adaptive-style-transfer
adaptive-style-transfer copied to clipboard
CompVis
source code for the ECCV18 paper A Style-Aware Content Loss for Real-time HD Style Transfer
Hello, Been running this lovely code in google colab. However, python 2 is going away this month, and there are various dependencies (around scipy.misc.imread, for example) that cause issues in...
[] Reading latest checkpoint from folder ./models\model_van-gogh_new\checkpoint. [] Reading latest checkpoint from folder ./models\model_van-gogh_new\checkpoint_long. [!] Load failed... 0%| | 0/300000 [00:00
After start: Limit: 3210821632 InUse: 3142544896 MaxInUse: 3166815232 NumAllocs: 1714 MaxAllocSize: 688914432 Then the system show that : Hint: If you want to see a list of allocated tensors when...
hello, I am very instrested in you excellent job about the style transfer of ECCV2018. but I am puzzled about the hyperparameter of the other style datasets such as gauguin,...
How are the results if training on less than 100 GB of images? If reasonable, is it possible to get an archive of some sampled set (5-10%) of these images...
I have trained the model using another content dataset with the given styles images of Monet, but it seems it will soon collapse and output entirely black stylized images. I've...
Hi, I find a problem as follows when I test your program. I hope your help. Thank you very much. Traceback (most recent call last): File "main.py", line 149, in...
There are some problems as follows. 1. In the line 177 of "model.py", I think that self.gener_loss should be divided by float(len(scale_weight.keys())). Thus we have the whole average value of...
Hello, Anyone have this running in colab these days? I ran into some issues with current versions of tensorflow, wondering if any has solved them? Thanks!