MrBesen/ffmpeg
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

libavfilter/vf_dnn_detect: Add input pad

Browse Source 
Add input pad to get model input resolution. Detection models always
have fixed input size. And the output coordinators are based on the
input resolution, so we need to get input size to map coordinators to
our real output frames.

Signed-off-by: Wenbin Chen <wenbin.chen@intel.com>
Reviewed-by: Guo Yejun <yejun.guo@intel.com>
This commit is contained in:
Wenbin Chen 2023-12-12 10:33:32 +08:00 committed by Guo Yejun
parent 22652b576c
commit da02836b9d
2 changed files with 45 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
libavfilter/dnn/dnn_backend_openvino.c
View File

@ -1073,9 +1073,15 @@ static int get_input_ov(void *model, DNNData *input, const char *input_name)
return AVERROR(ENOSYS);
}
input->channels = dims[1];
input->height = input_resizable ? -1 : dims[2];
input->width = input_resizable ? -1 : dims[3];
if (dims[1] <= 3) { // NCHW
input->channels = dims[1];
input->height = input_resizable ? -1 : dims[2];
input->width = input_resizable ? -1 : dims[3];
} else { // NHWC
input->height = input_resizable ? -1 : dims[1];
input->width = input_resizable ? -1 : dims[2];
input->channels = dims[3];
}
input->dt = precision_to_datatype(precision);
return 0;
@ -1105,9 +1111,15 @@ static int get_input_ov(void *model, DNNData *input, const char *input_name)
return DNN_GENERIC_ERROR;
}
input->channels = dims.dims[1];
input->height = input_resizable ? -1 : dims.dims[2];
input->width = input_resizable ? -1 : dims.dims[3];
if (dims[1] <= 3) { // NCHW
input->channels = dims[1];
input->height = input_resizable ? -1 : dims[2];
input->width = input_resizable ? -1 : dims[3];
} else { // NHWC
input->height = input_resizable ? -1 : dims[1];
input->width = input_resizable ? -1 : dims[2];
input->channels = dims[3];
}
input->dt = precision_to_datatype(precision);
return 0;
}

28
libavfilter/vf_dnn_detect.c
View File

@ -705,13 +705,39 @@ static av_cold void dnn_detect_uninit(AVFilterContext *context)
free_detect_labels(ctx);
}
static int config_input(AVFilterLink *inlink)
{
AVFilterContext *context = inlink->dst;
DnnDetectContext *ctx = context->priv;
DNNData model_input;
int ret;
ret = ff_dnn_get_input(&ctx->dnnctx, &model_input);
if (ret != 0) {
av_log(ctx, AV_LOG_ERROR, "could not get input from the model\n");
return ret;
}
ctx->scale_width = model_input.width == -1 ? inlink->w : model_input.width;
ctx->scale_height = model_input.height == -1 ? inlink->h : model_input.height;
return 0;
}
static const AVFilterPad dnn_detect_inputs[] = {
{
.name = "default",
.type = AVMEDIA_TYPE_VIDEO,
.config_props = config_input,
},
};
const AVFilter ff_vf_dnn_detect = {
.name = "dnn_detect",
.description = NULL_IF_CONFIG_SMALL("Apply DNN detect filter to the input."),
.priv_size = sizeof(DnnDetectContext),
.init = dnn_detect_init,
.uninit = dnn_detect_uninit,
FILTER_INPUTS(ff_video_default_filterpad),
FILTER_INPUTS(dnn_detect_inputs),
FILTER_OUTPUTS(ff_video_default_filterpad),
FILTER_PIXFMTS_ARRAY(pix_fmts),
.priv_class = &dnn_detect_class,