rslearn 0.0.25__py3-none-any.whl → 0.0.26__py3-none-any.whl

rslearn/train/tasks/per_pixel_regression.py

@@ -66,20 +66,18 @@ class PerPixelRegressionTask(BasicTask):
             return {}, {}
 
         assert isinstance(raw_inputs["targets"], RasterImage)
-        assert raw_inputs["targets"].image.shape[0] == 1
-        assert raw_inputs["targets"].image.shape[1] == 1
-        labels = raw_inputs["targets"].image[0, 0, :, :].float() * self.scale_factor
+        labels = raw_inputs["targets"].get_hw_tensor().float() * self.scale_factor
 
         if self.nodata_value is not None:
-            valid = (
-                raw_inputs["targets"].image[0, 0, :, :] != self.nodata_value
-            ).float()
+            valid = (raw_inputs["targets"].get_hw_tensor() != self.nodata_value).float()
         else:
             valid = torch.ones(labels.shape, dtype=torch.float32)
 
+        # Wrap in RasterImage with CTHW format (C=1, T=1) so values and valid can be
+        # used in image transforms.
         return {}, {
-            "values": labels,
-            "valid": valid,
+            "values": RasterImage(labels[None, None, :, :], timestamps=None),
+            "valid": RasterImage(valid[None, None, :, :], timestamps=None),
         }
 
     def process_output(
@@ -121,7 +119,7 @@ class PerPixelRegressionTask(BasicTask):
         image = super().visualize(input_dict, target_dict, output)["image"]
         if target_dict is None:
             raise ValueError("target_dict is required for visualization")
-        gt_values = target_dict["classes"].cpu().numpy()
+        gt_values = target_dict["values"].get_hw_tensor().cpu().numpy()
         pred_values = output.cpu().numpy()[0, :, :]
         gt_vis = np.clip(gt_values * 255, 0, 255).astype(np.uint8)
         pred_vis = np.clip(pred_values * 255, 0, 255).astype(np.uint8)
@@ -210,8 +208,10 @@ class PerPixelRegressionHead(Predictor):
 
         losses = {}
         if targets:
-            labels = torch.stack([target["values"] for target in targets])
-            mask = torch.stack([target["valid"] for target in targets])
+            labels = torch.stack(
+                [target["values"].get_hw_tensor() for target in targets]
+            )
+            mask = torch.stack([target["valid"].get_hw_tensor() for target in targets])
 
             if self.loss_mode == "mse":
                 scores = torch.square(outputs - labels)
@@ -262,14 +262,14 @@ class PerPixelRegressionMetricWrapper(Metric):
         """
         if not isinstance(preds, torch.Tensor):
             preds = torch.stack(preds)
-        labels = torch.stack([target["values"] for target in targets])
+        labels = torch.stack([target["values"].get_hw_tensor() for target in targets])
 
         # Sub-select the valid labels.
         # We flatten the prediction and label images at valid pixels.
         if len(preds.shape) == 4:
             assert preds.shape[1] == 1
             preds = preds[:, 0, :, :]
-        mask = torch.stack([target["valid"] > 0 for target in targets])
+        mask = torch.stack([target["valid"].get_hw_tensor() > 0 for target in targets])
         preds = preds[mask]
         labels = labels[mask]
         if len(preds) == 0:

rslearn/train/tasks/segmentation.py

@@ -128,9 +128,7 @@ class SegmentationTask(BasicTask):
             return {}, {}
 
         assert isinstance(raw_inputs["targets"], RasterImage)
-        assert raw_inputs["targets"].image.shape[0] == 1
-        assert raw_inputs["targets"].image.shape[1] == 1
-        labels = raw_inputs["targets"].image[0, 0, :, :].long()
+        labels = raw_inputs["targets"].get_hw_tensor().long()
 
         if self.class_id_mapping is not None:
             new_labels = labels.clone()
@@ -146,9 +144,11 @@ class SegmentationTask(BasicTask):
         else:
             valid = torch.ones(labels.shape, dtype=torch.float32)
 
+        # Wrap in RasterImage with CTHW format (C=1, T=1) so classes and valid can be
+        # used in image transforms.
         return {}, {
-            "classes": labels,
-            "valid": valid,
+            "classes": RasterImage(labels[None, None, :, :], timestamps=None),
+            "valid": RasterImage(valid[None, None, :, :], timestamps=None),
         }
 
     def process_output(
@@ -206,7 +206,7 @@ class SegmentationTask(BasicTask):
         image = super().visualize(input_dict, target_dict, output)["image"]
         if target_dict is None:
             raise ValueError("target_dict is required for visualization")
-        gt_classes = target_dict["classes"].cpu().numpy()
+        gt_classes = target_dict["classes"].get_hw_tensor().cpu().numpy()
         pred_classes = output.cpu().numpy().argmax(axis=0)
         gt_vis = np.zeros((gt_classes.shape[0], gt_classes.shape[1], 3), dtype=np.uint8)
         pred_vis = np.zeros(
@@ -291,12 +291,19 @@ class SegmentationTask(BasicTask):
 class SegmentationHead(Predictor):
     """Head for segmentation task."""
 
-    def __init__(self, weights: list[float] | None = None, dice_loss: bool = False):
+    def __init__(
+        self,
+        weights: list[float] | None = None,
+        dice_loss: bool = False,
+        temperature: float = 1.0,
+    ):
         """Initialize a new SegmentationTask.
 
         Args:
             weights: weights for cross entropy loss (Tensor of size C)
             dice_loss: weather to add dice loss to cross entropy
+            temperature: temperature scaling for softmax, does not affect the loss,
+                only the predictor outputs
         """
         super().__init__()
         if weights is not None:
@@ -304,6 +311,7 @@ class SegmentationHead(Predictor):
         else:
             self.weights = None
         self.dice_loss = dice_loss
+        self.temperature = temperature
 
     def forward(
         self,
@@ -332,12 +340,16 @@ class SegmentationHead(Predictor):
             )
 
         logits = intermediates.feature_maps[0]
-        outputs = torch.nn.functional.softmax(logits, dim=1)
+        outputs = torch.nn.functional.softmax(logits / self.temperature, dim=1)
 
         losses = {}
         if targets:
-            labels = torch.stack([target["classes"] for target in targets], dim=0)
-            mask = torch.stack([target["valid"] for target in targets], dim=0)
+            labels = torch.stack(
+                [target["classes"].get_hw_tensor() for target in targets], dim=0
+            )
+            mask = torch.stack(
+                [target["valid"].get_hw_tensor() for target in targets], dim=0
+            )
             per_pixel_loss = torch.nn.functional.cross_entropy(
                 logits, labels, weight=self.weights, reduction="none"
             )
@@ -350,7 +362,8 @@ class SegmentationHead(Predictor):
                 # the summed mask loss be zero.
                 losses["cls"] = torch.sum(per_pixel_loss * mask)
             if self.dice_loss:
-                dice_loss = DiceLoss()(outputs, labels, mask)
+                softmax_woT = torch.nn.functional.softmax(logits, dim=1)
+                dice_loss = DiceLoss()(softmax_woT, labels, mask)
                 losses["dice"] = dice_loss
 
         return ModelOutput(
@@ -401,12 +414,12 @@ class SegmentationMetric(Metric):
         """
         if not isinstance(preds, torch.Tensor):
             preds = torch.stack(preds)
-        labels = torch.stack([target["classes"] for target in targets])
+        labels = torch.stack([target["classes"].get_hw_tensor() for target in targets])
 
         # Sub-select the valid labels.
         # We flatten the prediction and label images at valid pixels.
         # Prediction is changed from BCHW to BHWC so we can select the valid BHW mask.
-        mask = torch.stack([target["valid"] > 0 for target in targets])
+        mask = torch.stack([target["valid"].get_hw_tensor() > 0 for target in targets])
         preds = preds.permute(0, 2, 3, 1)[mask]
         labels = labels[mask]
         if len(preds) == 0:

rslearn/train/transforms/concatenate.py

@@ -54,36 +54,26 @@ class Concatenate(Transform):
             target_dict: the target
 
         Returns:
-            concatenated (input_dicts, target_dicts) tuple. If one of the
-            specified inputs is a RasterImage, a RasterImage will be returned.
-            Otherwise it will be a torch.Tensor.
+            (input_dicts, target_dicts) where the entry corresponding to
+            output_selector contains the concatenated RasterImage.
         """
-        images = []
-        return_raster_image: bool = False
+        tensors: list[torch.Tensor] = []
         timestamps: list[tuple[datetime, datetime]] | None = None
+
         for selector, wanted_bands in self.selections.items():
             image = read_selector(input_dict, target_dict, selector)
-            if isinstance(image, torch.Tensor):
-                if wanted_bands:
-                    image = image[wanted_bands, :, :]
-                images.append(image)
-            elif isinstance(image, RasterImage):
-                return_raster_image = True
-                if wanted_bands:
-                    images.append(image.image[wanted_bands, :, :])
-                else:
-                    images.append(image.image)
-                if timestamps is None:
-                    if image.timestamps is not None:
-                        # assume all concatenated modalities have the same
-                        # number of timestamps
-                        timestamps = image.timestamps
-        if return_raster_image:
-            result = RasterImage(
-                torch.concatenate(images, dim=self.concatenate_dim),
-                timestamps=timestamps,
-            )
-        else:
-            result = torch.concatenate(images, dim=self.concatenate_dim)
+            if wanted_bands:
+                tensors.append(image.image[wanted_bands, :, :])
+            else:
+                tensors.append(image.image)
+            if timestamps is None and image.timestamps is not None:
+                # assume all concatenated modalities have the same
+                # number of timestamps
+                timestamps = image.timestamps
+
+        result = RasterImage(
+            torch.concatenate(tensors, dim=self.concatenate_dim),
+            timestamps=timestamps,
+        )
         write_selector(input_dict, target_dict, self.output_selector, result)
         return input_dict, target_dict

rslearn/train/transforms/crop.py

@@ -71,9 +71,7 @@ class Crop(Transform):
             "remove_from_top": remove_from_top,
         }
 
-    def apply_image(
-        self, image: RasterImage | torch.Tensor, state: dict[str, Any]
-    ) -> RasterImage | torch.Tensor:
+    def apply_image(self, image: RasterImage, state: dict[str, Any]) -> RasterImage:
         """Apply the sampled state on the specified image.
 
         Args:
@@ -84,22 +82,13 @@ class Crop(Transform):
         crop_size = state["crop_size"] * image.shape[-1] // image_shape[1]
         remove_from_left = state["remove_from_left"] * image.shape[-1] // image_shape[1]
         remove_from_top = state["remove_from_top"] * image.shape[-2] // image_shape[0]
-        if isinstance(image, RasterImage):
-            image.image = torchvision.transforms.functional.crop(
-                image.image,
-                top=remove_from_top,
-                left=remove_from_left,
-                height=crop_size,
-                width=crop_size,
-            )
-        else:
-            image = torchvision.transforms.functional.crop(
-                image,
-                top=remove_from_top,
-                left=remove_from_left,
-                height=crop_size,
-                width=crop_size,
-            )
+        image.image = torchvision.transforms.functional.crop(
+            image.image,
+            top=remove_from_top,
+            left=remove_from_left,
+            height=crop_size,
+            width=crop_size,
+        )
         return image
 
     def apply_boxes(self, boxes: Any, state: dict[str, bool]) -> torch.Tensor:

rslearn/train/transforms/flip.py

@@ -57,16 +57,10 @@ class Flip(Transform):
             image: the image to transform.
             state: the sampled state.
         """
-        if isinstance(image, RasterImage):
-            if state["horizontal"]:
-                image.image = torch.flip(image.image, dims=[-1])
-            if state["vertical"]:
-                image.image = torch.flip(image.image, dims=[-2])
-        elif isinstance(image, torch.Tensor):
-            if state["horizontal"]:
-                image = torch.flip(image, dims=[-1])
-            if state["vertical"]:
-                image = torch.flip(image, dims=[-2])
+        if state["horizontal"]:
+            image.image = torch.flip(image.image, dims=[-1])
+        if state["vertical"]:
+            image.image = torch.flip(image.image, dims=[-2])
         return image
 
     def apply_boxes(

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