diff options
| author | Guo, Yejun <yejun.guo@intel.com> | 2021-02-07 14:35:22 +0800 |
|---|---|---|
| committer | Guo, Yejun <yejun.guo@intel.com> | 2021-02-18 09:59:37 +0800 |
| commit | 76fc6879e2c59929e7d81a72986bb4950053177e (patch) | |
| tree | 62ac1a7bd345bfe6fd06f15113b1d46e466413ee /libavfilter/vf_sr.c | |
| parent | bdce6361004b3a24082e00b6c0126e2694a65b50 (diff) | |
dnn: add function type for model
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>
Diffstat (limited to 'libavfilter/vf_sr.c')
| -rw-r--r-- | libavfilter/vf_sr.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/libavfilter/vf_sr.c b/libavfilter/vf_sr.c index 20334a84c4..45f941acdb 100644 --- a/libavfilter/vf_sr.c +++ b/libavfilter/vf_sr.c @@ -63,7 +63,7 @@ AVFILTER_DEFINE_CLASS(sr); static av_cold int init(AVFilterContext *context) { SRContext *sr_context = context->priv; - return ff_dnn_init(&sr_context->dnnctx, context); + return ff_dnn_init(&sr_context->dnnctx, DFT_PROCESS_FRAME, context); } static int query_formats(AVFilterContext *context) |