Merge branch 'main' into docs/dataset_table

.gitattributes

@@ -1,2 +1,4 @@
 # Do not change line endings on test data, it will change the MD5
-/tests/data/*/** binary
+/tests/data/*/** -text
+# Test data generation files are fine though
+/tests/data/**/data.py text

.github/workflows/tests.yaml

@@ -59,9 +59,7 @@ jobs:
       if: ${{ runner.os == 'Windows' }}
     - name: Install conda dependencies (Windows)
       run: |
-        # PyTorch isn't compatible with setuptools 59.6+, pin for now until new PyTorch release
-        # https://github.com/pytorch/pytorch/pull/69904
-        conda install 'fiona>=1.5' h5py 'rasterio>=1.0.16' 'setuptools<59.6'
+        conda install 'fiona>=1.5' 'rasterio>=1.0.16'
         conda list
         conda info
       if: ${{ runner.os == 'Windows' }}

.pre-commit-config.yaml

@@ -24,9 +24,9 @@ repos:
             additional_dependencies: ["toml"]
 
     -   repo: https://github.com/pre-commit/mirrors-mypy
-        rev: v0.931
+        rev: v0.940
         hooks:
         -   id: mypy
             args: [--strict, --ignore-missing-imports, --show-error-codes]
-            additional_dependencies: [torch>=1.7, torchmetrics>=0.7, pytorch-lightning>=1.3, pytest>=6, omegaconf>=2.1, kornia>=0.6, numpy>=1.22.0]
+            additional_dependencies: [torch>=1.11, torchmetrics>=0.7, pytorch-lightning>=1.3, pytest>=6, omegaconf>=2.1, kornia>=0.6, numpy>=1.22.0]
             exclude: (build|data|dist|logo|logs|output)/

.readthedocs.yaml

@@ -4,6 +4,12 @@
 # Required
 version: 2
 
+# Set the version of Python
+build:
+  os: ubuntu-20.04
+  tools:
+    python: "3.9"
+
 # Configuration of the Python environment to be used
 python:
    install:

benchmark.py

@@ -208,17 +208,15 @@ def main(args: argparse.Namespace) -> None:
     # Benchmark model
     model = resnet34()
     # Change number of input channels to match Landsat
-    model.conv1 = nn.Conv2d(  # type: ignore[attr-defined]
+    model.conv1 = nn.Conv2d(
         len(bands), 64, kernel_size=7, stride=2, padding=3, bias=False
     )
 
-    criterion = nn.CrossEntropyLoss()  # type: ignore[attr-defined]
+    criterion = nn.CrossEntropyLoss()
     params = model.parameters()
     optimizer = optim.SGD(params, lr=0.0001)
 
-    device = torch.device(  # type: ignore[attr-defined]
-        "cuda" if torch.cuda.is_available() else "cpu", args.device
-    )
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu", args.device)
     model = model.to(device)
 
     tic = time.time()
@@ -227,7 +225,7 @@ def main(args: argparse.Namespace) -> None:
         num_total_patches += args.batch_size
         x = torch.rand(args.batch_size, len(bands), args.patch_size, args.patch_size)
         # y = torch.randint(0, 256, (args.batch_size, args.patch_size, args.patch_size))
-        y = torch.randint(0, 256, (args.batch_size,))  # type: ignore[attr-defined]
+        y = torch.randint(0, 256, (args.batch_size,))
         x = x.to(device)
         y = y.to(device)
 

docs/api/datasets.rst

@@ -18,11 +18,16 @@ Geospatial Datasets
    :align: center
    :file: generic_datasets.csv
 
+Aboveground Live Woody Biomass Density
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. autoclass:: AbovegroundLiveWoodyBiomassDensity
+
 Aster Global Digital Evaluation Model
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 .. autoclass:: AsterGDEM
-    
+
 Canadian Building Footprints
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
@@ -63,6 +68,16 @@ Esri2020
 
 .. autoclass:: Esri2020
 
+EU-DEM
+^^^^^^
+
+.. autoclass:: EUDEM
+
+GlobBiomass
+^^^^^^^^^^^
+
+.. autoclass:: GlobBiomass
+
 Landsat
 ^^^^^^^
 
@@ -83,6 +98,11 @@ National Agriculture Imagery Program (NAIP)
 
 .. autoclass:: NAIP
 
+Open Buildings
+^^^^^^^^^^^^^^
+
+.. autoclass:: OpenBuildings
+
 Sentinel
 ^^^^^^^^
 
@@ -239,6 +259,11 @@ UC Merced
 
 .. autoclass:: UCMerced
 
+USAVars
+^^^^^^^
+
+.. autoclass:: USAVars
+
 Vaihingen
 ^^^^^^^^^
 

docs/tutorials/trainers.ipynb

@@ -492,13 +492,13 @@
     "        csv_reader = csv.DictReader(f, delimiter=',')\n",
     "        for i, row in enumerate(csv_reader):\n",
     "            try:\n",
-    "                train_rmse.append(float(row[\"train_rmse\"]))\n",
+    "                train_rmse.append(float(row[\"train_RMSE\"]))\n",
     "                train_steps.append(i)\n",
     "            except ValueError: # Ignore rows where train RMSE is empty\n",
     "                pass\n",
     "\n",
     "            try:\n",
-    "                val_rmse.append(float(row[\"val_rmse\"]))\n",
+    "                val_rmse.append(float(row[\"val_RMSE\"]))\n",
     "                val_steps.append(i)\n",
     "            except ValueError: # Ignore rows where val RMSE is empty\n",
     "                pass"

evaluate.py

@@ -12,7 +12,7 @@
 
 import pytorch_lightning as pl
 import torch
-from torchmetrics import Accuracy, JaccardIndex, Metric, MetricCollection
+from torchmetrics import Accuracy, JaccardIndex, MetricCollection
 
 from torchgeo.trainers import ClassificationTask, SemanticSegmentationTask
 from train import TASK_TO_MODULES_MAPPING
@@ -85,19 +85,20 @@ def set_up_parser() -> argparse.ArgumentParser:
 def run_eval_loop(
     model: pl.LightningModule,
     dataloader: Any,
-    device: torch.device,  # type: ignore[name-defined]
-    metrics: Metric,
+    device: torch.device,
+    metrics: MetricCollection,
 ) -> Any:
     """Runs a standard test loop over a dataloader and records metrics.
 
     Args:
         model: the model used for inference
         dataloader: the dataloader to get samples from
         device: the device to put data on
-        metrics: a torchmetrics compatible Metric to score the output from the model
+        metrics: a torchmetrics compatible metric collection to score the output
+            from the model
 
     Returns:
-        the result of ``metric.compute()``
+        the result of ``metrics.compute()``
     """
     for batch in dataloader:
         x = batch["image"].to(device)
@@ -158,7 +159,7 @@ def main(args: argparse.Namespace) -> None:
             "loss": model.hparams["loss"],
         }
     elif issubclass(TASK, SemanticSegmentationTask):
-        val_row: Dict[str, Union[str, float]] = {  # type: ignore[no-redef]
+        val_row = {
             "split": "val",
             "segmentation_model": model.hparams["segmentation_model"],
             "encoder_name": model.hparams["encoder_name"],
@@ -167,7 +168,7 @@ def main(args: argparse.Namespace) -> None:
             "loss": model.hparams["loss"],
         }
 
-        test_row: Dict[str, Union[str, float]] = {  # type: ignore[no-redef]
+        test_row = {
             "split": "test",
             "segmentation_model": model.hparams["segmentation_model"],
             "encoder_name": model.hparams["encoder_name"],
@@ -179,7 +180,7 @@ def main(args: argparse.Namespace) -> None:
         raise ValueError(f"{TASK} is not supported")
 
     # Compute metrics
-    device = torch.device("cuda:%d" % (args.gpu))  # type: ignore[attr-defined]
+    device = torch.device("cuda:%d" % (args.gpu))
     model = model.to(device)
 
     if args.task == "etci2021":  # Custom metric setup for testing ETCI2021

setup.cfg

@@ -95,7 +95,7 @@ datasets =
 # Optional developer requirements
 style =
     # black 21+ required for Python 3.9 support
-    black>=21.4b0
+    black>=21
     # flake8 3.8+ depends on pyflakes 2.2+, which fixes a bug with mypy error code ignores:
     # https://github.com/PyCQA/pyflakes/pull/455
     flake8>=3.8

tests/data/agb_live_woody_density/Aboveground_Live_Woody_Biomass_Density.geojson

@@ -0,0 +1 @@
+{"type": "FeatureCollection", "name": "Aboveground_Live_Woody_Biomass_Density", "crs": {"type": "name", "properties": {"name": "urn:ogc:def:crs:OGC:1.3:CRS84"}}, "features": [{"type": "Feature", "properties": {"tile_id": "00N_000E", "download": "tests/data/agb_live_woody_density/00N_000E.tif", "ObjectId": 1, "Shape__Area": 1245542622548.87, "Shape__Length": 4464169.76558139}, "geometry": {"type": "Polygon", "coordinates": [[[0.0, 0.0], [10.0, 0.0], [10.0, -10.0], [0.0, -10.0], [0.0, 0.0]]]}}]}

tests/data/agb_live_woody_density/data.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python3
+
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+
+import json
+import os
+import random
+
+import numpy as np
+import rasterio
+
+SIZE = 32
+
+np.random.seed(0)
+random.seed(0)
+
+
+base_file = {
+    "type": "FeatureCollection",
+    "name": "Aboveground_Live_Woody_Biomass_Density",
+    "crs": {"type": "name", "properties": {"name": "urn:ogc:def:crs:OGC:1.3:CRS84"}},
+    "features": [
+        {
+            "type": "Feature",
+            "properties": {
+                "tile_id": "00N_000E",
+                "download": os.path.join(
+                    "tests", "data", "agb_live_woody_density", "00N_000E.tif"
+                ),
+                "ObjectId": 1,
+                "Shape__Area": 1245542622548.8701,
+                "Shape__Length": 4464169.7655813899,
+            },
+            "geometry": {
+                "type": "Polygon",
+                "coordinates": [
+                    [[0.0, 0.0], [10.0, 0.0], [10.0, -10.0], [0.0, -10.0], [0.0, 0.0]]
+                ],
+            },
+        }
+    ],
+}
+
+
+def create_file(path: str, dtype: str, num_channels: int) -> None:
+    profile = {}
+    profile["driver"] = "GTiff"
+    profile["dtype"] = dtype
+    profile["count"] = num_channels
+    profile["crs"] = "epsg:4326"
+    profile["transform"] = rasterio.transform.from_bounds(0, 0, 1, 1, 1, 1)
+    profile["height"] = SIZE
+    profile["width"] = SIZE
+    profile["compress"] = "lzw"
+    profile["predictor"] = 2
+
+    if "float" in profile["dtype"]:
+        Z = np.random.randn(SIZE, SIZE).astype(profile["dtype"])
+    else:
+        Z = np.random.randint(
+            np.iinfo(profile["dtype"]).max, size=(SIZE, SIZE), dtype=profile["dtype"]
+        )
+
+    src = rasterio.open(path, "w", **profile)
+    for i in range(1, profile["count"] + 1):
+        src.write(Z, i)
+
+
+if __name__ == "__main__":
+    base_file_name = "Aboveground_Live_Woody_Biomass_Density.geojson"
+    if os.path.exists(base_file_name):
+        os.remove(base_file_name)
+
+    with open(base_file_name, "w") as f:
+        json.dump(base_file, f)
+
+    for i in base_file["features"]:
+        filepath = os.path.basename(i["properties"]["download"])
+        create_file(path=filepath, dtype="int32", num_channels=1)

tests/data/cbf/Alberta.geojson

@@ -1,7 +1 @@
-{
-"type": "FeatureCollection",
-"crs": { "type": "name", "properties": { "name": "urn:ogc:def:crs:OGC:1.3:CRS84" } },
-"features": [
-{ "type": "Feature", "properties": { }, "geometry": { "type": "Polygon", "coordinates": [ [ [ 0.0, 0.0 ], [ 0.0, 1.0 ], [ 1.0, 1.0 ], [ 1.0, 0.0 ], [ 0.0, 0.0 ] ] ] } }
-]
-}
+{"type": "FeatureCollection", "crs": {"type": "name", "properties": {"name": "urn:ogc:def:crs:OGC:1.3:CRS84"}}, "features": [{"type": "Feature", "properties": {}, "geometry": {"type": "Polygon", "coordinates": [[[0.0, 0.0], [0.0, 1.0], [1.0, 1.0], [1.0, 0.0], [0.0, 0.0]]]}}]}