I have some questsions !!

[taki0112]

Hi

1. If you look at configs, there is no information about animal translation.
   When will you upload it?
   Is it ok to just run as hyper-parameter like edge2shoes?

2. The paper used a common gan loss
   But you used lsgan in your code. What was the difference in the results when comparing the two?

3. How many datasets did you use for edges2shoes or edges2handbags?
   In these cases, the amount is much larger than the other datasets. But did you use it all?

[mingyuliutw]

For 2, we use LSGAN as specified in Section 5.1 in the paper.
For 3, we use all the training images in the datasets for training.

[zhf459]

I failed to run the command "python test.py --config configs/edges2shoes.yaml --input inputs/edge.jpg --output_folder outputs --checkpoint models/edges2shoes.pt --a2b 1" and got an error:

Traceback (most recent call last):
  File "/home/zeng/work/pycharm/MUNIT/test.py", line 76, in <module>
    main(sys.argv)
  File "/home/zeng/work/pycharm/MUNIT/test.py", line 44, in main
    trainer.gen_a.load_state_dict(state_dict['a'])
  File "/home/zeng/.conda/envs/conda-python3/lib/python3.5/site-packages/torch/nn/modules/module.py", line 538, in load_state_dict
    .format(name))
KeyError: 'unexpected key "enc_content.model.0.norm.running_mean" in state_dict'

anything wrong? thanks.

[XiangyuWu]

@zhf459 I think you'd better check the version of the dependencies.