Can't run the test code

[hellowangfeng]

when I finished BEGAN training with my own dataset, I get the following error when I run the test code as follows: python main.py --dataset=my_dataset --load_path=my_dataset_0824_004250 --use_gpu=True --is_train=False --split valid
the error is :
ValueError: Cannot feed value of shape (32, 64) for Tensor 'random_uniform:0', which has shape '(64, 64)'
so anyone meets the same error? how to use BEGAN to generate fake images?

[AlexRoidl]

hey, I have the exact same issue!

[Aneekdas]

I have the same error as well. Any solutions?

[9icesk]

@hellowangfeng @AlexRoidl @Aneekdas
delete line 293 in trainer.py and it works
z = np.stack([slerp(ratio, r1, r2) for r1, r2 in zip(z1, z2)])
It makes z ==z1, only half of the batch_size
But I don't know whether it will influence the result

[ivanlen]

I am having the same problem.

[EASY-EAI]

I have the same error as well. Any solutions? @carpedm20