Update README.md

Author: mseitzer

README.md

@@ -4,10 +4,14 @@ This is a port of the official implementation of [Fréchet Inception Distance](h
 See [https://github.com/bioinf-jku/TTUR](https://github.com/bioinf-jku/TTUR) for the original implementation using Tensorflow.
 
 FID is a measure of similarity between two datasets of images. 
-It was shown to correlate well with human judgement of visual quality and is used most often used to evaluate the quality of samples of Generative Adversarial Networks.
+It was shown to correlate well with human judgement of visual quality and is most often used to evaluate the quality of samples of Generative Adversarial Networks.
 FID is calculated by computing the [Fréchet distance](https://en.wikipedia.org/wiki/Fr%C3%A9chet_distance) between two Gaussians fitted to feature representations of the Inception network. 
 
-Further insights and an independent evaluation of the FID score can be found in [Are GANs Created Equal? A Large-Scale Study](https://arxiv.org/pdf/1711.10337.pdf)
+Further insights and an independent evaluation of the FID score can be found in [Are GANs Created Equal? A Large-Scale Study](https://arxiv.org/abs/1711.10337).
+
+**Note that the official implementation most likely gives slightly different scores**, as it uses pretrained weights from Tensorflow 's Inception, not PyTorch's Inception as used here.
+If you report FID scores in your paper, and you want them to be comparable to FID scores reported in other papers, you should use [the official Tensorflow implementation](https://github.com/bioinf-jku/TTUR).
+You can still use this version if you want a quick FID estimate without installing Tensorflow.
 
 ## Usage
 
@@ -25,8 +29,6 @@ To compute the FID score between two datasets, where images of each dataset are
 
 To run the evaluation on GPU, use the flag `--gpu N`, where `N` is the index of the GPU to use. 
 
-Note that the official implementation might give slightly different scores, as it uses pretrained weights from Tensorflow 's Inception, not PyTorch's Inception as used here.
-
 ### Using different layers for feature maps
 
 In difference to the official implementation, you can choose to use a different feature layer of the Inception network instead of the default `pool3` layer.