Benchmark.evaluate has a bug

trevor-m / tensorflow-SRGAN

Tensorflow implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network" (Ledig et al. 2017)

MIT License

39 stars 14 forks source link

Closed trevor-m closed 6 years ago

trevor-m commented 6 years ago

Benchmarks work for validate() when the comparison images are loaded from disk, but there is a bug when using the model output.