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.

Sign up for GitHub

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

Jump to bottom

Add plot method and new band names for Sen12MS dataset #320

Closed
wants to merge 27 commits into from
Closed

Add plot method and new band names for Sen12MS dataset #320

wants to merge 27 commits into from

Conversation

nilsleh
Copy link
Collaborator

@nilsleh nilsleh commented Dec 21, 2021

Add plot method to Sen12MS dataset, as well as passing band names as Tuple(str) as mentioned in #289.

TODO/Questions:

  • the mask in this dataset has 4 channels that represent MODIS Land Cover as I understand from here, how should this be handled in the plot?
  • show example that plot method yields
  • looking at the lighting module, should both passing a tuple of strings, as well as a key word like "all", "s1", "s2" be supported?
  • Sen12ms Dataset repo mentions that there is also an extension of this dataset with a classification task. Is that something that should be added?

@adamjstewart adamjstewart added the datasets Geospatial or benchmark datasets label Dec 21, 2021
@adamjstewart adamjstewart added this to the 0.2.0 milestone Dec 21, 2021
@adamjstewart adamjstewart mentioned this pull request Dec 21, 2021
Closed
19 tasks
adamjstewart and others added 18 commits December 21, 2021 14:05
@adamjstewart
Docs: get rid of "Return type: None" for procedures with no return va…
d985f31 
…lue (microsoft#277)

* Various improvements to API docs

* Remove setting that is already the default
@RitwikGupta
Add custom RasterDataset notebook (microsoft#283)
a3f5593 
* Add custom RasterDataset notebook

* Update docs index.rst

* Update copyright, fix URL typo, and add verbose description

* Add xview3 sample data

* Update notebook

* Show simple example first, complicated example second

* Remove the second half of the notebook, can expand later
@calebrob6
Lower headers one step on tutorial notebook
5a57d6c
@adamjstewart
Move DataModules to torchgeo.datamodules (microsoft#321)
cbebc1e 
* Move DataModules to torchgeo.datamodules

* Clean up local imports
@adamjstewart
Fix new mypy warnings (microsoft#324)
3557848
@adamjstewart
Only test optional dataset deps on release branch (microsoft#327)
bae2bf1
@adamjstewart
Mark features added in #144 as new (microsoft#328)
20459d7
@adamjstewart
Move imports out of global namespace (microsoft#325)
9bc0bdb
@adamjstewart
Convert rST comments to directives
469d02c
@adamjstewart
Use labeler bot to automatically label PRs (microsoft#323)
324f0f8
@ashnair1
Update hooks (microsoft#330)
41533ff
@isaaccorley
fix imports in train.py (microsoft#332)
33efc2c
@adamjstewart
More uniform name for labeler action
0abb780
@nilsleh @calebrob6
Add plotting method for COWC dataset (microsoft#300)
45df0f8 
* plotting method cowc dataset

* boolean label for detection

* restructure plotting method

* typo

* label title not as variable

* single plot method in super class

Co-authored-by: Caleb Robinson <[email protected]>
@estherrolf @calebrob6
functionality for learning on the prior with QR loss and ChesapeakeCV…
0d4811b 
…PR data (#202)

* adding QR loss functions for learning on the prior

* chesapake learn on prior trainer with self-contained code for visualization

* adding prior dataset to the chesapeake datasets; doesn't handle downloading or anything like that yet

* updating init files to include chesapeake CVPR prior

* adding FCNModified for learning on the prior

* changing input to samplers to pass dataset instead of dataset.index

* fixing style issues

* Removing FCN_modified

* Fixing super call and mypy in FCN model

* Added learning on the prior extension

* Update tests

* Formatting

* Adding QR loss

* Added losses to docs

* Removing trainer, moving datamodule

* Combining chesapeake and chesapeake prior datamodules

* Formatting

* Test coverage

* Formatting

* Adding losses

* Re-moving the datamodules around

* Make loss function a torch Module

* Version added

* Fixed some stuff that got messed up in the rebase

* Formatting

* How'd this get there?

* Change qr losses to expect probabilities instead of log-probabilities

* Clean up test

* Rename qr loss file

* Renamed test file

Co-authored-by: Caleb Robinson <[email protected]>
@calebrob6
Add plot method to ADVANCE, BeninSmallHolderCashews, and BigEarthNet …
7ad3194 
…datasets (microsoft#264)

* Adding plot to ADVANCE dataset

* Adding plot to BeninSmallHolderCashews

* Adding plot to BigEarthNet

* Doctstring adjustment for BigEarthNet plot

* Cleaning up ugly test

* Cleaning up bigearthnet classes

* Added time step plot to benin_cashews

* Formatting

* Update benin cashew tests

* Add S1 plotting and type to np.ndarray

* Trying numpy with quotes
@calebrob6
Quick fix for losses docs (microsoft#333)
f18c428 
* Fix doc link

* Brute forcing rst syntax

* Adding more docs to ChesapeakeCVPR
@nilsleh
testing real data
0f969d3
@github-actions github-actions bot added the testing Continuous integration testing label Dec 29, 2021
adamjstewart
adamjstewart requested changes Dec 29, 2021
View reviewed changes
torchgeo/datasets/sen12ms.py Show resolved Hide resolved
torchgeo/datasets/sen12ms.py Outdated Show resolved Hide resolved
torchgeo/datasets/sen12ms.py Outdated Show resolved Hide resolved
torchgeo/datasets/sen12ms.py Outdated Show resolved Hide resolved
torchgeo/datasets/sen12ms.py Outdated Show resolved Hide resolved
torchgeo/datasets/sen12ms.py Outdated Show resolved Hide resolved
torchgeo/datasets/sen12ms.py Outdated Show resolved Hide resolved
@nilsleh
Add plotting method for CV4A Kenya Crop Type Dataset (microsoft#312)
a9f004e 
* Add plotting method for CV4A Kenya Crop Type Dataset

* remove print statements, still fix test_plot

* fix rgb plot test

* fix rgb plot test

* requested changes
@adamjstewart adamjstewart marked this pull request as draft December 29, 2021 17:16
@adamjstewart
Copy link
Collaborator

Can you resolve the merge conflicts?

nilsleh and others added 2 commits December 30, 2021 12:05
@nilsleh
Add plot method to Levir, and change directory path (microsoft#335)
61e10f7 
* add plotting method

* implement test

* axis off

* prediction flag

* requested changes

* indexing fix
@adamjstewart
Refactor datamodule/model testing (microsoft#329)
744078f 
* Refactor RegressionTask testing

* Programmatically determine max value

* Refactor ClassificationTask testing

* Silence warnings

* Refactor SegmentationTask testing

* Fix training mappings

* Fix GeoDataset trainers

* Fix ETCI trainer fake data

* Update OSCD training data

* Get LandCoverAI tests to pass

* Fix OSCD checksum handling

* Fix NAIP-Chesapeake tests

* Fix OSCD tests

* Keep BoundingBox icy

* Fix other datamodules

* Fix chesapeake testing

* Refactor BYOLTask tests

* Style fixes

* Silence pytorch-lightning warnings

* Get coverage for Chesapeake CVPR prior

* Fix trainer tests
@github-actions github-actions bot added datamodules PyTorch Lightning datamodules documentation Improvements or additions to documentation losses Geospatial loss functions models Models and pretrained weights samplers Samplers for indexing datasets trainers PyTorch Lightning trainers transforms Data augmentation transforms labels Dec 30, 2021
@adamjstewart
Copy link
Collaborator

Looks like a bad rebase, this PR now modifies 300+ files.

@nilsleh
Copy link
Collaborator Author

nilsleh commented Dec 30, 2021

Should I delete this branch and open it again with the changes specific to Sen12MS?

@adamjstewart
Copy link
Collaborator

Yeah, if you don't know git well that's probably the easiest approach.

@nilsleh nilsleh mentioned this pull request Dec 31, 2021
Merged
@adamjstewart
Copy link
Collaborator

Closing in favor of #338

@adamjstewart adamjstewart removed this from the 0.2.0 milestone Dec 31, 2021
adamjstewart pushed a commit that referenced this pull request Dec 31, 2021
@nilsleh
Add plotting method and band selection to Sen12ms, replacing #320 (#338)
7d90045 
* add plot method to sen12

* tuple
yichiac pushed a commit to yichiac/torchgeo that referenced this pull request Apr 29, 2023
@nilsleh
Add plotting method and band selection to Sen12ms, replacing microsof…
1852e9e 
…t#320 (microsoft#338)

* add plot method to sen12

* tuple
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@adamjstewart adamjstewart adamjstewart requested changes

Assignees
No one assigned
Labels
datamodules PyTorch Lightning datamodules datasets Geospatial or benchmark datasets documentation Improvements or additions to documentation losses Geospatial loss functions models Models and pretrained weights samplers Samplers for indexing datasets testing Continuous integration testing trainers PyTorch Lightning trainers transforms Data augmentation transforms
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
7 participants
@nilsleh @adamjstewart @RitwikGupta @calebrob6 @ashnair1 @isaaccorley @estherrolf