careamics 0.0.12__py3-none-any.whl → 0.0.14__py3-none-any.whl

careamics/dataset_ng/demos/demo_datamodule.ipynb

@@ -6,7 +6,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from careamics.config.configuration_factories import create_n2v_configuration\n",
+    "from careamics.config.configuration_factories import (\n",
+    "    _create_ng_data_configuration,\n",
+    "    _list_spatial_augmentations,\n",
+    ")\n",
     "from careamics.lightning.dataset_ng.data_module import CareamicsDataModule"
    ]
   },
@@ -70,20 +73,19 @@
    "source": [
     "# from path, train and val, no target\n",
     "\n",
-    "config = create_n2v_configuration(\n",
-    "    experiment_name=\"bsd68_n2v\",\n",
+    "config = _create_ng_data_configuration(\n",
     "    data_type=\"tiff\",\n",
     "    axes=\"SYX\",\n",
     "    patch_size=(64, 64),\n",
     "    batch_size=64,\n",
-    "    num_epochs=100\n",
+    "    augmentations=_list_spatial_augmentations()\n",
     ")\n",
     "\n",
-    "config.data_config.set_means_and_stds([image_mean], [image_std])\n",
-    "config.data_config.val_dataloader_params = {\"shuffle\": False}\n",
+    "config.set_means_and_stds([image_mean], [image_std])\n",
+    "config.val_dataloader_params = {\"shuffle\": False}\n",
     "\n",
     "data_module = CareamicsDataModule(\n",
-    "    data_config=config.data_config,\n",
+    "    data_config=config,\n",
     "    train_data=train_path,\n",
     "    val_data=val_path,\n",
     ")\n",
@@ -112,13 +114,15 @@
    "source": [
     "# from path, only predict\n",
     "\n",
-    "from careamics.config.inference_model import InferenceConfig\n",
+    "from careamics.config.data import NGDataConfig\n",
     "\n",
-    "config = InferenceConfig(\n",
-    "    model_config=config,\n",
+    "config = NGDataConfig(\n",
     "    data_type=\"tiff\",\n",
-    "    tile_size=(128, 128),\n",
-    "    tile_overlap=(32, 32),\n",
+    "    patching={\n",
+    "        \"name\": \"tiled\",\n",
+    "        \"patch_size\": (128, 128),\n",
+    "        \"overlaps\": (32, 32)\n",
+    "    },\n",
     "    axes=\"YX\",\n",
     "    batch_size=8,\n",
     "    image_means=[image_mean],\n",
@@ -167,20 +171,19 @@
    "source": [
     "# from array, train and val, no target\n",
     "\n",
-    "config = create_n2v_configuration(\n",
-    "    experiment_name=\"bsd68_n2v\",\n",
+    "config = _create_ng_data_configuration(\n",
     "    data_type=\"array\",\n",
     "    axes=\"SYX\",\n",
     "    patch_size=(64, 64),\n",
     "    batch_size=64,\n",
-    "    num_epochs=100\n",
+    "    augmentations=_list_spatial_augmentations()\n",
     ")\n",
     "\n",
-    "config.data_config.set_means_and_stds([image_mean], [image_std])\n",
-    "config.data_config.val_dataloader_params = {\"shuffle\": False}\n",
+    "config.set_means_and_stds([image_mean], [image_std])\n",
+    "config.val_dataloader_params = {\"shuffle\": False}\n",
     "\n",
     "data_module = CareamicsDataModule(\n",
-    "    data_config=config.data_config,\n",
+    "    data_config=config,\n",
     "    train_data=train_array,\n",
     "    val_data=val_array,\n",
     ")\n",
@@ -239,15 +242,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "config = create_n2v_configuration(\n",
-    "    experiment_name=\"mitosis\",\n",
+    "config = _create_ng_data_configuration(\n",
     "    data_type=\"array\",\n",
     "    axes=\"YX\",\n",
     "    patch_size=(64, 64),\n",
     "    batch_size=64,\n",
-    "    num_epochs=100\n",
+    "    augmentations=_list_spatial_augmentations()\n",
     ")\n",
-    "config.data_config.set_means_and_stds(\n",
+    "config.set_means_and_stds(\n",
     "    [example_data.mean()],\n",
     "    [example_data.std()],\n",
     "    [segmentation.mean()],\n",
@@ -255,7 +257,7 @@
     ")\n",
     "\n",
     "data_module = CareamicsDataModule(\n",
-    "    data_config=config.data_config,\n",
+    "    data_config=config,\n",
     "    train_data=[example_data],\n",
     "    train_data_target=[segmentation],\n",
     "    val_data=[example_data],\n",
@@ -267,15 +269,17 @@
     "train_batch = next(iter(data_module.train_dataloader()))\n",
     "val_batch = next(iter(data_module.val_dataloader()))\n",
     "\n",
-    "fig, ax = plt.subplots(1, 8, figsize=(10, 5))\n",
+    "fig, ax = plt.subplots(2, 8, figsize=(10, 3))\n",
     "\n",
     "for i in range(8):\n",
-    "    ax[i].imshow(train_batch[0].data[i][0].numpy(), cmap=\"gray\")\n",
+    "    ax[0][i].imshow(train_batch[0].data[i][0].numpy(), cmap=\"gray\")\n",
+    "    ax[1][i].imshow(train_batch[1].data[i][0].numpy())\n",
     "\n",
     "\n",
-    "fig, ax = plt.subplots(1, 8, figsize=(10, 5))\n",
+    "fig, ax = plt.subplots(2, 8, figsize=(10, 3))\n",
     "for i in range(8):\n",
-    "    ax[i].imshow(val_batch[0].data[i][0].numpy(), cmap=\"gray\")"
+    "    ax[0][i].imshow(val_batch[0].data[i][0].numpy(), cmap=\"gray\")\n",
+    "    ax[1][i].imshow(val_batch[1].data[i][0].numpy())"
    ]
   },
   {
@@ -286,13 +290,15 @@
    "source": [
     "# from array, only predict, with target\n",
     "\n",
-    "from careamics.config.inference_model import InferenceConfig\n",
+    "from careamics.config.data import NGDataConfig\n",
     "\n",
-    "config = InferenceConfig(\n",
-    "    model_config=config,\n",
+    "config = NGDataConfig(\n",
     "    data_type=\"array\",\n",
-    "    tile_size=(128, 128),\n",
-    "    tile_overlap=(32, 32),\n",
+    "    patching={\n",
+    "        \"name\": \"tiled\",\n",
+    "        \"patch_size\": (128, 128),\n",
+    "        \"overlaps\": (32, 32)\n",
+    "    },\n",
     "    axes=\"YX\",\n",
     "    batch_size=8,\n",
     "    image_means=[image_mean],\n",
@@ -329,20 +335,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "config = create_n2v_configuration(\n",
-    "    experiment_name=\"bsd68_n2v\",\n",
+    "config = _create_ng_data_configuration(\n",
     "    data_type=\"tiff\",\n",
     "    axes=\"SYX\",\n",
     "    patch_size=(64, 64),\n",
     "    batch_size=64,\n",
-    "    num_epochs=100\n",
+    "    augmentations=_list_spatial_augmentations()\n",
     ")\n",
     "\n",
-    "config.data_config.set_means_and_stds([image_mean], [image_std])\n",
-    "config.data_config.val_dataloader_params = {\"shuffle\": False}\n",
+    "config.set_means_and_stds([image_mean], [image_std])\n",
+    "config.val_dataloader_params = {\"shuffle\": False}\n",
     "\n",
     "data_module = CareamicsDataModule(\n",
-    "    data_config=config.data_config,\n",
+    "    data_config=config,\n",
     "    train_data=sorted(train_path.glob(\"*.tiff\")),\n",
     "    val_data=sorted(val_path.glob(\"*.tiff\")),\n",
     ")\n",
@@ -378,17 +383,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "config = create_n2v_configuration(\n",
-    "    experiment_name=\"bsd68_n2v\",\n",
+    "config = _create_ng_data_configuration(\n",
     "    data_type=\"custom\",\n",
     "    axes=\"SYX\",\n",
     "    patch_size=(64, 64),\n",
     "    batch_size=64,\n",
-    "    num_epochs=100\n",
+    "    augmentations=_list_spatial_augmentations()\n",
     ")\n",
     "\n",
-    "config.data_config.set_means_and_stds([image_mean], [image_std])\n",
-    "config.data_config.val_dataloader_params = {\"shuffle\": False}\n",
+    "config.set_means_and_stds([image_mean], [image_std])\n",
+    "config.val_dataloader_params = {\"shuffle\": False}\n",
     "\n",
     "def read_source_func(path):\n",
     "    image = tifffile.imread(path)\n",
@@ -396,7 +400,7 @@
     "    return image\n",
     "\n",
     "data_module = CareamicsDataModule(\n",
-    "    data_config=config.data_config,\n",
+    "    data_config=config,\n",
     "    train_data=sorted(train_path.glob(\"*.tiff\")),\n",
     "    val_data=sorted(val_path.glob(\"*.tiff\")),\n",
     "    read_source_func=read_source_func\n",
@@ -421,7 +425,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "czi",
    "language": "python",
    "name": "python3"
   },
@@ -435,7 +439,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.20"
+   "version": "3.12.11"
   }
  },
  "nbformat": 4,

careamics/dataset_ng/demos/demo_dataset.ipynb

@@ -14,9 +14,12 @@
     "import skimage\n",
     "import tifffile\n",
     "\n",
-    "from careamics.config import create_n2n_configuration\n",
-    "from careamics.dataset_ng.dataset.dataset import Mode\n",
-    "from careamics.dataset_ng.dataset.factory import create_dataset"
+    "from careamics.config.configuration_factories import (\n",
+    "    _create_ng_data_configuration,\n",
+    "    _list_spatial_augmentations,\n",
+    ")\n",
+    "from careamics.dataset_ng.dataset import Mode\n",
+    "from careamics.dataset_ng.factory import create_dataset"
    ]
   },
   {
@@ -58,24 +61,21 @@
    "source": [
     "# 1. Train val from an array\n",
     "\n",
-    "train_data_config = create_n2n_configuration(\n",
-    "    \"test_exp\",\n",
+    "train_data_config = _create_ng_data_configuration(\n",
     "    data_type=\"array\",\n",
     "    axes=\"YX\",\n",
     "    patch_size=(32, 32),\n",
     "    batch_size=1,\n",
-    "    num_epochs=1,\n",
-    ").data_config\n",
+    "    augmentations=_list_spatial_augmentations()\n",
+    ")\n",
     "\n",
-    "val_data_config = create_n2n_configuration(\n",
-    "    \"test_exp\",\n",
+    "val_data_config = _create_ng_data_configuration(\n",
     "    data_type=\"array\",\n",
     "    axes=\"YX\",\n",
     "    patch_size=(32, 32),\n",
     "    batch_size=1,\n",
-    "    num_epochs=1,\n",
     "    augmentations=[],\n",
-    ").data_config\n",
+    ")\n",
     "\n",
     "\n",
     "train_dataset = create_dataset(\n",
@@ -122,24 +122,21 @@
     "tifffile.imwrite(\"example_data2.tiff\", example_data[:256, :256])\n",
     "tifffile.imwrite(\"example_target2.tiff\", segmentation[:256, :256])\n",
     "\n",
-    "train_data_config = create_n2n_configuration(\n",
-    "    \"test_exp\",\n",
+    "train_data_config = _create_ng_data_configuration(\n",
     "    data_type=\"tiff\",\n",
     "    axes=\"YX\",\n",
     "    patch_size=(32, 32),\n",
     "    batch_size=1,\n",
-    "    num_epochs=1,\n",
-    ").data_config\n",
+    "    augmentations=_list_spatial_augmentations()\n",
+    ")\n",
     "\n",
-    "val_data_config = create_n2n_configuration(\n",
-    "    \"test_exp\",\n",
+    "val_data_config = _create_ng_data_configuration(\n",
     "    data_type=\"tiff\",\n",
     "    axes=\"YX\",\n",
     "    patch_size=(32, 32),\n",
     "    batch_size=1,\n",
-    "    num_epochs=1,\n",
     "    augmentations=[],\n",
-    ").data_config\n",
+    ")\n",
     "\n",
     "data = sorted(Path(\"./\").glob(\"example_data*.tiff\"))\n",
     "targets = sorted(Path(\"./\").glob(\"example_target*.tiff\"))\n",
@@ -182,18 +179,21 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from careamics.config import InferenceConfig\n",
+    "from careamics.config.data import NGDataConfig\n",
     "\n",
-    "prediction_config = InferenceConfig(\n",
+    "prediction_config = NGDataConfig(\n",
     "    data_type=\"array\",\n",
-    "    tile_size=(32, 32),\n",
-    "    tile_overlap=(16, 16),\n",
+    "    patching={\n",
+    "        \"name\": \"tiled\",\n",
+    "        \"patch_size\": (32, 32),\n",
+    "        \"overlaps\": (16, 16),\n",
+    "    },\n",
     "    axes=\"YX\",\n",
-    "    image_means=(example_data.mean(),),\n",
-    "    image_stds=(example_data.std(),),\n",
-    "    tta_transforms=False,\n",
     "    batch_size=1,\n",
+    "    image_means=[example_data.mean()],\n",
+    "    image_stds=[example_data.std()],\n",
     ")\n",
+    "\n",
     "prediction_dataset = create_dataset(\n",
     "    config=prediction_config,\n",
     "    mode=Mode.PREDICTING,\n",
@@ -205,7 +205,7 @@
     "fig, ax = plt.subplots(1, 5, figsize=(10, 5))\n",
     "ax[0].set_title(\"Prediction input\")\n",
     "for i in range(5):\n",
-    "    sample, _ = prediction_dataset[i]\n",
+    "    sample, *_ = prediction_dataset[i]\n",
     "    ax[i].imshow(sample.data[0])"
    ]
   },
@@ -224,14 +224,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "train_data_config = create_n2n_configuration(\n",
-    "    \"test_exp\",\n",
+    "train_data_config = _create_ng_data_configuration(\n",
     "    data_type=\"custom\",\n",
     "    axes=\"YX\",\n",
     "    patch_size=(32, 32),\n",
     "    batch_size=1,\n",
-    "    num_epochs=1,\n",
-    ").data_config\n",
+    "    augmentations=_list_spatial_augmentations(),\n",
+    ")\n",
     "\n",
     "\n",
     "def read_data_func_test(example_data):\n",
@@ -253,27 +252,11 @@
     "    sample, _ = train_dataset[i]\n",
     "    ax[i].imshow(sample.data[0])"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "10",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "11",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "czi",
    "language": "python",
    "name": "python3"
   },
@@ -287,7 +270,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.21"
+   "version": "3.12.11"
   }
  },
  "nbformat": 4,

careamics/dataset_ng/factory.py

@@ -1,15 +1,16 @@
 from collections.abc import Sequence
 from enum import Enum
 from pathlib import Path
-from typing import Any, Optional, Union
+from typing import Any, Optional
 
 from numpy.typing import NDArray
 from typing_extensions import ParamSpec
 
-from careamics.config import DataConfig, InferenceConfig
+from careamics.config.data.ng_data_model import NGDataConfig
 from careamics.config.support import SupportedData
 from careamics.dataset_ng.patch_extractor import ImageStackLoader, PatchExtractor
 from careamics.dataset_ng.patch_extractor.image_stack import (
+    CziImageStack,
     GenericImageStack,
     ImageStack,
     InMemoryImageStack,
@@ -19,6 +20,7 @@ from careamics.dataset_ng.patch_extractor.patch_extractor_factory import (
     create_array_extractor,
     create_custom_file_extractor,
     create_custom_image_stack_extractor,
+    create_czi_extractor,
     create_ome_zarr_extractor,
     create_tiff_extractor,
 )
@@ -38,6 +40,7 @@ class DatasetType(Enum):
     LAZY_TIFF = "lazy_tiff"
     IN_MEM_CUSTOM_FILE = "in_mem_custom_file"
     OME_ZARR = "ome_zarr"
+    CZI = "czi"
     CUSTOM_IMAGE_STACK = "custom_image_stack"
 
 
@@ -58,7 +61,7 @@ def determine_dataset_type(
         Whether all the data should be loaded into memory. This is argument is ignored
         unless the `data_type` is "tiff" or "custom".
     read_func : ReadFunc, optional
-        A function that can that can be used to load custom data. This argument is
+        A function that can be used to load custom data. This argument is
         ignored unless the `data_type` is "custom".
     image_stack_loader : ImageStackLoader, optional
         A function for custom image stack loading. This argument is ignored unless the
@@ -87,6 +90,8 @@ def determine_dataset_type(
             return DatasetType.IN_MEM_TIFF
         else:
             return DatasetType.LAZY_TIFF
+    elif data_type == SupportedData.CZI:
+        return DatasetType.CZI
     elif data_type == SupportedData.CUSTOM:
         if read_func is not None:
             if in_memory:
@@ -111,7 +116,7 @@ def determine_dataset_type(
 # convenience function but should use `create_dataloader` function instead
 # For lazy loading custom batch sampler also needs to be set.
 def create_dataset(
-    config: Union[DataConfig, InferenceConfig],
+    config: NGDataConfig,
     mode: Mode,
     inputs: Any,
     targets: Any,
@@ -151,7 +156,7 @@ def create_dataset(
     Returns
     -------
     CareamicsDataset[ImageStack]
-        The CAREamicsDataset
+        The CAREamicsDataset.
 
     Raises
     ------
@@ -167,6 +172,8 @@ def create_dataset(
     elif dataset_type == DatasetType.IN_MEM_TIFF:
         return create_tiff_dataset(config, mode, inputs, targets)
     # TODO: Lazy tiff
+    elif dataset_type == DatasetType.CZI:
+        return create_czi_dataset(config, mode, inputs, targets)
     elif dataset_type == DatasetType.IN_MEM_CUSTOM_FILE:
         if read_kwargs is None:
             read_kwargs = {}
@@ -191,7 +198,7 @@ def create_dataset(
 
 
 def create_array_dataset(
-    config: Union[DataConfig, InferenceConfig],
+    config: NGDataConfig,
     mode: Mode,
     inputs: Sequence[NDArray[Any]],
     targets: Optional[Sequence[NDArray[Any]]],
@@ -213,7 +220,7 @@ def create_array_dataset(
     Returns
     -------
     CareamicsDataset[InMemoryImageStack]
-        A CAREamicsDataset
+        A CAREamicsDataset.
     """
     input_extractor = create_array_extractor(source=inputs, axes=config.axes)
     target_extractor: Optional[PatchExtractor[InMemoryImageStack]]
@@ -225,7 +232,7 @@ def create_array_dataset(
 
 
 def create_tiff_dataset(
-    config: Union[DataConfig, InferenceConfig],
+    config: NGDataConfig,
     mode: Mode,
     inputs: Sequence[Path],
     targets: Optional[Sequence[Path]],
@@ -247,7 +254,7 @@ def create_tiff_dataset(
     Returns
     -------
     CareamicsDataset[InMemoryImageStack]
-        A CAREamicsDataset
+        A CAREamicsDataset.
     """
     input_extractor = create_tiff_extractor(
         source=inputs,
@@ -262,8 +269,44 @@ def create_tiff_dataset(
     return dataset
 
 
+def create_czi_dataset(
+    config: NGDataConfig,
+    mode: Mode,
+    inputs: Sequence[Path],
+    targets: Optional[Sequence[Path]],
+) -> CareamicsDataset[CziImageStack]:
+    """
+    Create a dataset from CZI files.
+
+    Parameters
+    ----------
+    config : DataConfig or InferenceConfig
+        The data configuration.
+    mode : Mode
+        Whether to create the dataset in "training", "validation" or "predicting" mode.
+    inputs : Any
+        The input sources to the dataset.
+    targets : Any, optional
+        The target sources to the dataset.
+
+    Returns
+    -------
+    CareamicsDataset[CziImageStack]
+        A CAREamicsDataset.
+    """
+
+    input_extractor = create_czi_extractor(source=inputs, axes=config.axes)
+    target_extractor: Optional[PatchExtractor[CziImageStack]]
+    if targets is not None:
+        target_extractor = create_czi_extractor(source=targets, axes=config.axes)
+    else:
+        target_extractor = None
+    dataset = CareamicsDataset(config, mode, input_extractor, target_extractor)
+    return dataset
+
+
 def create_ome_zarr_dataset(
-    config: Union[DataConfig, InferenceConfig],
+    config: NGDataConfig,
     mode: Mode,
     inputs: Sequence[Path],
     targets: Optional[Sequence[Path]],
@@ -285,7 +328,7 @@ def create_ome_zarr_dataset(
     Returns
     -------
     CareamicsDataset[ZarrImageStack]
-        A CAREamicsDataset
+        A CAREamicsDataset.
     """
 
     input_extractor = create_ome_zarr_extractor(source=inputs, axes=config.axes)
@@ -299,7 +342,7 @@ def create_ome_zarr_dataset(
 
 
 def create_custom_file_dataset(
-    config: Union[DataConfig, InferenceConfig],
+    config: NGDataConfig,
     mode: Mode,
     inputs: Sequence[Path],
     targets: Optional[Sequence[Path]],
@@ -330,7 +373,7 @@ def create_custom_file_dataset(
     Returns
     -------
     CareamicsDataset[InMemoryImageStack]
-        A CAREamicsDataset
+        A CAREamicsDataset.
     """
     input_extractor = create_custom_file_extractor(
         source=inputs, axes=config.axes, read_func=read_func, read_kwargs=read_kwargs
@@ -350,7 +393,7 @@ def create_custom_file_dataset(
 
 
 def create_custom_image_stack_dataset(
-    config: Union[DataConfig, InferenceConfig],
+    config: NGDataConfig,
     mode: Mode,
     inputs: Any,
     targets: Optional[Any],
@@ -384,7 +427,7 @@ def create_custom_image_stack_dataset(
     Returns
     -------
     CareamicsDataset[GenericImageStack]
-        A CAREamicsDataset
+        A CAREamicsDataset.
     """
     input_extractor = create_custom_image_stack_extractor(
         inputs,

careamics/dataset_ng/legacy_interoperability.py

@@ -74,7 +74,9 @@ def imageregions_to_tileinfos(
             tile_info = _imageregion_to_tileinfo(image_region, last_tile)
             tile_infos.append(tile_info)
 
-    return [(data, [tile_info]) for data, tile_info in zip(data, tile_infos)]
+    return [
+        (data, [tile_info]) for data, tile_info in zip(data, tile_infos, strict=False)
+    ]
 
 
 def _imageregion_to_tileinfo(

careamics/dataset_ng/patch_extractor/demo_custom_image_stack_loader.py

@@ -35,7 +35,7 @@ def create_zarr_array(file_path: Path, data_path: str, data: NDArray):
 
 
 def create_zarr(file_path: Path, data_paths: Sequence[str], data: Sequence[NDArray]):
-    for data_path, array in zip(data_paths, data):
+    for data_path, array in zip(data_paths, data, strict=False):
         create_zarr_array(file_path=file_path, data_path=data_path, data=array)
 
 

careamics/dataset_ng/patch_extractor/image_stack/__init__.py

@@ -1,10 +1,12 @@
 __all__ = [
+    "CziImageStack",
     "GenericImageStack",
     "ImageStack",
     "InMemoryImageStack",
     "ZarrImageStack",
 ]
 
+from .czi_image_stack import CziImageStack
 from .image_stack_protocol import GenericImageStack, ImageStack
 from .in_memory_image_stack import InMemoryImageStack
 from .zarr_image_stack import ZarrImageStack