if it is not initialized with zero, the tensorflow lib will report error message such as: Attempt to add output -7920 of depth_to_space4 not in range [0, 1) to node with type Identity
Signed-off-by: Guo, Yejun <yejun....@intel.com> --- libavfilter/dnn/dnn_backend_tf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/libavfilter/dnn/dnn_backend_tf.c b/libavfilter/dnn/dnn_backend_tf.c index ba959ae..ca7434a 100644 --- a/libavfilter/dnn/dnn_backend_tf.c +++ b/libavfilter/dnn/dnn_backend_tf.c @@ -490,6 +490,7 @@ static DNNReturnType load_native_model(TFModel *tf_model, const char *model_file op_desc = TF_NewOperation(tf_model->graph, "Identity", "y"); input.oper = op; + input.index = 0; TF_AddInput(op_desc, input); TF_FinishOperation(op_desc, tf_model->status); if (TF_GetCode(tf_model->status) != TF_OK){ -- 2.7.4 _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".