x/ffmpeg
1
0
Fork 0
mirror of https://git.ffmpeg.org/ffmpeg.git synced 2026-06-11 08:13:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
master
ffmpeg/libavfilter/dnn
T
History
stevxiaoandGuo Yejun a077da895b avfilter/dnn_backend_torch: add CUDA/ROCm device support 
Add support for CUDA and ROCm (AMD GPU) devices in the LibTorch DNN
backend.

This works for both NVIDIA CUDA and AMD ROCm, as PyTorch exposes ROCm
through the CUDA-compatible API.

Usage:

./ffmpeg -i input.mp4 -vf scale=224:224,format=rgb24,dnn_processing=dnn_backend=torch:model=sr_model_torch.pt:device=cuda output.mp4

Reviewed-by: Guo Yejun <yejun.guo@intel.com>
Signed-off-by: younengxiao <steven.xiao@amd.com>
2026-03-21 16:25:40 +08:00
..
dnn_backend_common.c
avutil/common: Don't auto-include mem.h
2024-03-31 00:08:43 +01:00
dnn_backend_common.h
avfilter/dnn: Refactor DNN parameter configuration system
2024-05-18 19:44:50 +08:00
dnn_backend_openvino.c
all: fix typos found by codespell
2025-08-03 13:48:47 +02:00
dnn_backend_tf.c
avfilter/dnn_backend_tf: fix ctx async field access
2026-03-20 02:22:06 +00:00
dnn_backend_torch.cpp
avfilter/dnn_backend_torch: add CUDA/ROCm device support
2026-03-21 16:25:40 +08:00
dnn_interface.c
avfilter/dnn: fix missing set default value to options
2026-03-06 21:41:11 +08:00
dnn_io_proc.c
libavfilter/dnn_io_proc: Take step into consideration when crop frame
2024-04-04 14:26:57 +08:00
dnn_io_proc.h
lavfi/dnn_io_proc: Return Specific Error Codes
2022-03-12 15:10:28 +08:00
Makefile
libavfi/dnn: add LibTorch as one of DNN backend
2024-03-19 14:48:58 +08:00
queue.c
Remove unnecessary avassert.h inclusions
2021-07-22 15:02:30 +02:00
queue.h
lavfi/dnn: Common Function to Get Async Result in DNN Backends
2021-08-10 22:27:27 +08:00
safe_queue.c
dnn/queue: remove prefix FF for Queue and SafeQueue
2021-01-22 08:28:13 +08:00
safe_queue.h
lavfi/dnn/safe_queue.h: Add Documentation to SafeQueue
2021-04-27 10:01:20 +08:00