Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
 help / color / mirror / Atom feed
From: wenbin.chen-at-intel.com@ffmpeg.org
To: ffmpeg-devel@ffmpeg.org
Subject: [FFmpeg-devel] [PATCH v2 2/4] libavfilter/vf_dnn_detect: Add input pad
Date: Tue, 12 Dec 2023 10:33:32 +0800
Message-ID: <20231212023334.2506376-2-wenbin.chen@intel.com> (raw)
In-Reply-To: <20231212023334.2506376-1-wenbin.chen@intel.com>

From: Wenbin Chen <wenbin.chen@intel.com>

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>
---
 libavfilter/dnn/dnn_backend_openvino.c | 24 ++++++++++++++++------
 libavfilter/vf_dnn_detect.c            | 28 +++++++++++++++++++++++++-
 2 files changed, 45 insertions(+), 7 deletions(-)

diff --git a/libavfilter/dnn/dnn_backend_openvino.c b/libavfilter/dnn/dnn_backend_openvino.c
index 089e028818..671a995c70 100644
--- a/libavfilter/dnn/dnn_backend_openvino.c
+++ b/libavfilter/dnn/dnn_backend_openvino.c
@@ -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;
         }
diff --git a/libavfilter/vf_dnn_detect.c b/libavfilter/vf_dnn_detect.c
index 373dda58bf..86f61c9907 100644
--- a/libavfilter/vf_dnn_detect.c
+++ b/libavfilter/vf_dnn_detect.c
@@ -699,13 +699,39 @@ 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,
-- 
2.34.1

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".

  reply	other threads:[~2023-12-12  2:34 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-12-12  2:33 [FFmpeg-devel] [PATCH v2 1/4] libavfiter/dnn_backend_openvino: Add multiple output support wenbin.chen-at-intel.com
2023-12-12  2:33 ` wenbin.chen-at-intel.com [this message]
2023-12-12  2:33 ` [FFmpeg-devel] [PATCH v2 3/4] libavfilter/vf_dnn_detect: Add yolov3 support wenbin.chen-at-intel.com
2023-12-12  2:33 ` [FFmpeg-devel] [PATCH v2 4/4] libavfilter/vf_dnn_detect: Add yolov4 support wenbin.chen-at-intel.com
2023-12-15 12:45 ` [FFmpeg-devel] [PATCH v2 1/4] libavfiter/dnn_backend_openvino: Add multiple output support Guo, Yejun

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20231212023334.2506376-2-wenbin.chen@intel.com \
    --to=wenbin.chen-at-intel.com@ffmpeg.org \
    --cc=ffmpeg-devel@ffmpeg.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://master.gitmailbox.com/ffmpegdev/0 ffmpegdev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 ffmpegdev ffmpegdev/ https://master.gitmailbox.com/ffmpegdev \
		ffmpegdev@gitmailbox.com
	public-inbox-index ffmpegdev

Example config snippet for mirrors.


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git