Closed jinuhwang closed 1 year ago
Hi, yes, the model takes the original pixel values ranging from 0 to 255 as the inputs. This is aligned with YOLOX, which does not use any normalization.
@MasterBin-IIAU Thank you for the clarification, I really appreciate it.
Hi,
While following along the
inference.py
code to see how the model is working, I noticed something in the preprocessing code.PreprocessorX
atexternal/lib/test/tracker/unicorn_sot.py:111
turns RGB format back to BGR format and the normalization process is missing. Theself.normalize
is not referenced at all as well. So the input seems to be raw image in BGR format with values between range [0, 255].I wasn't able to find any code that performs normalization in the
forward
functions of the inner models as well. Is it just that the model was trained on raw pixel values or am I missing anything?