Skip to content
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

Release 0.2 #25

Merged
merged 47 commits into from
Aug 20, 2020
Merged

Release 0.2 #25

merged 47 commits into from
Aug 20, 2020

Conversation

bcoltin
Copy link
Member

@bcoltin bcoltin commented Aug 20, 2020

No description provided.

ScottMcMichael and others added 30 commits April 14, 2020 23:04
- Added convert_image_list helper tool
- Added more options to other tools
ScottMcMichael and others added 17 commits July 8, 2020 14:09
Merge final commits from other repo.
* Remove top-level tensorflow import, add tests for this.

* Separate register_arg method for config, more flexible.
* Add option to stop/bypass input errors

* Make stop on input error defalt true
* Support worldview files with subdirectories of same name.

* Fix memory use in classify.
* Added script to display the number of labels in a label geotif image and how many times each label shows up

* Added a script to extract neural network specification from .h5 files into DELTA yaml config files
* Move classes from network to dataset.

* Extended classes config for colors and names and arbitrary numbers.

* Ignore nodata labelled pixels in predict evaluation.
Also fix bug causing crash with validation.
Modified: the caching for the worldview images.
Right now it assumes that the zip files that contain the .tif files will be named with a particular format.
I changed it to query the zipfile for *.tif files, and if there is one (and only one) in there, queries that file name for
the date, sensor, etc.
@bcoltin bcoltin merged commit fa19528 into master Aug 20, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants