kwotsin
The value is different as it was based upon the original torch implementation of the ENet authors (see references in README).
@dreambear1234 Unfortunately I've not yet have the time to test this out - have you experimented with the value you chosen and see if it results in a better performance?...
Do you specifically refer to line 91 where the median is divided by `sum(j)`?
Are you trying to perform the XLA AOT compilation? Can you elaborate on what you mean by "it cannot target that layer as output"?
For reproducing the 21.7 score, unfortunately I was not able to get exactly that score, and I think it is expected because FID produces highly biased estimates depending on the...