-
Notifications
You must be signed in to change notification settings - Fork 31
Integrate training from sbb pixelwise segmentation #187
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
Add LICENSE
Update README.md
continue training, loss functions, rotation and ...
Perfect!
Correct. eynollah/docs/train.md supersedes all other versions and wikis.
This is already part of The intention was to make the main README.md shorter and cleaner and separate more specific documentation into their own Markdown files - and stop using the Wiki but include all relevant docs as part of the codebase.
👍 |
i.e. `pip install "eynollah[training]"` will install the requirements for training
…ttps://github.com/qurator-spk/eynollah into integrate-training-from-sbb_pixelwise_segmentation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
All good to go now, thx!
…on as in eynollah proper
This merges the
unifying-training-models
branch of https://github.com/qurator-spk/sbb_pixelwise_segmentation into the foldertrain
, so we have everything needed for running and training eynollah's components in a single place.I did the merge with:
So, all the commits of
sbb_pixelwise_segmentation
are included in eynollah's git history now.I struggled with the documentation, though. The documentation on training models was in different states in three places AFAICS: sbb_pixelwise_segmentation.wiki,
train.md
in sbb_pixelwise_segmentation and indocs/train.md
in eynollah. I did align the texts syntactically to compare and decided thatdocs/train.md
is the most up-to-date version, so I removed the others. While resolving thetrain.md
version, I also added the eynollah wiki page documenting (an earlier stage of) eynollah (layout
) asdocs/eynollah_layout.md
. Unless there are good reasons against, I would recommend closing that wiki and keeping all documentation in/docs
.Once we merge here, I would:
tf.keras
version that allows any input resolution and doesn't useLambda
layers sbb_pixelwise_segmentation#16)