yaxingwang

Thank you @taki0112, I use the dataset [online](http://www.robots.ox.ac.uk/~vgg//data/pets/) where you can download and crop the animal face based on the annotation and resize 128*128, and also collect from the other...

Ok, let's wait for the final result from my experiment. If you can try, I can share the dataset with you later.

Hi, I have got the latest result which is as following: cat--->dog:  dog--->cat:  There are some reasons for this result is like: 1. the domain A and B...

Hi, I use the same parameter from your file for the animal. I guess the hyper-parameter could be different.

Hi @xiang-zhe, I tried the official code of MUNIT, it works well. I also experienced a similar condition to you. The following translation is from cat2tiger  Maybe there are...

The cat2tiger is also tried on this project(taki0112), which fails.

Thanks. I am checking one by one. It is vary helpful if you can point which parts. In fact, I also reset Lr(G, D) to 0., and only train one...

@VincieD, I have fixed it. In _get_data_loaders_ of utils.py, you should set **start_itr = 0** when you use pretrained model, since using pretrained model, it is not 0. I guess...

The original setting is fine-tunning. The key point is about computing resource. If you conduct papally it with Multi-GPUs, results is interesting. Otherwise, using one GPU(12G) is difficulty. In fact,...

Let me know if you have new insight when you train.