TOKUNAGA Hiroyuki

As a long term vision, I think introducing a new class for Tensor is a good idea. On the other hand, it might be possible to implement `Split` operator by...

> Since it will have similar issues as #377 . I worry that they can not support various tasks in future. Actually I want to rewrite them using cv2. 🤔...

> I think data augmentation will only be used in training environment, does it matter only add them into training dependency? Considering that adding a dependency to OpenCV will increase...

> I just worry if it will make graph more complicated and we may need to define a clean name_scope to make it easy to compile. I think we can...

Short answer is, not enough. - `lmnet/lmnet/common.py` defines a color map for label coloring, it's for object detection and semantic segmentation. It's widely used in the Blueoil. - `lmnet/lmnet/networks/classification/base.py` uses...

`PerImageStandardization` is still not possible to apply in the `blueoil init` command. I think it's better to keep this issue for now.

I would like to know more about the second solution to prevent misunderstanding. Do you intend to create a new binary file and load data from the file? Or do...

I see. I agree to your idea. Are you already working on this issue? If you haven't, would you mind if I worked on it?

OK, I'll try.