In producer.py, the docstring for make_ref() says:
ctx_mode: (str) The method used to define the context region around
the target, options are ['max', 'mean'], where 'max' simply takes
the largest of the two dimensions of the bounding box and mean
takes the mean.
But in producer.py:
if ctx_mode == 'max': ctx_size = max(bbox[2], bbox[3])
To match what I think the docstring is saying, I tried to changed ctx_size to the max of width and height:
if ctx_mode == 'max': ctx_size = max(bbox[2] - bbox[0], bbox[3] - bbox[1])
But program crashes. Can you let me know if I am interpreting the docstring properly? Thanks.
In producer.py, the docstring for make_ref() says:
But in producer.py:
if ctx_mode == 'max': ctx_size = max(bbox[2], bbox[3])
To match what I think the docstring is saying, I tried to changed ctx_size to the max of width and height:
if ctx_mode == 'max': ctx_size = max(bbox[2] - bbox[0], bbox[3] - bbox[1])
But program crashes. Can you let me know if I am interpreting the docstring properly? Thanks.