Inversion goes to collapse about idinvert HOT 7 CLOSED

In this case, you could decrease the --learning_rate (i.e., ten times smaller) in invert.py. By the way, we have updated the encoder network and its weight in the repo, you could try it without adjusting the learning rate.

from idinvert.

@zhujiapeng
After updating the new encoder network and its weight, I got the following error. Did you encounter this problem?
ModuleNotFoundError: No module named 'tensorflow.contrib.nccl

from idinvert.

We added Synchronized BatchNorm in the encoder, it will use nccl in TensorFlow, the tf version I trained encoder is 1.12, so you need to change the tf version to 1.12.

from idinvert.

@zhujiapeng
Thank you for your quickly reply. I currently use TensorFlow 1.14.0, I will try it on 1.12. 👍

from idinvert.

@zhujiapeng
I success to run the new model using TF 1.12.2 as your suggestion.
Even though the image, 00015.png still has a similar problem, for others the new model improves a lot. Great work! I will close this issue.

from idinvert.

@ChengBinJin
I picked the wrong model when uploading, I have updated it, sorry about that.
The new model's inversion results show as follows, but this problem may happen on some other images, this caused by the small batch size when training the encoder due to our GPU memory. Anyway, thank you for testing our model!

from idinvert.

@zhujiapeng
I tested the new model again, now the results are exactly the same as yours! Great work!

from idinvert.