Stylized-ImageNet icon indicating copy to clipboard operation
Stylized-ImageNet copied to clipboard

docker image missing requirements

Open kiranchari opened this issue 5 years ago • 7 comments

Hi, fyi - the docker image did not have tensorboardX installed and also, protobuf needed to be updated to version 3.6.0. This was causing errors.

Also, roughly how long does it take for create_stylized_imagenet.sh to complete?

Thanks!

kiranchari avatar Jul 25 '19 10:07 kiranchari

Thanks for pointing this out, I'll have a look at the docker image. I'd say it took a bit less than a day on a single GPU to create Stylized-ImageNet.

rgeirhos avatar Jul 25 '19 11:07 rgeirhos

Hey Robert, a question about the "Content-style trade-off" option in the original ADAIN repo..it looks like you're using a default value of 1.0 for alpha? https://github.com/rgeirhos/Stylized-ImageNet/blob/master/code/adain.py#L224

Can I change that default value to modify alpha? Thanks

kiranchari avatar Aug 19 '19 04:08 kiranchari

The answer is yes to both questions: I'm using alpha = 1.0 but it's absolutely fine to change that value depending on your needs.

rgeirhos avatar Aug 19 '19 05:08 rgeirhos

Did the docker image work with those changes? I am still struggling to get this working.

kahnchana avatar Apr 18 '21 13:04 kahnchana

@kiranchari how did you get the docker image to work. I have pulled bethgelab/deeplearning:cuda10.0-cudnn7-12_2019 but when I run it I get the error [C 11:17:16.512 NotebookApp] Running as root is not recommended. Use --allow-root to bypass.

KeyaPatani717 avatar Apr 05 '22 11:04 KeyaPatani717

Did the docker image work with those changes? I am still struggling to get this working.

No it isn't working for me. Even after installing tensorboardX, it wasn't working

Vashi1 avatar Apr 15 '24 12:04 Vashi1

Did the docker image work with those changes? I am still struggling to get this working.

No it isn't working for me. Even after installing tensorboardX, it wasn't working

File "/usr/local/lib/python3.6/dist-packages/tensorboardX/proto/resource_handle_pb2.py", line 22, in <module>
    serialized_pb=_b('\n(tensorboardX/proto/resource_handle.proto\x12\x0ctensorboardX\"r\n\x13ResourceHandleProto\x12\x0e\n\x06\x64\x65vice\x18\x01 \x01(\t\x12\x11\n\tcontainer\x18\x02 \x01(\t\x12\x0c\n\x04name\x18\x03 \x01(\t\x12\x11\n\thash_code\x18\x04 \x01(\x04\x12\x17\n\x0fmaybe_type_name\x18\x05 \x01(\tB/\n\x18org.tensorflow.frameworkB\x0eResourceHandleP\x01\xf8\x01\x01\x62\x06proto3')
TypeError: __new__() got an unexpected keyword argument 'serialized_options'

This Is the error I'm getting

Vashi1 avatar Apr 15 '24 12:04 Vashi1