Add notes about the exported ONNX model

[zhiqwang]

The ONNX model exported with yolort differs from the official one in the following three ways.

• The exported ONNX graph now supports dynamic shapes, and we use (3, H, W) as the input shape (for example (3, 640, 640)).
• We embed the pre-processing (letterbox) into the graph as well. We only require the input image to be in the RGB channel, and to be rescaled to float32 [0-1] from general uint [0-255]. The main logic we use to implement this mechanism is below. (And this plays the same role of the official letterbox, but there will be a little difference in accuracy now.)
• We embed the post-processing (nms) into the model graph, which performs the same task as non_max_suppression except for the format of the inputs. (And here the ONNX graph is required to be dynamic.)