Optimize Preprocessing Computation¶
Model Optimizer performs preprocessing to a model. It is possible to optimize this step and improve first inference time, to do that, follow the tips bellow:
Image mean/scale parameters
Make sure to use the input image mean/scale parameters (
–mean_values) with the Model Optimizer when you need pre-processing. It allows the tool to bake the pre-processing into the IR to get accelerated by the Inference Engine.
RGB vs. BGR inputs
If, for example, your network assumes the RGB inputs, the Model Optimizer can swap the channels in the first convolution using the
--reverse_input_channelscommand line option, so you do not need to convert your inputs to RGB every time you get the BGR image, for example, from OpenCV*.
Larger batch size
Notice that the devices like GPU are doing better with larger batch size. While it is possible to set the batch size in the runtime using the Inference Engine ShapeInference feature.
Resulting IR precision
The resulting IR precision, for instance,
FP32, directly affects performance. As CPU now supports
FP16(while internally upscaling to
FP32anyway) and because this is the best precision for a GPU target, you may want to always convert models to
FP16. Notice that this is the only precision that Intel Movidius Myriad 2 and Intel Myriad X VPUs support.