-
-
Notifications
You must be signed in to change notification settings - Fork 3
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
🚸 Walkthrough on object detection with bounding boxes #49
Commits on Sep 2, 2022
-
Configuration menu - View commit details
-
Copy full SHA for 1aad0e1 - Browse repository at this point
Copy the full SHA 1aad0e1View commit details -
🚧 Walkthrough on object detection with bounding boxes
Initial draft tutorial on preparing vector bounding box labels for an object detection task. Will be looking at building footprints over Kampong Ayer, Brunei on ESRI World Imagery. Also added intersphinx links for contextily and numpy.
Configuration menu - View commit details
-
Copy full SHA for 2eabb29 - Browse repository at this point
Copy the full SHA 2eabb29View commit details
Commits on Sep 3, 2022
-
Fsspec-compatible Azure Datalake and Azure Blob Storage access!
Configuration menu - View commit details
-
Copy full SHA for d9fe8cc - Browse repository at this point
Copy the full SHA d9fe8ccView commit details -
📝 Writeup section on loading GeoParquet files
Show how to load the Microsoft Building Footprints from GeoParquet files! Using `geopandas.read_parquet` for now (should it become a DataPipe?) to demonstrate things work. Have tried `pyogrio.read_dataframe(asset.href)` but got `DataSourceError: abfs://footprints/global/2022-07-06/ml-buildings.parquet/RegionName=Brunei: No such file or directory`. Might need to figure out https://gdal.org/user/virtual_file_systems.html#vsiadls auth issues somehow.
Configuration menu - View commit details
-
Copy full SHA for ea5a7b0 - Browse repository at this point
Copy the full SHA ea5a7b0View commit details
Commits on Sep 4, 2022
-
📝 Writeup section on georeferencing numpy.ndarray image
Show how to turn a numpy.ndarray image into an xarray.DataArray grid with coordinates assigned. Had to first change the image from channel-last to channel-first format (Pytorch/Chainer style) and drop the alpha channel (since there's no mask anyway. Afterwards is just setting the coordinates with xarray/rioxarray.
Configuration menu - View commit details
-
Copy full SHA for ae0c0f6 - Browse repository at this point
Copy the full SHA ae0c0f6View commit details
Commits on Sep 5, 2022
-
🔀 Merge branch 'main' into object-detection-boxes
New GeoPandasRectangleClipper DataPipe to use!
Configuration menu - View commit details
-
Copy full SHA for baf9bdf - Browse repository at this point
Copy the full SHA baf9bdfView commit details
Commits on Sep 6, 2022
-
📝 Writeup section on pairing sliced chips with clipped vectors
Show how to use small chips (generated with xbatcher) as masks to clip an input vector geometry. Included an important note that GeoPandasRectangleClipper only works with one global vector database, but it will reproject and clip to each chip's crs and bounding box extent. Showed a side by side image and vector polygon visualization, and did a bit of Brunei Tourism marketing 😆 Also had to change `.rio.set_crs` to `.rio.write_crs` to preserve the crs property on xbatcher slicing.
Configuration menu - View commit details
-
Copy full SHA for 4b979ff - Browse repository at this point
Copy the full SHA 4b979ffView commit details -
📝 Writeup section on converting geo polygons to image coord boxes
Show how to turn things upside down! First step is to derive geographic bounding boxes from the polygons. Second step is to convert the boxes from geographical coordinates to image/pixel coordinates. Also added an intersphinx link for torchvision to reference the `torchvision.ops.box_convert` function.
Configuration menu - View commit details
-
Copy full SHA for 5a61d0e - Browse repository at this point
Copy the full SHA 5a61d0eView commit details
Commits on Sep 7, 2022
-
📝 Writeup final section on batching, dataloading and georeferencing
Show how to create a list of bounding box tensors, looping over batches of object detection data, and georeferencing of the 'predicted' output. Metadata is critical to tie everything together! Also added an intersphinx link for mmdetection, shoutout to their fantastic Model Zoo!
Configuration menu - View commit details
-
Copy full SHA for 1ce268c - Browse repository at this point
Copy the full SHA 1ce268cView commit details