[FFmpeg-devel] [PATCH FFmpeg 13/15] libavfilter/dnn: more common clip input dimensions to test

[FFmpeg-devel] [PATCH FFmpeg 13/15] libavfilter/dnn: more common clip input dimensions to test

[m.kaindl0208]

Try the new filters using my Github Repo https://github.com/MaximilianKaindl/DeepFFMPEGVideoClassification. 

Any Feedback is appreciated!

Signed-off-by: MaximilianKaindl <m.kaindl0208@gmail.com>
---
 libavfilter/dnn/dnn_backend_torch.cpp | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/libavfilter/dnn/dnn_backend_torch.cpp b/libavfilter/dnn/dnn_backend_torch.cpp
index c8804639d9..3100ea5afc 100644
--- a/libavfilter/dnn/dnn_backend_torch.cpp
+++ b/libavfilter/dnn/dnn_backend_torch.cpp
@@ -372,9 +372,12 @@ static int test_clip_inference(THModel *th_model, const c10::Device &device)
     // Common CLIP input dimensions to test
     std::vector<int64_t> test_dims[] = {
         {1, 3, 224, 224},
+        {1, 3, 240, 240},
         {1, 3, 256, 256},
-        {1, 3, 384, 384},
+        {1, 3, 336, 336},
         {1, 3, 378, 378},
+        {1, 3, 384, 384},
+        {1, 3, 512, 512}
     };
     bool found_dims = false;
     int64_t resolution = 0;
-- 
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".