only the
input frame and send NULL as output frame instead of input frame
to the DNN backends.
1. vf_dnn_detect
2. vf_dnn_classify
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 2 +-
libavfilter/dnn
Signed-off-by: Shubhanshu Saxena
---
doc/filters.texi | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/doc/filters.texi b/doc/filters.texi
index d99368e64b..112adc5d94 100644
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -9982,7 +9982,7 @@ Note that different backends
Item
3. inference_queue -> lltask_queue
4. inference -> lltask
5. inference_count -> lltask_count
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.h | 4 +-
libavfilter/dnn/dnn_backend_native.c | 58 ++---
libavfilter/dnn/dnn_backend_native.h | 2 +-
Remove async flag from filter's perspective after the unification
of async and sync modes in the DNN backend.
Signed-off-by: Shubhanshu Saxena
---
doc/filters.texi | 14 --
libavfilter/dnn/dnn_backend_tf.c | 7 +++
libavfilter/dnn_filter_common.c
This commit removes the unused sync mode specific code from the DNN
filters since the sync and async mode are now unified from the
filters' perspective.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/vf_dnn_detect.c | 71 +---
libavfilter/vf_dnn_processing.c
1 for
async and 0 for sync mode of execution.
This commit affects the following filters:
1. vf_dnn_classify
2. vf_dnn_detect
3. vf_dnn_processing
4. vf_sr
5. vf_derain
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 2 +-
libavfilter/dnn/dnn_backend_common.h | 5
This commit rearranges the code in Native Backend to use the TaskItem
for inference.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_native.c | 176 ++-
libavfilter/dnn/dnn_backend_native.h | 2 +
2 files changed, 121 insertions(+), 57 deletions
This commit updates the following two filters to send only the
input frame and send NULL as output frame instead of input frame
to the DNN backends.
1. vf_dnn_detect
2. vf_dnn_classify
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 2 +-
libavfilter/dnn
Signed-off-by: Shubhanshu Saxena
---
doc/filters.texi | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/doc/filters.texi b/doc/filters.texi
index d99368e64b..112adc5d94 100644
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -9982,7 +9982,7 @@ Note that different backends
Item
3. inference_queue -> lltask_queue
4. inference -> lltask
5. inference_count -> lltask_count
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.h | 4 +-
libavfilter/dnn/dnn_backend_native.c | 58 ++---
libavfilter/dnn/dnn_backend_native.h | 2 +-
Remove async flag from filter's perspective after the unification
of async and sync modes in the DNN backend.
Signed-off-by: Shubhanshu Saxena
---
doc/filters.texi | 14 --
libavfilter/dnn/dnn_backend_tf.c | 7 +++
libavfilter/dnn_filter_common.c
This commit removes the unused sync mode specific code from the DNN
filters since the sync and async mode are now unified from the
filters' perspective.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/vf_dnn_detect.c | 71 +---
libavfilter/vf_dnn_processing.c
1 for
async and 0 for sync mode of execution.
This commit affects the following filters:
1. vf_dnn_classify
2. vf_dnn_detect
3. vf_dnn_processing
4. vf_sr
5. vf_derain
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 2 +-
libavfilter/dnn/dnn_backend_common.h | 5
This commit rearranges the code in Native Backend to use the TaskItem
for inference.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_native.c | 176 ++-
libavfilter/dnn/dnn_backend_native.h | 2 +
2 files changed, 121 insertions(+), 57 deletions
On Mon, Aug 23, 2021 at 3:57 PM Fu, Ting wrote:
>
>
> > -Original Message-
> > From: ffmpeg-devel On Behalf Of
> > Shubhanshu Saxena
> > Sent: Saturday, August 21, 2021 03:59 PM
> > To: ffmpeg-devel@ffmpeg.org
> > Cc: Shubhanshu Saxena
>
Signed-off-by: Shubhanshu Saxena
---
doc/filters.texi | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/doc/filters.texi b/doc/filters.texi
index f7b6b61f4c..0b2da7c71f 100644
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -9974,7 +9974,7 @@ Note that different backends
Item
3. inference_queue -> lltask_queue
4. inference -> lltask
5. inference_count -> lltask_count
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.h | 4 +-
libavfilter/dnn/dnn_backend_native.c | 58 ++---
libavfilter/dnn/dnn_backend_native.h | 2 +-
Remove async flag from filter's perspective after the unification
of async and sync modes in the DNN backend.
Signed-off-by: Shubhanshu Saxena
---
doc/filters.texi | 14 --
libavfilter/dnn/dnn_backend_tf.c | 7 +++
libavfilter/dnn_filter_common.c
This commit removes the unused sync mode specific code from the DNN
filters since the sync and async mode are now unified from the
filters' perspective.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/vf_dnn_detect.c | 71 +---
libavfilter/vf_dnn_processing.c
1 for
async and 0 for sync mode of execution.
This commit affects the following filters:
1. vf_dnn_classify
2. vf_dnn_detect
3. vf_dnn_processing
4. vf_sr
5. vf_derain
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 2 +-
libavfilter/dnn/dnn_backend_common.h | 5
This commit rearranges the code in Native Backend to use the TaskItem
for inference.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_native.c | 176 ++-
libavfilter/dnn/dnn_backend_native.h | 2 +
2 files changed, 121 insertions(+), 57 deletions
On Sat, Aug 21, 2021 at 12:56 PM Guo, Yejun wrote:
>
>
> > -Original Message-
> > From: ffmpeg-devel On Behalf Of
> > Shubhanshu Saxena
> > Sent: Saturday, August 21, 2021 3:05 PM
> > To: FFmpeg development discussions and patches > de...@ffm
On Sat, Aug 21, 2021 at 8:41 AM Guo, Yejun wrote:
>
>
> > -Original Message-
> > From: ffmpeg-devel On Behalf Of
> > Shubhanshu Saxena
> > Sent: 2021年8月20日 22:21
> > To: ffmpeg-devel@ffmpeg.org
> > Cc: Shubhanshu Saxena
> > Subjec
Signed-off-by: Shubhanshu Saxena
---
doc/filters.texi | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/doc/filters.texi b/doc/filters.texi
index fac19ac413..03a355a982 100644
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -9974,7 +9974,7 @@ Note that different backends
Item
3. inference_queue -> lltask_queue
4. inference -> lltask
5. inference_count -> lltask_count
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.h | 4 +-
libavfilter/dnn/dnn_backend_native.c | 58 ++---
libavfilter/dnn/dnn_backend_native.h | 2 +-
Remove async flag from filter's perspective after the unification
of async and sync modes in the DNN backend.
Signed-off-by: Shubhanshu Saxena
---
doc/filters.texi | 14 --
libavfilter/dnn/dnn_backend_tf.c | 7 +++
libavfilter/dnn_filter_common.c
This commit removes the unused sync mode specific code from the DNN
filters since the sync and async mode are now unified from the
filters' perspective.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/vf_dnn_detect.c | 71 +---
libavfilter/vf_dnn_processing.c
1 for
async and 0 for sync mode of execution.
This commit affects the following filters:
1. vf_dnn_classify
2. vf_dnn_detect
3. vf_dnn_processing
4. vf_sr
5. vf_derain
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 2 +-
libavfilter/dnn/dnn_backend_common.h | 5
This commit rearranges the code in Native Backend to use the TaskItem
for inference.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_native.c | 176 ++-
libavfilter/dnn/dnn_backend_native.h | 2 +
2 files changed, 121 insertions(+), 57 deletions
This commit includes the check for the case when the newly created
TFInferRequest is NULL.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/libavfilter/dnn/dnn_backend_tf.c b/libavfilter/dnn/dnn_backend_tf.c
index
The frame allocation and filling the TaskItem with execution
parameters is common in the three backends. This commit shifts
this logic to dnn_backend_common.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 26 +
libavfilter/dnn/dnn_backend_common.h
This commit adds the case handling if the asynchronous execution
of a request fails by checking the exit status of the thread when
joining before starting another execution. On failure, it does the
cleanup as well.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 23
Since requests are running in parallel, there is inconsistency in
the status of the execution. To resolve it, we avoid using mutex
as it would result in single TF_Session running at a time. So add
TF_Status to the TFRequestItem
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn
This patch adds error handling for cases where the execute_model_tf
fails, clears the used memory in the TFRequestItem and finally pushes
it back to the request queue.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 52 ++--
1 file changed, 36
comparison of this mechanism with the existing
sync mechanism on TensorFlow C API 2.5 CPU variant.
Async Mode: 4m32.846s
Sync Mode: 5m17.582s
The above was performed on super resolution filter using SRCNN model.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 121
This commit adds a function for execution of TFInferRequest and documentation
for functions related to TFInferRequest.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 45
1 file changed, 45 insertions(+)
diff --git a/libavfilter/dnn
This commits refactors the get async result function for common
use in all three backends.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 20
libavfilter/dnn/dnn_backend_common.h | 15 +++
libavfilter/dnn/dnn_backend_openvino.c
This commit adds an async execution mechanism for common use
in the TensorFlow and Native backends.
This commit also adds the documentation of typedefs and functions in
the async module for common use in DNN backends.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c
This commits refactors the get async result function for common
use in all three backends.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 20
libavfilter/dnn/dnn_backend_common.h | 15 +++
libavfilter/dnn/dnn_backend_openvino.c
comparison of this mechanism with the existing
sync mechanism on TensorFlow C API 2.5 CPU variant.
Async Mode: 4m32.846s
Sync Mode: 5m17.582s
The above was performed on super resolution filter using SRCNN model.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 121
This commit adds a function for execution of TFInferRequest and documentation
for functions related to TFInferRequest.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 45
1 file changed, 45 insertions(+)
diff --git a/libavfilter/dnn
Since requests are running in parallel, there is inconsistency in
the status of the execution. To resolve it, we avoid using mutex
as it would result in single TF_Session running at a time. So add
TF_Status to the TFRequestItem
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn
This patch adds error handling for cases where the execute_model_tf
fails, clears the used memory in the TFRequestItem and finally pushes
it back to the request queue.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 52 ++--
1 file changed, 36
This commit includes the check for the case when the newly created
TFInferRequest is NULL.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/libavfilter/dnn/dnn_backend_tf.c b/libavfilter/dnn/dnn_backend_tf.c
index
This commit adds an async execution mechanism for common use
in the TensorFlow and Native backends.
This commit also adds the documentation of typedefs and functions in
the async module for common use in DNN backends.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c
The frame allocation and filling the TaskItem with execution
parameters is common in the three backends. This commit shifts
this logic to dnn_backend_common.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 26 +
libavfilter/dnn/dnn_backend_common.h
This commit adds an async execution mechanism for common use
in the TensorFlow and Native backends.
This commit also adds the documentation of typedefs and functions in
the async module for common use in DNN backends.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c
This commit adds a function for execution of TFInferRequest and documentation
for functions related to TFInferRequest.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 45
1 file changed, 45 insertions(+)
diff --git a/libavfilter/dnn
This patch adds error handling for cases where the execute_model_tf
fails, clears the used memory in the TFRequestItem and finally pushes
it back to the request queue.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 52 ++--
1 file changed, 36
This commits refactors the get async result function for common
use in all three backends.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 20
libavfilter/dnn/dnn_backend_common.h | 15 +++
libavfilter/dnn/dnn_backend_openvino.c
Since requests are running in parallel, there is inconsistency in
the status of the execution. To resolve it, we avoid using mutex
as it would result in single TF_Session running at a time. So add
TF_Status to the TFRequestItem
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn
variant.
Async Mode: 0m57.064s
Sync Mode: 1m1.959s
The above was performed on super resolution filter using ESPCN model.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 121 ++-
libavfilter/dnn/dnn_backend_tf.h | 3 +
libavfilter/dnn
This commit includes the check for the case when the newly created
TFInferRequest is NULL.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/libavfilter/dnn/dnn_backend_tf.c b/libavfilter/dnn/dnn_backend_tf.c
index
The frame allocation and filling the TaskItem with execution
parameters is common in the three backends. This commit shifts
this logic to dnn_backend_common.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 26 +
libavfilter/dnn/dnn_backend_common.h
Rename RequestItem to OVRequestItem in the OpenVINO backend
to avoid confusion.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_openvino.c | 24
1 file changed, 12 insertions(+), 12 deletions(-)
diff --git a/libavfilter/dnn/dnn_backend_openvino.c
b
In cases where the execution inside the function execute_model_ov fails,
the OVRequestItem must be pushed back to the request_queue before returning
the error. In case pushing back fails, release the allocated memory.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_openvino.c
On Sun, Jul 11, 2021 at 6:25 PM Guo, Yejun wrote:
>
>
> > -Original Message-
> > From: ffmpeg-devel On Behalf Of
> > Shubhanshu Saxena
> > Sent: 2021年7月5日 18:31
> > To: ffmpeg-devel@ffmpeg.org
> > Cc: Shubhanshu Saxena
> > Subject: [F
This commit uses TFRequestItem and the existing sync execution
mechanism to use request-based execution. It will help in adding
async functionality to the TensorFlow backend later.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.h | 3 +
libavfilter/dnn
This commit introduces a typedef TFInferRequest to store
execution parameters for a single call to the TensorFlow C API.
This typedef is used in the TFRequestItem.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 49
1 file changed, 49
This commit rearranges the existing code to create separate function
for filling request with execution data.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 137 ++-
1 file changed, 80 insertions(+), 57 deletions(-)
diff --git a/libavfilter
This commit rearranges the existing code to create a separate function
for the completion callback in execute_model_tf.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 109 +--
1 file changed, 61 insertions(+), 48 deletions(-)
diff --git a
This commit adds handling for cases where an error may occur, clearing
the allocated memory resources.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 80
1 file changed, 60 insertions(+), 20 deletions(-)
diff --git a/libavfilter/dnn
This commit uses the common TaskItem and InferenceItem typedefs
for execution in TensorFlow backend.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 134 ++-
1 file changed, 94 insertions(+), 40 deletions(-)
diff --git a/libavfilter/dnn
In cases where the execution inside the function execute_model_ov fails,
push the RequestItem back to the request_queue before returning the error.
In case pushing back fails, release the allocated memory.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_openvino.c | 12
Fix memory leak for RequestItem upon error while pushing to the
request_queue in the completion callback.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_openvino.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/libavfilter/dnn/dnn_backend_openvino.c
b/libavfilter/dnn
Add nb_output property to TaskItem for use in TensorFlow backend
and Native backend.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.h | 1 +
libavfilter/dnn/dnn_backend_openvino.c | 3 +++
2 files changed, 4 insertions(+)
diff --git a/libavfilter/dnn
Extract TaskItem and InferenceItem from OpenVino backend and convert
ov_model to void in TaskItem.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.h | 19 +
libavfilter/dnn/dnn_backend_openvino.c | 58 ++
2 files changed, 40 insertions
This commit adds a common function for filling the TaskItems
in all three backends.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.c | 20
libavfilter/dnn/dnn_backend_common.h | 15 +++
libavfilter/dnn/dnn_backend_openvino.c | 23
These properties have values either 0 or 1, so using uint8_t
is a better option as compared to int.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/libavfilter/dnn/dnn_backend_common.h
b
Convert output_name to char **output_names in TaskItem and use it as
a pointer to array of output names in the DNN backend.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.h | 2 +-
libavfilter/dnn/dnn_backend_openvino.c | 10 +-
2 files changed, 6 insertions
Extract TaskItem and InferenceItem from OpenVino backend and convert
ov_model to void in TaskItem.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.h | 19 +
libavfilter/dnn/dnn_backend_openvino.c | 58 ++
2 files changed, 40 insertions
Add nb_output property to TaskItem for use in TensorFlow backend
and Native backend.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.h | 1 +
libavfilter/dnn/dnn_backend_openvino.c | 3 +++
2 files changed, 4 insertions(+)
diff --git a/libavfilter/dnn
Convert output_name to char **output_names in TaskItem and use it as
a pointer to array of output names in the DNN backend.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_common.h | 2 +-
libavfilter/dnn/dnn_backend_openvino.c | 10 +-
2 files changed, 6 insertions
This commit adds handling for cases where an error may occur, clearing
the allocated memory resources.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 100 +++
1 file changed, 74 insertions(+), 26 deletions(-)
diff --git a/libavfilter/dnn
Documentation for functions related to tf_infer_request
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 41
1 file changed, 41 insertions(+)
diff --git a/libavfilter/dnn/dnn_backend_tf.c b/libavfilter/dnn/dnn_backend_tf.c
index
This commit rearranges the existing code to create two separate functions
for filling request with execution data and the completion callback.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 81 ++--
1 file changed, 57 insertions(+), 24
This commit adds functions to execute the inference requests
to TensorFlow Backend asynchronously in detached threads.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 198 ---
libavfilter/dnn/dnn_backend_tf.h | 3 +
libavfilter/dnn
This commit adds RequestItem and rearranges the existing sync
execution mechanism to use request-based execution. It will help
in adding async functionality to the TensorFlow backend later.
Signed-off-by: Shubhanshu Saxena
---
libavfilter/dnn/dnn_backend_tf.c | 297
1 - 100 of 135 matches
Mail list logo
