I was trying to use the implementation of FID score from this resource: https://machinelearningmastery.com/how-to-implement-the-frechet-inception-distance-fid-from-scratch/ but when I run the FID score for the same vectors (act1) I expected the FID score to be 0, instead I am getting a large number. Where am I going wrong? # example of calculating the frechet inception distance import numpy from numpy import cov from numpy import trace from numpy import iscomplexobj from numpy.random import random from scipy.linalg import sqrtm # calculate frechet inception distance def calculate_fid(act1, act2): # calculate mean and covariance statistics mu1, sigma1 = act1.mean(axis=0), cov(act1, rowvar=False) mu2, sigma2 = act2.mean(axis=0), cov(act2, rowvar=False) # calculate sum squared difference between means ssdiff = numpy.sum((mu1 - mu2)**2.0) # calculate sqrt of product between cov covmean = sqrtm(sigma1.dot(sigma2)) # check and correct imaginary numbers from sqrt if iscomplexobj(covmean): covmean = covmean.real # calculate score fid = ssdiff + trace(sigma1 + sigma2 - 2.0 * covmean) return fid # define two collections of activations act1 = random(10*2048) act1 = act1.reshape((10,2048)) act2 = random(10*2048) act2 = act2.reshape((10,2048)) # fid between act1 and act1 fid = calculate_fid(act1, act1) print('FID (same): %.3f' % fid) # fid between act1 and act2 fid = calculate_fid(act1, act2) print('FID (different): %.3f' % fid) Results: FID (same): -66113130760175032991744.000 FID (different): -55213970774324510299478046898216203619608871777363092441300193790394368.000 I was expecting the fid score for the same vectors to be zero but it is coming up as large number which was contrary to what I understood of FID scores and what is demonstrated in the source linked above. Continue reading...
