As seen in this automated test, there is a bug in the FID calculation with scipy 1.11.2: https://github.com/facebookresearch/NeuralCompression/actions/runs/5905240241/job/16018960652 This bug results in a huge imaginary component from the sqrtm operation. scipy 1.11.1 fixes the problem, so I'm adding this as a test requirement for now.
As seen in this automated test, there is a bug in the FID calculation with scipy 1.11.2:
https://github.com/facebookresearch/NeuralCompression/actions/runs/5905240241/job/16018960652
This bug results in a huge imaginary component from the sqrtm operation.
scipy 1.11.1 fixes the problem, so I'm adding this as a test requirement for now.