Stowage/ffmpeg
2
0
Fork 0
mirror of https://git.ffmpeg.org/ffmpeg.git synced 2025-12-08 06:09:50 +00:00
Code Issues Projects Releases Packages Wiki Activity

libavfilter/dnn: add more data type support for dnn model input

Browse source 
currently, only float is supported as model input, actually, there
are other data types, this patch adds uint8.

Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
This commit is contained in:
Guo, Yejun 2019-04-25 10:14:42 +08:00 • committed by Pedro Arthur
parent 25c1cd909f
commit c636dc9819
4 changed files with 39 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

4
libavfilter/vf_sr.c
View file

@ -40,7 +40,8 @@ typedef struct SRContext {
DNNBackendType backend_type;
DNNModule *dnn_module;
DNNModel *model;
DNNData input, output;
DNNInputData input;
DNNData output;
int scale_factor;
struct SwsContext *sws_contexts[3];
int sws_slice_h, sws_input_linesize, sws_output_linesize;
@ -86,6 +87,7 @@ static av_cold int init(AVFilterContext *context)
return AVERROR(EIO);
}
sr_context->input.dt = DNN_FLOAT;
sr_context->sws_contexts[0] = NULL;
sr_context->sws_contexts[1] = NULL;
sr_context->sws_contexts[2] = NULL;