/home/featurize/work/ldm/lib/python3.8/site-packages/numpy/core/fromnumeric.py:3474: RuntimeWarning: Mean of empty slice.
return _methods._mean(a, axis=axis, dtype=dtype,
/home/featurize/work/ldm/lib/python3.8/site-packages/numpy/core/_methods.py:181: RuntimeWarning: invalid value encountered in true_divide
ret = um.true_divide(
/home/featurize/work/ldm/lib/python3.8/site-packages/numpy/lib/function_base.py:495: RuntimeWarning: Mean of empty slice.
avg = a.mean(axis)
/home/featurize/work/ldm/lib/python3.8/site-packages/pytorch_gan_metrics/utils.py:282: RuntimeWarning: Degrees of freedom <= 0 for slice
sigma = np.cov(acts, rowvar=False)
/home/featurize/work/ldm/lib/python3.8/site-packages/numpy/lib/function_base.py:2680: RuntimeWarning: divide by zero encountered in true_divide
c *= np.true_divide(1, fact)
/home/featurize/work/ldm/lib/python3.8/site-packages/numpy/lib/function_base.py:2680: RuntimeWarning: invalid value encountered in multiply
c *= np.true_divide(1, fact)
Still I got a statistics.npz. However, I am not sure if it is correct. What's wrong with it?
When computing FID with following cmd:
I got this traceback.
Still I got a statistics.npz. However, I am not sure if it is correct. What's wrong with it?