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

[WiP] Segmentation #321

Closed
wants to merge 11 commits into from
Closed

Conversation

jamesmcclain
Copy link
Contributor

@jamesmcclain jamesmcclain commented Jul 18, 2018

  1. Requires Segmentation: Chips and Training #337
  2. Complete or remove instance segmentation
  3. Semantic segmentation
    • Deeplap
      • Protobuf
      • Configuration
        • Backend configuration
        • Workflow configuration
      • Label store
      • Task
      • Backend
      • compute_raster_stats
      • make_training_chips
      • train
      • predict
      • eval
  4. Ensure remote operation
  5. Prediction packages
  6. Unit tests
  7. Review

@jamesmcclain jamesmcclain force-pushed the segmentation branch 5 times, most recently from 7bfcb0f to 5293bff Compare July 23, 2018 17:17
@jamesmcclain
Copy link
Contributor Author

As an initial step, labeled pixels are rendered in black (that will change later).

13
31
69

Copy link
Contributor

@lewfish lewfish left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Took a quick look and things seem to be going well.


def get_train_windows(self, scene, options):
raster_source = scene.raster_source
meta = raster_source.image_dataset.meta
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could use RasterSource.get_extent() instead

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you


windows = []
for i in range(100): # XXX insensitive
xmin = np.random.randint(low=0, high=width-chip_size)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could use extent.make_random_square() instead.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you

@jamesmcclain jamesmcclain force-pushed the segmentation branch 3 times, most recently from a99bef8 to 7455763 Compare July 26, 2018 16:28
@jamesmcclain
Copy link
Contributor Author

Will reopen later.

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.

None yet

3 participants