Closed fengyuentau closed 5 years ago
@fengyuentau The 577.0 is experimented in CAFFE and the other framework may not have the same limitation. During using PyTorch, we use anthor limitation from the GPU memory.
I thought the number might be related to the model structure. Anyway, thanks for your answer.
I read the wider face test code in the
wider_test.py
, where the calculation ofmax_im_shrink
is:I am confused with the number
577.0
. From the comment of the above line of code, https://github.com/sfzhang15/SFD/issues/21#issue-306633279 and https://github.com/BVLC/caffe/issues/3084#issue-107192046, I found it could be related to the code from caffe. However, the comments I found still cannot explain why577.0
is used. Could you explain why577.0
?I also found this metric is used in recent face detection models even if the framework is not Caffe:
200.0
is used instead of577.0
)