rslearn 0.0.25__py3-none-any.whl → 0.0.27__py3-none-any.whl

rslearn/train/transforms/mask.py

@@ -1,7 +1,5 @@
 """Mask transform."""
 
-import torch
-
 from rslearn.train.model_context import RasterImage
 from rslearn.train.transforms.transform import Transform, read_selector
 
@@ -32,9 +30,7 @@ class Mask(Transform):
         self.mask_selector = mask_selector
         self.mask_value = mask_value
 
-    def apply_image(
-        self, image: torch.Tensor | RasterImage, mask: torch.Tensor | RasterImage
-    ) -> torch.Tensor | RasterImage:
+    def apply_image(self, image: RasterImage, mask: RasterImage) -> RasterImage:
         """Apply the mask on the image.
 
         Args:
@@ -44,21 +40,19 @@ class Mask(Transform):
         Returns:
             masked image
         """
-        # Tile the mask to have same number of bands as the image.
-        if isinstance(mask, RasterImage):
-            mask = mask.image
+        # Extract the mask tensor (CTHW format)
+        mask_tensor = mask.image
 
-        if image.shape[0] != mask.shape[0]:
-            if mask.shape[0] != 1:
+        # Tile the mask to have same number of bands (C dimension) as the image.
+        if image.shape[0] != mask_tensor.shape[0]:
+            if mask_tensor.shape[0] != 1:
                 raise ValueError(
                     "expected mask to either have same bands as image, or one band"
                 )
-            mask = mask.repeat(image.shape[0], 1, 1)
+            # Repeat along C dimension, keep T, H, W the same
+            mask_tensor = mask_tensor.repeat(image.shape[0], 1, 1, 1)
 
-        if isinstance(image, torch.Tensor):
-            image[mask == 0] = self.mask_value
-        else:
-            image.image[mask == 0] = self.mask_value
+        image.image[mask_tensor == 0] = self.mask_value
         return image
 
     def forward(self, input_dict: dict, target_dict: dict) -> tuple[dict, dict]:

rslearn/train/transforms/normalize.py

@@ -1,5 +1,6 @@
 """Normalization transforms."""
 
+import warnings
 from typing import Any
 
 import torch
@@ -35,14 +36,17 @@ class Normalize(Transform):
             bands: optionally restrict the normalization to these band indices. If set,
                 mean and std must either be one value, or have length equal to the
                 number of band indices passed here.
-            num_bands: the number of bands per image, to distinguish different images
-                in a time series. If set, then the bands list is repeated for each
-                image, e.g. if bands=[2] then we apply normalization on images[2],
-                images[2+num_bands], images[2+num_bands*2], etc. Or if the bands list
-                is not set, then we apply the mean and std on each image in the time
-                series.
+            num_bands: deprecated, no longer used. Will be removed after 2026-04-01.
         """
         super().__init__()
+
+        if num_bands is not None:
+            warnings.warn(
+                "num_bands is deprecated and no longer used. "
+                "It will be removed after 2026-04-01.",
+                FutureWarning,
+            )
+
         self.mean = torch.tensor(mean)
         self.std = torch.tensor(std)
 
@@ -55,92 +59,37 @@ class Normalize(Transform):
 
         self.selectors = selectors
         self.bands = torch.tensor(bands) if bands is not None else None
-        self.num_bands = num_bands
 
-    def apply_image(
-        self, image: torch.Tensor | RasterImage
-    ) -> torch.Tensor | RasterImage:
+    def apply_image(self, image: RasterImage) -> RasterImage:
         """Normalize the specified image.
 
         Args:
             image: the image to transform.
         """
-
-        def _repeat_mean_and_std(
-            image_channels: int, num_bands: int | None, is_raster_image: bool
-        ) -> tuple[torch.Tensor, torch.Tensor]:
-            """Get mean and std tensor that are suitable for applying on the image."""
-            # We only need to repeat the tensor if both of these are true:
-            # - The mean/std are not just one scalar.
-            # - self.num_bands is set, otherwise we treat the input as a single image.
-            if len(self.mean.shape) == 0:
-                return self.mean, self.std
-            if num_bands is None:
-                return self.mean, self.std
-            num_images = image_channels // num_bands
-            if is_raster_image:
-                # add an extra T dimension, CTHW
-                return self.mean.repeat(num_images)[
-                    :, None, None, None
-                ], self.std.repeat(num_images)[:, None, None, None]
-            else:
-                # add an extra T dimension, CTHW
-                return self.mean.repeat(num_images)[:, None, None], self.std.repeat(
-                    num_images
-                )[:, None, None]
+        # Get mean/std with singleton dims for broadcasting over CTHW.
+        if len(self.mean.shape) == 0:
+            # Scalar - broadcasts naturally.
+            mean, std = self.mean, self.std
+        else:
+            # Vector of length C - add singleton dims for T, H, W.
+            mean = self.mean[:, None, None, None]
+            std = self.std[:, None, None, None]
 
         if self.bands is not None:
-            # User has provided band indices to normalize.
-            # If num_bands is set, then we repeat these for each image in the input
-            # image time series.
-            band_indices = self.bands
-            if self.num_bands:
-                num_images = image.shape[0] // self.num_bands
-                band_indices = torch.cat(
-                    [
-                        band_indices + image_idx * self.num_bands
-                        for image_idx in range(num_images)
-                    ],
-                    dim=0,
+            # Normalize only specific band indices.
+            image.image[self.bands] = (image.image[self.bands] - mean) / std
+            if self.valid_min is not None:
+                image.image[self.bands] = torch.clamp(
+                    image.image[self.bands],
+                    min=self.valid_min,
+                    max=self.valid_max,
                 )
-
-            # We use len(self.bands) here because that is how many bands per timestep
-            # we are actually processing with the mean/std.
-            mean, std = _repeat_mean_and_std(
-                image_channels=len(band_indices),
-                num_bands=len(self.bands),
-                is_raster_image=isinstance(image, RasterImage),
-            )
-            if isinstance(image, torch.Tensor):
-                image[band_indices] = (image[band_indices] - mean) / std
-                if self.valid_min is not None:
-                    image[band_indices] = torch.clamp(
-                        image[band_indices], min=self.valid_min, max=self.valid_max
-                    )
-            else:
-                image.image[band_indices] = (image.image[band_indices] - mean) / std
-                if self.valid_min is not None:
-                    image.image[band_indices] = torch.clamp(
-                        image.image[band_indices],
-                        min=self.valid_min,
-                        max=self.valid_max,
-                    )
         else:
-            mean, std = _repeat_mean_and_std(
-                image_channels=image.shape[0],
-                num_bands=self.num_bands,
-                is_raster_image=isinstance(image, RasterImage),
-            )
-            if isinstance(image, torch.Tensor):
-                image = (image - mean) / std
-                if self.valid_min is not None:
-                    image = torch.clamp(image, min=self.valid_min, max=self.valid_max)
-            else:
-                image.image = (image.image - mean) / std
-                if self.valid_min is not None:
-                    image.image = torch.clamp(
-                        image.image, min=self.valid_min, max=self.valid_max
-                    )
+            image.image = (image.image - mean) / std
+            if self.valid_min is not None:
+                image.image = torch.clamp(
+                    image.image, min=self.valid_min, max=self.valid_max
+                )
         return image
 
     def forward(

rslearn/train/transforms/pad.py

@@ -50,9 +50,7 @@ class Pad(Transform):
         """
         return {"size": torch.randint(low=self.size[0], high=self.size[1], size=())}
 
-    def apply_image(
-        self, image: RasterImage | torch.Tensor, state: dict[str, bool]
-    ) -> RasterImage | torch.Tensor:
+    def apply_image(self, image: RasterImage, state: dict[str, bool]) -> RasterImage:
         """Apply the sampled state on the specified image.
 
         Args:
@@ -105,16 +103,12 @@ class Pad(Transform):
             horizontal_pad = (horizontal_half, horizontal_extra - horizontal_half)
             vertical_pad = (vertical_half, vertical_extra - vertical_half)
 
-        if isinstance(image, RasterImage):
-            image.image = apply_padding(
-                image.image, True, horizontal_pad[0], horizontal_pad[1]
-            )
-            image.image = apply_padding(
-                image.image, False, vertical_pad[0], vertical_pad[1]
-            )
-        else:
-            image = apply_padding(image, True, horizontal_pad[0], horizontal_pad[1])
-            image = apply_padding(image, False, vertical_pad[0], vertical_pad[1])
+        image.image = apply_padding(
+            image.image, True, horizontal_pad[0], horizontal_pad[1]
+        )
+        image.image = apply_padding(
+            image.image, False, vertical_pad[0], vertical_pad[1]
+        )
         return image
 
     def apply_boxes(self, boxes: Any, state: dict[str, bool]) -> torch.Tensor:

rslearn/train/transforms/resize.py

@@ -2,7 +2,6 @@
 
 from typing import Any
 
-import torch
 import torchvision
 from torchvision.transforms import InterpolationMode
 
@@ -40,32 +39,16 @@ class Resize(Transform):
         self.selectors = selectors
         self.interpolation = INTERPOLATION_MODES[interpolation]
 
-    def apply_resize(
-        self, image: torch.Tensor | RasterImage
-    ) -> torch.Tensor | RasterImage:
+    def apply_resize(self, image: RasterImage) -> RasterImage:
         """Apply resizing on the specified image.
 
-        If the image is 2D, it is unsqueezed to 3D and then squeezed
-        back after resizing.
-
         Args:
             image: the image to transform.
         """
-        if isinstance(image, torch.Tensor):
-            if image.dim() == 2:
-                image = image.unsqueeze(0)  # (H, W) -> (1, H, W)
-                result = torchvision.transforms.functional.resize(
-                    image, self.target_size, self.interpolation
-                )
-                return result.squeeze(0)  # (1, H, W) -> (H, W)
-            return torchvision.transforms.functional.resize(
-                image, self.target_size, self.interpolation
-            )
-        else:
-            image.image = torchvision.transforms.functional.resize(
-                image.image, self.target_size, self.interpolation
-            )
-            return image
+        image.image = torchvision.transforms.functional.resize(
+            image.image, self.target_size, self.interpolation
+        )
+        return image
 
     def forward(
         self, input_dict: dict[str, Any], target_dict: dict[str, Any]

rslearn/train/transforms/select_bands.py

@@ -1,9 +1,8 @@
 """The SelectBands transform."""
 
+import warnings
 from typing import Any
 
-from rslearn.train.model_context import RasterImage
-
 from .transform import Transform, read_selector, write_selector
 
 
@@ -17,60 +16,41 @@ class SelectBands(Transform):
         output_selector: str = "image",
         num_bands_per_timestep: int | None = None,
     ):
-        """Initialize a new Concatenate.
+        """Initialize a new SelectBands.
 
         Args:
-            band_indices: the bands to select.
+            band_indices: the bands to select from the channel dimension.
             input_selector: the selector to read the input image.
             output_selector: the output selector under which to save the output image.
-            num_bands_per_timestep: the number of bands per image, to distinguish
-                between stacked images in an image time series. If set, then the
-                band_indices are selected for each image in the time series.
+            num_bands_per_timestep: deprecated, no longer used. Will be removed after
+                2026-04-01.
         """
         super().__init__()
+
+        if num_bands_per_timestep is not None:
+            warnings.warn(
+                "num_bands_per_timestep is deprecated and no longer used. "
+                "It will be removed after 2026-04-01.",
+                FutureWarning,
+            )
+
         self.input_selector = input_selector
         self.output_selector = output_selector
         self.band_indices = band_indices
-        self.num_bands_per_timestep = num_bands_per_timestep
 
     def forward(
         self, input_dict: dict[str, Any], target_dict: dict[str, Any]
     ) -> tuple[dict[str, Any], dict[str, Any]]:
-        """Apply concatenation over the inputs and targets.
+        """Apply band selection over the inputs and targets.
 
         Args:
             input_dict: the input
             target_dict: the target
 
         Returns:
-            normalized (input_dicts, target_dicts) tuple
+            (input_dicts, target_dicts) tuple with selected bands
         """
         image = read_selector(input_dict, target_dict, self.input_selector)
-        num_bands_per_timestep = (
-            self.num_bands_per_timestep
-            if self.num_bands_per_timestep is not None
-            else image.shape[0]
-        )
-        if isinstance(image, RasterImage):
-            assert num_bands_per_timestep == image.shape[0], (
-                "Expect a seperate dimension for timesteps in RasterImages."
-            )
-
-        if image.shape[0] % num_bands_per_timestep != 0:
-            raise ValueError(
-                f"channel dimension {image.shape[0]} is not multiple of bands per timestep {num_bands_per_timestep}"
-            )
-
-        # Copy the band indices for each timestep in the input.
-        wanted_bands: list[int] = []
-        for start_channel_idx in range(0, image.shape[0], num_bands_per_timestep):
-            wanted_bands.extend(
-                [(start_channel_idx + band_idx) for band_idx in self.band_indices]
-            )
-
-        if isinstance(image, RasterImage):
-            image.image = image.image[wanted_bands]
-        else:
-            image = image[wanted_bands]
+        image.image = image.image[self.band_indices]
         write_selector(input_dict, target_dict, self.output_selector, image)
         return input_dict, target_dict

rslearn/train/transforms/sentinel1.py

@@ -33,31 +33,19 @@ class Sentinel1ToDecibels(Transform):
         self.from_decibels = from_decibels
         self.epsilon = epsilon
 
-    def apply_image(
-        self, image: torch.Tensor | RasterImage
-    ) -> torch.Tensor | RasterImage:
+    def apply_image(self, image: RasterImage) -> RasterImage:
         """Normalize the specified image.
 
         Args:
             image: the image to transform.
         """
-        if isinstance(image, torch.Tensor):
-            image_to_process = image
-        else:
-            image_to_process = image.image
         if self.from_decibels:
             # Decibels to linear scale.
-            image_to_process = torch.pow(10.0, image_to_process / 10.0)
+            image.image = torch.pow(10.0, image.image / 10.0)
         else:
             # Linear scale to decibels.
-            image_to_process = 10 * torch.log10(
-                torch.clamp(image_to_process, min=self.epsilon)
-            )
-        if isinstance(image, torch.Tensor):
-            return image_to_process
-        else:
-            image.image = image_to_process
-            return image
+            image.image = 10 * torch.log10(torch.clamp(image.image, min=self.epsilon))
+        return image
 
     def forward(
         self, input_dict: dict[str, Any], target_dict: dict[str, Any]

rslearn/utils/__init__.py

@@ -7,6 +7,7 @@ from .geometry import (
     PixelBounds,
     Projection,
     STGeometry,
+    get_global_raster_bounds,
     is_same_resolution,
     shp_intersects,
 )
@@ -23,6 +24,7 @@ __all__ = (
     "Projection",
     "STGeometry",
     "daterange",
+    "get_global_raster_bounds",
     "get_utm_ups_crs",
     "is_same_resolution",
     "logger",

rslearn/utils/geometry.py

@@ -116,6 +116,27 @@ class Projection:
 WGS84_PROJECTION = Projection(CRS.from_epsg(WGS84_EPSG), 1, 1)
 
 
+def get_global_raster_bounds(projection: Projection) -> PixelBounds:
+    """Get very large pixel bounds for a global raster in the given projection.
+
+    This is useful for data sources that cover the entire world and don't want to
+    compute exact bounds in arbitrary projections (which can fail for projections
+    like UTM that only cover part of the world).
+
+    Args:
+        projection: the projection to get bounds in.
+
+    Returns:
+        Pixel bounds that will intersect with any reasonable window. We assume that the
+        absolute value of CRS coordinates is at most 2^32, and adjust it based on the
+        resolution in the Projection in case very fine-grained resolutions are used.
+    """
+    crs_bound = 2**32
+    pixel_bound_x = int(crs_bound / abs(projection.x_resolution))
+    pixel_bound_y = int(crs_bound / abs(projection.y_resolution))
+    return (-pixel_bound_x, -pixel_bound_y, pixel_bound_x, pixel_bound_y)
+
+
 class ResolutionFactor:
     """Multiplier for the resolution in a Projection.