mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-12-28 20:53:54 +02:00
fce3e3e137
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. |
||
|---|---|---|
| .. | ||
| dnn_backend_native_layer_avgpool.c | ||
| dnn_backend_native_layer_avgpool.h | ||
| dnn_backend_native_layer_conv2d.c | ||
| dnn_backend_native_layer_conv2d.h | ||
| dnn_backend_native_layer_depth2space.c | ||
| dnn_backend_native_layer_depth2space.h | ||
| dnn_backend_native_layer_mathbinary.c | ||
| dnn_backend_native_layer_mathbinary.h | ||
| dnn_backend_native_layer_mathunary.c | ||
| dnn_backend_native_layer_mathunary.h | ||
| dnn_backend_native_layer_maximum.c | ||
| dnn_backend_native_layer_maximum.h | ||
| dnn_backend_native_layer_pad.c | ||
| dnn_backend_native_layer_pad.h | ||
| dnn_backend_native_layers.c | ||
| dnn_backend_native_layers.h | ||
| dnn_backend_native.c | ||
| dnn_backend_native.h | ||
| dnn_backend_openvino.c | ||
| dnn_backend_openvino.h | ||
| dnn_backend_tf.c | ||
| dnn_backend_tf.h | ||
| dnn_interface.c | ||
| dnn_io_proc.c | ||
| dnn_io_proc.h | ||
| Makefile | ||