Re: [FFmpeg-devel] [PATCH V2 5/7] libavfilter/dnn: avoid memcpy for tensorflow dnn output

2019-04-29 Thread Pedro Arthur
Em qua, 24 de abr de 2019 às 23:14, Guo, Yejun escreveu: > > use TF_Tensor's cpu address to avoid extra memcpy. > > Signed-off-by: Guo, Yejun > --- > libavfilter/dnn_backend_tf.c | 36 > libavfilter/vf_sr.c | 3 --- > 2 files changed, 12 insertions(

[FFmpeg-devel] [PATCH V2 5/7] libavfilter/dnn: avoid memcpy for tensorflow dnn output

2019-04-24 Thread Guo, Yejun
use TF_Tensor's cpu address to avoid extra memcpy. Signed-off-by: Guo, Yejun --- libavfilter/dnn_backend_tf.c | 36 libavfilter/vf_sr.c | 3 --- 2 files changed, 12 insertions(+), 27 deletions(-) diff --git a/libavfilter/dnn_backend_tf.c b/libavfil