careamics 0.0.16__py3-none-any.whl → 0.0.17__py3-none-any.whl

careamics/lightning/dataset_ng/data_module.py

@@ -39,6 +39,10 @@ class CareamicsDataModule(L.LightningDataModule):
     train_data_target : Optional[InputType]
         Training data target, can be a path to a folder,
         a list of paths, or a numpy array.
+    train_data_mask : InputType (when filtering is needed)
+        Training data mask, can be a path to a folder,
+        a list of paths, or a numpy array. Used for coordinate filtering.
+        Only required when using coordinate-based patch filtering.
     val_data : Optional[InputType]
         Validation data, can be a path to a folder,
         a list of paths, or a numpy array.
@@ -99,6 +103,9 @@ class CareamicsDataModule(L.LightningDataModule):
     train_data_target : Optional[Any]
         Training data target, can be a path to a folder, a list of paths, or a numpy
         array.
+    train_data_mask : Optional[Any]
+        Training data mask, can be a path to a folder, a list of paths, or a numpy
+        array.
     val_data : Optional[Any]
         Validation data, can be a path to a folder, a list of paths, or a numpy array.
     val_data_target : Optional[Any]
@@ -118,7 +125,7 @@ class CareamicsDataModule(L.LightningDataModule):
         If input and target data types are not consistent.
     """
 
-    # standard use
+    # standard use (no mask)
     @overload
     def __init__(
         self,
@@ -136,7 +143,26 @@ class CareamicsDataModule(L.LightningDataModule):
         use_in_memory: bool = True,
     ) -> None: ...
 
-    # custom read function
+    # with training mask for filtering
+    @overload
+    def __init__(
+        self,
+        data_config: NGDataConfig,
+        *,
+        train_data: InputType | None = None,
+        train_data_target: InputType | None = None,
+        train_data_mask: InputType,
+        val_data: InputType | None = None,
+        val_data_target: InputType | None = None,
+        pred_data: InputType | None = None,
+        pred_data_target: InputType | None = None,
+        extension_filter: str = "",
+        val_percentage: float | None = None,
+        val_minimum_split: int = 5,
+        use_in_memory: bool = True,
+    ) -> None: ...
+
+    # custom read function (no mask)
     @overload
     def __init__(
         self,
@@ -156,6 +182,48 @@ class CareamicsDataModule(L.LightningDataModule):
         use_in_memory: bool = True,
     ) -> None: ...
 
+    # custom read function with training mask
+    @overload
+    def __init__(
+        self,
+        data_config: NGDataConfig,
+        *,
+        train_data: InputType | None = None,
+        train_data_target: InputType | None = None,
+        train_data_mask: InputType,
+        val_data: InputType | None = None,
+        val_data_target: InputType | None = None,
+        pred_data: InputType | None = None,
+        pred_data_target: InputType | None = None,
+        read_source_func: Callable,
+        read_kwargs: dict[str, Any] | None = None,
+        extension_filter: str = "",
+        val_percentage: float | None = None,
+        val_minimum_split: int = 5,
+        use_in_memory: bool = True,
+    ) -> None: ...
+
+    # image stack loader (no mask)
+    @overload
+    def __init__(
+        self,
+        data_config: NGDataConfig,
+        *,
+        train_data: Any | None = None,
+        train_data_target: Any | None = None,
+        val_data: Any | None = None,
+        val_data_target: Any | None = None,
+        pred_data: Any | None = None,
+        pred_data_target: Any | None = None,
+        image_stack_loader: ImageStackLoader,
+        image_stack_loader_kwargs: dict[str, Any] | None = None,
+        extension_filter: str = "",
+        val_percentage: float | None = None,
+        val_minimum_split: int = 5,
+        use_in_memory: bool = True,
+    ) -> None: ...
+
+    # image stack loader with training mask
     @overload
     def __init__(
         self,
@@ -163,6 +231,7 @@ class CareamicsDataModule(L.LightningDataModule):
         *,
         train_data: Any | None = None,
         train_data_target: Any | None = None,
+        train_data_mask: Any,
         val_data: Any | None = None,
         val_data_target: Any | None = None,
         pred_data: Any | None = None,
@@ -181,6 +250,7 @@ class CareamicsDataModule(L.LightningDataModule):
         *,
         train_data: Any | None = None,
         train_data_target: Any | None = None,
+        train_data_mask: Any | None = None,
         val_data: Any | None = None,
         val_data_target: Any | None = None,
         pred_data: Any | None = None,
@@ -209,6 +279,10 @@ class CareamicsDataModule(L.LightningDataModule):
         train_data_target : Optional[InputType]
             Training data target, can be a path to a folder,
             a list of paths, or a numpy array.
+        train_data_mask : InputType (when filtering is needed)
+            Training data mask, can be a path to a folder,
+            a list of paths, or a numpy array. Used for coordinate filtering.
+            Only required when using coordinate-based patch filtering.
         val_data : Optional[InputType]
             Validation data, can be a path to a folder,
             a list of paths, or a numpy array.
@@ -268,6 +342,8 @@ class CareamicsDataModule(L.LightningDataModule):
         self.train_data, self.train_data_target = self._initialize_data_pair(
             train_data, train_data_target
         )
+        self.train_data_mask, _ = self._initialize_data_pair(train_data_mask, None)
+
         self.val_data, self.val_data_target = self._initialize_data_pair(
             val_data, val_data_target
         )
@@ -574,6 +650,7 @@ class CareamicsDataModule(L.LightningDataModule):
                 mode=Mode.TRAINING,
                 inputs=self.train_data,
                 targets=self.train_data_target,
+                masks=self.train_data_mask,
                 config=self.config,
                 in_memory=self.use_in_memory,
                 read_func=self.read_source_func,

careamics/lightning/lightning_module.py

@@ -437,7 +437,8 @@ class VAEModule(L.LightningModule):
                 or self.noise_model_likelihood.data_std is None
             ):
                 raise RuntimeError(
-                    "NoiseModelLikelihood: data_mean and data_std must be set before training."
+                    "NoiseModelLikelihood: data_mean and data_std must be set before"
+                    "training."
                 )
         loss = self.loss_func(
             model_outputs=out,
@@ -541,9 +542,9 @@ class VAEModule(L.LightningModule):
                 # get reconstructed img
                 if self.model.predict_logvar is None:
                     rec_img = rec
-                    logvar = torch.tensor([-1])
+                    _logvar = torch.tensor([-1])
                 else:
-                    rec_img, logvar = torch.chunk(rec, chunks=2, dim=1)
+                    rec_img, _logvar = torch.chunk(rec, chunks=2, dim=1)
                 rec_img_list.append(rec_img.cpu().unsqueeze(0))  # add MMSE dim
 
             # aggregate results

careamics/lightning/microsplit_data_module.py

@@ -74,7 +74,8 @@ def load_data(datadir):
         channel_stack = np.concatenate(
             channel_images, axis=0
         )  # FIXME: this line works iff images have
-        # a singleton channel dimension. Specify in the notebook or change with `torch.stack`??
+        # a singleton channel dimension. Specify in the notebook or change with
+        # `torch.stack`??
         channels_data.append(channel_stack)
 
     final_data = np.stack(channels_data, axis=-1)
@@ -204,7 +205,8 @@ class MicroSplitDataModule(L.LightningDataModule):
 
     def __init__(
         self,
-        data_config: MicroSplitDataConfig,  # Should be compatible with microSplit DatasetConfig
+        # Should be compatible with microSplit DatasetConfig
+        data_config: MicroSplitDataConfig,
         train_data: str,
         val_data: str | None = None,
         train_data_target: str | None = None,
@@ -301,7 +303,8 @@ class MicroSplitDataModule(L.LightningDataModule):
         """
         return DataLoader(
             self.train_dataset,
-            batch_size=self.train_config.batch_size,  # TODO should be inside dataloader params?
+            # TODO should be inside dataloader params?
+            batch_size=self.train_config.batch_size,
             **self.train_config.train_dataloader_params,
         )
 
@@ -355,7 +358,9 @@ def create_microsplit_train_datamodule(
     **dataset_kwargs,
 ) -> MicroSplitDataModule:
     """
-    Create a MicroSplitDataModule for microSplit-style datasets, including config creation.
+    Create a MicroSplitDataModule for microSplit-style datasets.
+
+    This includes config creation.
 
     Parameters
     ----------
@@ -424,10 +429,10 @@ def create_microsplit_train_datamodule(
         **dataset_config_params,
         datasplit_type=DataSplitType.Train,
     )
-    val_config = MicroSplitDataConfig(
-        **dataset_config_params,
-        datasplit_type=DataSplitType.Val,
-    )
+    # val_config = MicroSplitDataConfig(
+    #     **dataset_config_params,
+    #     datasplit_type=DataSplitType.Val,
+    # )
     # TODO, data config is duplicated here and in configuration
 
     return MicroSplitDataModule(
@@ -578,10 +583,10 @@ def create_microsplit_predict_datamodule(
         Grid size for patch extraction.
     multiscale_count : int, optional
         Number of LC scales.
-    tiling_mode : TilingMode, default=ShiftBoundary
-        Tiling mode for patch extraction.
     data_stats : tuple, optional
         Data statistics, by default None.
+    tiling_mode : TilingMode, default=ShiftBoundary
+        Tiling mode for patch extraction.
     read_source_func : Callable, optional
         Function to read the source data.
     extension_filter : str, optional

careamics/lvae_training/eval_utils.py

@@ -32,7 +32,7 @@ class TilingMode:
     ShiftBoundary = 2
 
 
-# ------------------------------------------------------------------------------------------------
+# ------------------------------------------------------------------------------------
 # Function of plotting: TODO -> moved them to another file, plot_utils.py
 def clean_ax(ax):
     """
@@ -68,7 +68,9 @@ def get_psnr_str(tar_hsnr, pred, col_idx):
     """
     Compute PSNR between the ground truth (`tar_hsnr`) and the predicted image (`pred`).
     """
-    return f"{scale_invariant_psnr(tar_hsnr[col_idx][None], pred[col_idx][None]).item():.1f}"
+    psnr = scale_invariant_psnr(tar_hsnr[col_idx][None], pred[col_idx][None]).item()
+
+    return f"{psnr:.1f}"
 
 
 def add_psnr_str(ax_, psnr):
@@ -129,8 +131,10 @@ def show_for_one(
     baseline_preds=None,
 ):
     """
-    Given an index, it plots the input, target, reconstructed images and the difference image.
-    Note the the difference image is computed with respect to a ground truth image, obtained from the high SNR dataset.
+    Given an index, it plots the input, target, reconstructed images and the difference
+    image.
+    Note the the difference image is computed with respect to a ground truth image,
+    obtained from the high SNR dataset.
     """
     highsnr_val_dset.set_img_sz(patch_size, 64)
     highsnr_val_dset.disable_noise()
@@ -164,7 +168,8 @@ def plot_crops(
         for i in range(len(baseline_preds)):
             if baseline_preds[i].shape != tar_hsnr.shape:
                 print(
-                    f"Baseline prediction {i} shape {baseline_preds[i].shape} does not match target shape {tar_hsnr.shape}"
+                    f"Baseline prediction {i} shape {baseline_preds[i].shape} does not "
+                    f"match target shape {tar_hsnr.shape}"
                 )
                 print("This happens when we want to predict the edges of the image.")
                 return
@@ -333,14 +338,21 @@ def plot_crops(
     ax_temp.imshow(inp[0, 0].cpu().numpy(), cmap="magma")
     clean_ax(ax_temp)
 
-    # line_ch1 = mlines.Line2D([0, 1], [0, 1], color=color_ch_list[0], linestyle='-', label='$C_1$')
-    # line_ch2 = mlines.Line2D([0, 1], [0, 1], color=color_ch_list[1], linestyle='-', label='$C_2$')
-    # line_pred = mlines.Line2D([0, 1], [0, 1], color=color_pred, linestyle='-', label='Pred')
-    # line_noisych1 = mlines.Line2D([0, 1], [0, 1], color=color_ch_list[0], linestyle='--', label='$C^N_1$')
-    # line_noisych2 = mlines.Line2D([0, 1], [0, 1], color=color_ch_list[1], linestyle='--', label='$C^N_2$')
-    # legend_ch1 = legend_ch1_ax.legend(handles=[line_ch1, line_noisych1, line_pred], loc='upper right', frameon=False, labelcolor='white',
+    # line_ch1 = mlines.Line2D([0, 1], [0, 1], color=color_ch_list[0], linestyle='-',
+    # label='$C_1$')
+    # line_ch2 = mlines.Line2D([0, 1], [0, 1], color=color_ch_list[1], linestyle='-',
+    # label='$C_2$')
+    # line_pred = mlines.Line2D([0, 1], [0, 1], color=color_pred, linestyle='-',
+    # label='Pred')
+    # line_noisych1 = mlines.Line2D([0, 1], [0, 1], color=color_ch_list[0],
+    # linestyle='--', label='$C^N_1$')
+    # line_noisych2 = mlines.Line2D([0, 1], [0, 1], color=color_ch_list[1],
+    # linestyle='--', label='$C^N_2$')
+    # legend_ch1 = legend_ch1_ax.legend(handles=[line_ch1, line_noisych1, line_pred],
+    # loc='upper right', frameon=False, labelcolor='white',
     #                         prop={'size': 11})
-    # legend_ch2 = legend_ch2_ax.legend(handles=[line_ch2, line_noisych2, line_pred], loc='upper right', frameon=False, labelcolor='white',
+    # legend_ch2 = legend_ch2_ax.legend(handles=[line_ch2, line_noisych2, line_pred],
+    # loc='upper right', frameon=False, labelcolor='white',
     #                             prop={'size': 11})
 
     if calibration_stats is not None:
@@ -383,7 +395,9 @@ def plot_calibration(ax, calibration_stats):
 
 def shiftedColorMap(cmap, start=0, midpoint=0.5, stop=1.0, name="shiftedcmap"):
     """
-    Adapted from https://stackoverflow.com/questions/7404116/defining-the-midpoint-of-a-colormap-in-matplotlib
+    Adapted from
+    https://stackoverflow.com/questions/7404116/defining-the-midpoint-of-a-colormap-in-
+    matplotlib
 
     Function to offset the "center" of a colormap. Useful for
     data with a negative min and positive max and you want the
@@ -444,7 +458,8 @@ def get_fractional_change(target, prediction, max_val=None):
 
 def get_zero_centered_midval(error):
     """
-    When done this way, the midval ensures that the colorbar is centered at 0. (Don't know how, but it works ;))
+    When done this way, the midval ensures that the colorbar is centered at 0. (Don't
+    know how, but it works ;))
     """
     vmax = error.max()
     vmin = error.min()
@@ -670,7 +685,7 @@ def get_single_file_mmse(
     return stitched_predictions, stitched_stds
 
 
-# ------------------------------------------------------------------------------------------
+# ---------------------------------------------------------------------------------
 ### Classes and Functions used to stitch predictions
 class PatchLocation:
     """
@@ -698,9 +713,10 @@ def _get_location(extra_padding, hwt, pred_h, pred_w):
 
 def get_location_from_idx(dset, dset_input_idx, pred_h, pred_w):
     """
-    For a given idx of the dataset, it returns where exactly in the dataset, does this prediction lies.
-    Note that this prediction also has padded pixels and so a subset of it will be used in the final prediction.
-    Which time frame, which spatial location (h_start, h_end, w_start,w_end)
+    For a given idx of the dataset, it returns where exactly in the dataset, does this
+    prediction lies. Note that this prediction also has padded pixels and so a subset of
+    it will be used in the final prediction. Which time frame, which spatial location
+    (h_start, h_end, w_start,w_end)
     Args:
         dset:
         dset_input_idx:
@@ -785,9 +801,11 @@ def stitch_predictions(predictions, dset, smoothening_pixelcount=0):
                 # NOTE: don't need to compute it for every patch.
                 assert (
                     smoothening_pixelcount == 0
-                ), "For smoothing,enable the get_smoothing_mask. It is disabled since I don't use it and it needs modification to work with non-square images"
+                ), "For smoothing,enable the get_smoothing_mask. It is disabled since I"
+                "don't use it and it needs modification to work with non-square images"
                 mask = 1
-                # mask = _get_smoothing_mask(cropped_pred_i.shape, smoothening_pixelcount, loc, frame_size)
+                # mask = _get_smoothing_mask(cropped_pred_i.shape,
+                # smoothening_pixelcount, loc, frame_size)
 
             cropped_pred_list.append(cropped_pred_i)
 
@@ -827,7 +845,8 @@ def stitch_predictions_new(predictions, dset):
     output = np.zeros(shape, dtype=predictions.dtype)
     # frame_shape = dset.get_data_shape()[:-1]
     for dset_idx in range(predictions.shape[0]):
-        # loc = get_location_from_idx(dset, dset_idx, predictions.shape[-2], predictions.shape[-1])
+        # loc = get_location_from_idx(dset, dset_idx, predictions.shape[-2],
+        # predictions.shape[-1])
         # grid start, grid end
         gs = np.array(mng.get_location_from_dataset_idx(dset_idx), dtype=int)
         ge = gs + mng.grid_shape
@@ -843,7 +862,8 @@ def stitch_predictions_new(predictions, dset):
         vgs = np.array([max(0, x) for x in gs], dtype=int)
         vge = np.array([min(x, y) for x, y in zip(ge, mng.data_shape)], dtype=int)
         # assert np.all(vgs == gs)
-        # assert np.all(vge == ge) # TODO comented out this shit cuz I have no interest to dig why it's failing at this point !
+        # assert np.all(vge == ge) # TODO comented out this shit cuz I have no interest
+        # to dig why it's failing at this point !
         # print('VGS')
         # print(gs)
         # print(ge)
@@ -898,7 +918,8 @@ def stitch_predictions_general(predictions, dset):
     # frame_shape = dset.get_data_shape()[:-1]
     for patch_idx in range(predictions.shape[0]):
         # grid start, grid end
-        # channel_idx is 0 because during prediction we're only use one channel. # TODO revisit this
+        # channel_idx is 0 because during prediction we're only use one channel.
+        # # TODO revisit this
         # 0th dimension is sample index in the output list
         grid_coords = np.array(
             mng.get_location_from_patch_idx(channel_idx=0, patch_idx=patch_idx),
@@ -906,7 +927,8 @@ def stitch_predictions_general(predictions, dset):
         )
         sample_idx = grid_coords[0]
         grid_start = grid_coords[1:]
-        # from here on, coordinates are relative to the sample(file in the list of inputs)
+        # from here on, coordinates are relative to the sample(file in the list of
+        # inputs)
         grid_end = grid_start + mng.grid_shape
 
         # patch start, patch end

careamics/models/lvae/likelihoods.py

@@ -381,7 +381,8 @@ class NoiseModelLikelihood(LikelihoodModule):
         """
         if self.data_mean is None or self.data_std is None:
             raise RuntimeError(
-                "NoiseModelLikelihood: data_mean and data_std must be set before calling log_likelihood."
+                "NoiseModelLikelihood: data_mean and data_std must be set before"
+                "callinglog_likelihood."
             )
         self._set_params_to_same_device_as(x)
         predicted_s_denormalized = params["mean"] * self.data_std + self.data_mean

careamics/prediction_utils/prediction_outputs.py

@@ -47,8 +47,9 @@ def convert_outputs_microsplit(
     """
     Convert microsplit Lightning trainer outputs using eval_utils stitching functions.
 
-    This function processes microsplit predictions that return (tile_prediction, tile_std) tuples
-    and stitches them back together using the same logic as get_single_file_mmse.
+    This function processes microsplit predictions that return (tile_prediction,
+    tile_std) tuples and stitches them back together using the same logic as
+    get_single_file_mmse.
 
     Parameters
     ----------

careamics/prediction_utils/stitch_prediction.py

@@ -17,13 +17,21 @@ class TilingMode:
     ShiftBoundary = 2
 
 
-def stitch_prediction_vae(predictions, dset):
+def stitch_prediction_vae(predictions, dset) -> NDArray:
     """
     Stitch predictions back together using dataset's index manager.
 
-    Args:
-        predictions: Array of predictions with shape (n_tiles, channels, height, width)
-        dset: Dataset object with idx_manager containing tiling information
+    Parameters
+    ----------
+    predictions : np.ndarray
+        Array of predictions with shape (n_tiles, channels, height, width).
+    dset : Dataset
+        Dataset object with idx_manager containing tiling information.
+
+    Returns
+    -------
+    np.ndarray
+        Stitched array with shape matching the original data shape.
     """
     mng = dset.idx_manager
 
@@ -34,7 +42,8 @@ def stitch_prediction_vae(predictions, dset):
     output = np.zeros(shape, dtype=predictions.dtype)
     # frame_shape = dset.get_data_shape()[:-1]
     for dset_idx in range(predictions.shape[0]):
-        # loc = get_location_from_idx(dset, dset_idx, predictions.shape[-2], predictions.shape[-1])
+        # loc = get_location_from_idx(dset, dset_idx, predictions.shape[-2],
+        # predictions.shape[-1])
         # grid start, grid end
         gs = np.array(mng.get_location_from_dataset_idx(dset_idx), dtype=int)
         ge = gs + mng.grid_shape
@@ -178,6 +187,8 @@ def stitch_prediction_single(
 
         # Insert cropped tile into predicted image using stitch coordinates
         image_slices = (..., *[slice(c[0], c[1]) for c in tile_info.stitch_coords])
-        predicted_image[image_slices] = cropped_tile.astype(np.float32)
+
+        # TODO fix mypy error here, potentially due to numpy 2
+        predicted_image[image_slices] = cropped_tile.astype(np.float32)  # type: ignore
 
     return predicted_image

careamics/utils/version.py

@@ -21,9 +21,9 @@ def get_careamics_version() -> str:
     parts = __version__.split(".")
 
     # for local installs that do not detect the latest versions via tags
-    # (typically our CI will install `0.1.devX<hash>` versions)
-    if "dev" in parts[-1]:
-        parts[-1] = "*"
+    # (typically our CI will install `0.X.devX<hash>.<other hash>` versions)
+    if "dev" in parts[2]:
+        parts[2] = "*"
         clean_version = ".".join(parts[:3])
 
         logger.warning(
@@ -34,5 +34,5 @@ def get_careamics_version() -> str:
             f"closest CAREamics version from PyPI or conda-forge."
         )
 
-    # Remove any local version identifier)
+    # Remove any local version identifier
     return ".".join(parts[:3])

{careamics-0.0.16.dist-info → careamics-0.0.17.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: careamics
-Version: 0.0.16
+Version: 0.0.17
 Summary: Toolbox for running N2V and friends.
 Project-URL: homepage, https://careamics.github.io/
 Project-URL: repository, https://github.com/CAREamics/careamics
@@ -16,30 +16,24 @@ Classifier: Programming Language :: Python :: 3.13
 Classifier: Typing :: Typed
 Requires-Python: >=3.11
 Requires-Dist: bioimageio-core>=0.9.0
-Requires-Dist: matplotlib<=3.10.6
+Requires-Dist: matplotlib<=3.10.7
 Requires-Dist: numpy>=1.21
 Requires-Dist: numpy>=2.1.0; python_version >= '3.13'
 Requires-Dist: pillow<=11.3.0
 Requires-Dist: psutil<=7.1.0
-Requires-Dist: pydantic<=2.12,>=2.11
+Requires-Dist: pydantic<=2.12.2,>=2.11
 Requires-Dist: pytorch-lightning<=2.5.5,>=2.2
 Requires-Dist: pyyaml!=6.0.0,<=6.0.3
 Requires-Dist: scikit-image<=0.25.2
-Requires-Dist: tifffile<=2025.9.30
+Requires-Dist: tifffile<=2025.10.4
 Requires-Dist: torch<=2.8.0,>=2.0
+Requires-Dist: torchmetrics<1.5.0,>=0.11.0
 Requires-Dist: torchvision<=0.23.0
 Requires-Dist: typer<=0.19.2,>=0.12.3
 Requires-Dist: validators<=0.35.0
 Requires-Dist: zarr<4.0.0,>=3.0.0
 Provides-Extra: czi
 Requires-Dist: pylibczirw<6.0.0,>=4.1.2; extra == 'czi'
-Provides-Extra: dev
-Requires-Dist: ml-dtypes>=0.5.0; extra == 'dev'
-Requires-Dist: onnx; extra == 'dev'
-Requires-Dist: pre-commit; extra == 'dev'
-Requires-Dist: pytest; extra == 'dev'
-Requires-Dist: pytest-cov; extra == 'dev'
-Requires-Dist: sybil; extra == 'dev'
 Provides-Extra: examples
 Requires-Dist: careamics-portfolio; extra == 'examples'
 Requires-Dist: jupyter; extra == 'examples'