mxnet-finetuner docker-compose error

I am getting this error. Can you please help?

ERROR: Version in "./docker-compose.yml" is unsupported. You might be seeing this error because you're using the wrong Compose file version. Either specify a version of "2" (or "2.0") and place your service definitions under the services key, or omit the version key and place your service definitions at the root of the file to use version 1. For more on the Compose file format versions, see https://docs.docker.com/compose/compose-file/

Aug 31 '18 20:08 theprodev

Do you use mxnet-finetuner in GPU environment? In that case, you need 1.16.0 or higher version of docker-compose.

In GPU environment, the version of the automatically generated docker-compose.yml file is 2.3. In this version, version of docker-compose needs 1.16.0 or more. https://docs.docker.com/compose/compose-file/compose-versioning/#version-23

Sep 01 '18 12:09 knjcode

Thanks for the reply. I tried it on a different machine and it worked. No GPU. By the way, if I have a very small dataset of 4 images in each class and 8 classes what should be the best batch size? no. of epochs? and data_aug_level?

Is using transparent png images can improve prediction?

Sep 01 '18 15:09 theprodev

Sorry for my late reply.

I think that the number of images used for learning is quite small, so it is recommended to add images first.

And I do not know if prediction will improve using transparent PNG images.

Oct 15 '18 14:10 knjcode