Closed wonkyoc closed 2 years ago
The difference mainly comes from warmup stage. The warmup drastically reduces processing time. https://github.com/google/automl/blob/3bdff765d63113de7e5934868d2a1ef630e2b3d2/efficientdet/model_inspect.py#L397-L400
It is true that --runmode=bm
benefits from warmup but there is no benefit on --runmode=saved_model_benchmark
. I suspect that using an actual pre-trained model in --runmode=saved_model_benchmark
increases latency but not in --runmode=bm
Okay. I missed the section 4 in README.md. The "bm" one only takes network latency and the "saved_model_benchmark" processes end-to-end so it definitely differs from each other.
tensorflow==2.9.1 cuda==11.7 gpu==GTX1080Ti
Exp 1
Exp 2
Is a latency of EfficientDet determined by the complexity of an image vector? Since the first exp uses a real image, I assume that this may take longer than the second one. But still, the gap is quite high. Is this a normal result?