Commit Graph

12 Commits

Author SHA1 Message Date
Guo, Yejun 4c705a2775 lavfi/dnn: refine code to separate processing and detection in backends 2021-05-24 09:09:34 +08:00
Guo, Yejun 3fb1d2e71c lavfi/dnn/dnn_io_proc.c: fix Improper use of negative value (NEGATIVE_RETURNS)
fix coverity CID 1473511 and 1473566
2021-05-18 09:20:08 +08:00
Guo, Yejun bd6ea9ed1d lavfi/dnn/dnn_io_proc.c: Fix Out-of-bounds access (ARRAY_VS_SINGLETON)
fix coverity CID 1473571, 1473577 and 1482089
2021-05-18 09:20:08 +08:00
Ting Fu f02928eb5a dnn: add DCO_RGB color order to enum DNNColorOrder
Adding DCO_RGB color order to DNNColorOrder, since tensorflow model
needs this kind of color oder as input.

Signed-off-by: Ting Fu <ting.fu@intel.com>
2021-05-11 10:28:35 +08:00
Guo, Yejun fc26dca64e lavfi/dnn: add classify support with openvino backend
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
2021-05-06 10:50:44 +08:00
Guo, Yejun 2da3a5c10f dnn: add color conversion for analytic case
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
2021-02-18 09:59:37 +08:00
Guo, Yejun c5e30d588d libavfilter/dnn: add prefix ff_ for internal functions
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 <yejun.guo@intel.com>
2021-01-22 08:28:13 +08:00
Guo, Yejun 2d6af4a501 libavfilter/dnn: use avpriv_report_missing_feature for unsupported features
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
2021-01-22 08:28:13 +08:00
Ting Fu 5dbabb020e dnn: add NV12 pixel format support
Signed-off-by: Ting Fu <ting.fu@intel.com>
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
2020-12-22 10:53:35 +08:00
Jun Zhao 0320dab265 lavfi/dnn: check the return value from sws_getContext
sws_getContext may be return NULL, and it's will be dereferenced,
so add the check.

Signed-off-by: Jun Zhao <barryjzhao@tencent.com>
2020-12-12 13:34:30 +08:00
Jun Zhao ae2075265b lavfi/dnn: used the format name in debug message
Used the format name in debug message.

Signed-off-by: Jun Zhao <barryjzhao@tencent.com>
2020-12-12 13:34:24 +08:00
Guo, Yejun 2003e32f62 dnn: change dnn interface to replace DNNData* with AVFrame*
Currently, every filter needs to provide code to transfer data from
AVFrame* to model input (DNNData*), and also from model output
(DNNData*) to AVFrame*. Actually, such transfer can be implemented
within DNN module, and so filter can focus on its own business logic.

DNN module also exports the 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.
2020-09-21 21:26:56 +08:00