So the backend knows the usage of model is for frame processing,
detect, classify, etc. Each function type has different behavior
in backend when handling the input/output data of the model.
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
suppose we have a detect and classify filter in the future, the
detect filter generates some bounding boxes (BBox) as AVFrame sidedata,
and the classify filter executes DNN model for each BBox. For each
BBox, we need to crop the AVFrame, copy data to DNN model input and do
the model execution. So we have to save the in_frame at DNNModel.set_input
and use it at DNNModule.execute_model, such saving is not feasible
when we support async execute_model.
This patch sets the in_frame as execution_model parameter, and so
all the information are put together within the same function for
each inference. It also makes easy to support BBox async inference.
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.
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, Yejun <yejun.guo@intel.com>
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 <yejun.guo@intel.com>
currently, the model outputs the rain, and so need a subtraction
in filter c code to get the final derain result.
I've sent a PR to update the model file and accepted, see at
https://github.com/XueweiMeng/derain_filter/pull/3
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Steven Liu <lq@chinaffmpeg.org>
so, we can make a filter more general to accept different network
models, by adding a data type convertion after getting data from network.
After we add dt field into struct DNNData, it becomes the same as
DNNInputData, so merge them with one struct: DNNData.
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
Add the support of dehaze filter in existing derain filter source
code. As the processing procedure in FFmpeg is the same for current
derain and dehaze, we reuse the derain filter source code. The
model training and generation scripts are in repo
https://github.com/XueweiMeng/derain_filter.git
Reviewed-by: Steven Liu <lq@onvideo.cn>
Signed-off-by: Xuewei Meng <xwmeng96@gmail.com>
Remove the rain in the input image/video by applying the derain
methods based on convolutional neural networks. Training scripts
as well as scripts for model generation are provided in the
repository at https://github.com/XueweiMeng/derain_filter.git.
Signed-off-by: Xuewei Meng <xwmeng96@gmail.com>
Guo, Yejun
Xuewei Meng