search

TachibanaYoshino / AnimeGAN

A Tensorflow implementation of AnimeGAN for fast photo animation ! This is the Open source of the paper 「AnimeGAN: a novel lightweight GAN for photo animation」, which uses the GAN framwork to transform real-world photos into anime images.
4.49k stars 660 forks source link

i got this error #10

Closed stringk245 closed 4 years ago

stringk245 commented 4 years ago

File "D:\develop\workspace\AnimeGAN\AnimeGAN.py", line 232, in train anime, anime_smooth, real = self.sess.run([anime_img_op, anime_smooth_op, real_img_op])

tensorflow.python.framework.errors_impl.InvalidArgumentError: [Derived]buffer_size must be greater than zero. [[{{node OptimizeDataset/ShuffleDataset}}]] [[OneShotIterator]]

TachibanaYoshino commented 4 years ago

Check the data loader and note the batch size

jaysimon commented 4 years ago

@TonyK-T Have you solved the problem? I met this too.