Raja-89 27cdf70086 avfilter/dnn: implement asynchronous execution for LibTorch backend ...

This patch implements the DNNAsyncExecModule for the LibTorch backend,
enabling non-blocking inference using the common infrastructure instead
of custom threading (th_async_module_submit) to align with the
TensorFlow and OpenVINO backends.

The implementation uses ff_dnn_start_inference_async which provides
unified async logic across all DNN backends, eliminating the need for
backend-specific threading code.

Verified with:
  ffmpeg -f lavfi -i testsrc=duration=5:size=320x240:rate=30 -vf dnn_processing=dnn_backend=torch:model=model.pt -y output.mp4

Signed-off-by: Raja Rathour <imraja729@gmail.com>

2026-03-02 21:35:17 +08:00

..

dnn_backend_common.c

…

dnn_backend_common.h

…

dnn_backend_openvino.c

all: fix typos found by codespell

2025-08-03 13:48:47 +02:00

dnn_backend_tf.c

libavfilter/dnn/dnn_backend_tf: Remove redundant av_freep() to avoid double free

2025-08-13 19:50:26 +08:00

dnn_backend_torch.cpp

avfilter/dnn: implement asynchronous execution for LibTorch backend

2026-03-02 21:35:17 +08:00

dnn_interface.c

…

dnn_io_proc.c

…

dnn_io_proc.h

…

Makefile

…

queue.c

…

queue.h

…

safe_queue.c

…

safe_queue.h

…