how long for training in Colab?

[pamruta]

I am trying to run it in Google Colab. Just wondering how long the style.py should take for training with GPU runtime?

[darkmarthur]

Have you been able to run it in colab?

[JackGuogit]

NO！there is an error！

tensorflow.python.framework.errors_impl.DataLossError: Unable to open table file D:\fast-style-transfer-master\examples\style\wave.jpg: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator? [[node save/RestoreV2 (defined at evaluate.py:94) ]]

I am learning related knowledge, the solution I found is: replace model.ckpt the model.ckpt.data-00000-of-00001

发送自 Windows 10 版邮件应用

发件人: Mario Ricardo Dominguez Quiroz 发送时间: 2020年4月11日 2:40 收件人: lengstrom/fast-style-transfer 抄送: Subscribed 主题: Re: [lengstrom/fast-style-transfer] how long for training in Colab?(#231)

Have you been able to run it in colab? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.

[satoshiSchubert]

OOM Error

[PGG-DeepAI]

For OOM errors, reduce batch size and/or reduce input size of image/videos as the output size will match the input sizes and so do the layers shapes.

[yaroslavmavliutov]

It takes for me on Colab about 4 hours using default parameters

[darkmarthur]

Has somebody find out the limit of the limit size of the images that this project support?