Bm/version 1.4.0

.gitignore

@@ -1,13 +1,12 @@
 **/.ipynb_checkpoints
 **/__pycache__
 deeptrack-app/*
-*/datasets/*
+
 paper-examples/models/*
 
 build/*
 dist/*
 *.egg-info/
-*/datasets/*
 */theory
 _src/build/**/*
 
@@ -16,6 +15,11 @@ ParticleSizing
 CellData
 ParticleTracking
 data/
-datasets/
 examples/**/*/models/
 **/node_modules/
+
+*.tif
+*.png 
+*.jpg
+*.jpeg
+*.npy

deeptrack/__init__.py

@@ -2,6 +2,7 @@
 from pint import UnitRegistry, Context
 from .backend.pint_definition import pint_definitions
 
+
 units = UnitRegistry(pint_definitions.split("\n"))
 
 import tensorflow as tf
@@ -27,6 +28,7 @@
 from .statistics import *
 from .holography import *
 
+
 from .image import strip
 
 from . import (
@@ -39,4 +41,5 @@
     backend,
     test,
     visualization,
+    datasets,
 )

deeptrack/augmentations.py

@@ -681,6 +681,30 @@ def image_to_crop(image):
         )
 
 
+class CropTight(Feature):
+    def __init__(self, eps=1e-10, **kwargs):
+        """Crops input array to remove empty space.
+
+        Removes indices from the start and end of the array, where all values are below eps.
+
+        Currently only works for 3D arrays.
+
+        Parameters
+        ----------
+        eps : float, optional
+            The threshold for considering a pixel to be empty, by default 1e-10"""
+        super().__init__(eps=eps, **kwargs)
+
+    def get(self, image, eps, **kwargs):
+        image = np.asarray(image)
+
+        image = image[..., np.any(image > eps, axis=(0, 1))]
+        image = image[np.any(image > eps, axis=(1, 2)), ...]
+        image = image[:, np.any(image > eps, axis=(0, 2)), :]
+
+        return image
+
+
 class Pad(Augmentation):
     """Pads the image.
 

deeptrack/datasets/__init__.py

@@ -0,0 +1,6 @@
+from deeptrack.datasets import (
+    detection_QuantumDots,
+    segmentation_ssTEM_drosophila,
+    regression_holography_nanoparticles,
+    segmentation_fluorescence_u2os,
+)

deeptrack/datasets/detection_QuantumDots/__init__.py

@@ -0,0 +1,3 @@
+"""detection_QuantumDots dataset."""
+
+from .detection_QuantumDots import DetectionQuantumdots

deeptrack/datasets/detection_QuantumDots/checksums.tsv

@@ -0,0 +1,2 @@
+https://drive.google.com/file/d/1naaoxIaAU1F_rBaI-I1pB1K4Sp6pq_Jv/view?usp=sharing	67850	95f52b3bbfbf1b2fe7f213021fbd63bdf5040a4dc099ef6903243feb849f06c6	view
+https://drive.google.com/u/1/uc?id=1naaoxIaAU1F_rBaI-I1pB1K4Sp6pq_Jv&export=download	543855765	375476e7a70fa3c1a8f91f2e4035b896b8d8acb1800dae2e1e028c2db485a030	QuantumDots.zip

deeptrack/datasets/detection_QuantumDots/detection_QuantomDuts_test.py

@@ -0,0 +1,24 @@
+"""detection_QuantumDots dataset."""
+
+import tensorflow_datasets as tfds
+from . import detection_QuantumDots
+
+
+class DetectionQuantumdotsTest(tfds.testing.DatasetBuilderTestCase):
+  """Tests for detection_QuantumDots dataset."""
+  # TODO(detection_QuantumDots):
+  DATASET_CLASS = detection_QuantumDots.DetectionQuantumdots
+  SPLITS = {
+      'train': 3,  # Number of fake train example
+      'test': 1,  # Number of fake test example
+  }
+
+  # If you are calling `download/download_and_extract` with a dict, like:
+  #   dl_manager.download({'some_key': 'http://a.org/out.txt', ...})
+  # then the tests needs to provide the fake output paths relative to the
+  # fake data directory
+  # DL_EXTRACT_RESULT = {'some_key': 'output_file1.txt', ...}
+
+
+if __name__ == '__main__':
+  tfds.testing.test_main()

deeptrack/datasets/detection_QuantumDots/detection_QuantumDots.py

@@ -0,0 +1,69 @@
+"""detection_QuantumDots dataset."""
+
+import tensorflow_datasets as tfds
+import tensorflow as tf
+import numpy as np
+
+# TODO(detection_QuantumDots): Markdown description  that will appear on the catalog page.
+_DESCRIPTION = """
+Sequential images of quantum dots in a fluorescent microscope. The dataset is unlabeled. 
+"""
+
+# TODO(detection_QuantumDots): BibTeX citation
+_CITATION = """
+"""
+
+
+class DetectionQuantumdots(tfds.core.GeneratorBasedBuilder):
+    """DatasetBuilder for detection_QuantumDots dataset."""
+
+    VERSION = tfds.core.Version("1.0.0")
+    RELEASE_NOTES = {
+        "1.0.0": "Initial release.",
+    }
+
+    def _info(self) -> tfds.core.DatasetInfo:
+        """Returns the dataset metadata."""
+        # TODO(detection_QuantumDots): Specifies the tfds.core.DatasetInfo object
+        return tfds.core.DatasetInfo(
+            builder=self,
+            description=_DESCRIPTION,
+            features=tfds.features.FeaturesDict(
+                {
+                    # These are the features of your dataset like images, labels ...
+                    "image": tfds.features.Image(
+                        shape=(1200, 1200, 1),
+                        dtype=tf.uint16,
+                    ),
+                }
+            ),
+            # If there's a common (input, target) tuple from the
+            # features, specify them here. They'll be used if
+            # `as_supervised=True` in `builder.as_dataset`.
+            supervised_keys=None,  # Set to `None` to disable
+            homepage="https://dataset-homepage/",
+            citation=_CITATION,
+        )
+
+    def _split_generators(self, dl_manager: tfds.download.DownloadManager):
+        """Returns SplitGenerators."""
+        # TODO(detection_QuantumDots): Downloads the data and defines the splits
+        path = dl_manager.download_and_extract(
+            "https://drive.google.com/u/1/uc?id=1naaoxIaAU1F_rBaI-I1pB1K4Sp6pq_Jv&export=download"
+        )
+
+        # TODO(detection_QuantumDots): Returns the Dict[split names, Iterator[Key, Example]]
+        return {
+            "train": self._generate_examples(path / "QuantumDots"),
+        }
+
+    def _generate_examples(self, path):
+        """Yields examples."""
+        tifpath = path / "Qdots.tif"
+
+        image_stack = tfds.core.lazy_imports.tifffile.imread(tifpath)
+        image_stack = np.expand_dims(image_stack, axis=-1)
+        for i, image in enumerate(image_stack):
+            yield str(i), {
+                "image": image,
+            }

deeptrack/datasets/regression_holography_nanoparticles/__init__.py

@@ -0,0 +1,3 @@
+"""regression_holography_nanoparticles dataset."""
+
+from .regression_holography_nanoparticles import RegressionHolographyNanoparticles

deeptrack/datasets/regression_holography_nanoparticles/checksums.tsv

@@ -0,0 +1,3 @@
+# TODO(regression_holography_nanoparticles): If your dataset downloads files, then the checksums
+# will be automatically added here when running
+# `tfds build --register_checksums`.

deeptrack/datasets/regression_holography_nanoparticles/regression_holography_nanoparticles.py

@@ -0,0 +1,83 @@
+"""regression_holography_nanoparticles dataset."""
+
+import tensorflow_datasets as tfds
+import tensorflow as tf
+import numpy as np
+
+# TODO(regression_holography_nanoparticles): Markdown description  that will appear on the catalog page.
+_DESCRIPTION = """
+"""
+
+# TODO(regression_holography_nanoparticles): BibTeX citation
+_CITATION = """
+"""
+
+
+class RegressionHolographyNanoparticles(tfds.core.GeneratorBasedBuilder):
+    """DatasetBuilder for regression_holography_nanoparticles dataset."""
+
+    VERSION = tfds.core.Version("1.0.0")
+    RELEASE_NOTES = {
+        "1.0.0": "Initial release.",
+    }
+
+    def _info(self) -> tfds.core.DatasetInfo:
+        """Returns the dataset metadata."""
+        # TODO(regression_holography_nanoparticles): Specifies the tfds.core.DatasetInfo object
+        return tfds.core.DatasetInfo(
+            builder=self,
+            description=_DESCRIPTION,
+            features=tfds.features.FeaturesDict(
+                {
+                    # These are the features of your dataset like images, labels ...
+                    "image": tfds.features.Tensor(shape=(64, 64, 2), dtype=tf.float64),
+                    "radius": tfds.features.Scalar(tf.float64),
+                    "refractive_index": tfds.features.Scalar(tf.float64),
+                }
+            ),
+            # If there's a common (input, target) tuple from the
+            # features, specify them here. They'll be used if
+            # `as_supervised=True` in `builder.as_dataset`.
+            supervised_keys=(
+                "image",
+                "radius",
+                "refractive_index",
+            ),  # Set to `None` to disable
+            homepage="https://dataset-homepage/",
+            citation=_CITATION,
+        )
+
+    def _split_generators(self, dl_manager: tfds.download.DownloadManager):
+        """Returns SplitGenerators."""
+        # TODO(regression_holography_nanoparticles): Downloads the data and defines the splits
+        path = dl_manager.download_and_extract(
+            "https://drive.google.com/u/1/uc?id=1LJqWYmLj93WYLKaLm_yQFmiR1FZHhf1r&export=download"
+        )
+
+        # TODO(regression_holography_nanoparticles): Returns the Dict[split names, Iterator[Key, Example]]
+        return {
+            "train": self._generate_examples(path, "train"),
+            "test": self._generate_examples(path, "test"),
+        }
+
+    def _generate_examples(self, path, split):
+        """Yields examples."""
+        # TODO(regression_holography_nanoparticles): Yields (key, example) tuples from the dataset
+
+        if split == "train":
+            data = np.load(path / "training_set.npy")
+            radius = np.load(path / "training_radius.npy")
+            refractive_index = np.load(path / "training_n.npy")
+        elif split == "test":
+            data = np.load(path / "validation_set.npy")
+            radius = np.load(path / "validation_radius.npy")
+            refractive_index = np.load(path / "validation_n.npy")
+        else:
+            raise ValueError("Split not recognized:", split)
+
+        for idx in range(data.shape[0]):
+            yield str(idx), {
+                "image": data[idx],
+                "radius": radius[idx],
+                "refractive_index": refractive_index[idx],
+            }

deeptrack/datasets/regression_holography_nanoparticles/regression_holography_nanoparticles_test.py

@@ -0,0 +1,24 @@
+"""regression_holography_nanoparticles dataset."""
+
+import tensorflow_datasets as tfds
+from . import regression_holography_nanoparticles
+
+
+class RegressionHolographyNanoparticlesTest(tfds.testing.DatasetBuilderTestCase):
+  """Tests for regression_holography_nanoparticles dataset."""
+  # TODO(regression_holography_nanoparticles):
+  DATASET_CLASS = regression_holography_nanoparticles.RegressionHolographyNanoparticles
+  SPLITS = {
+      'train': 3,  # Number of fake train example
+      'test': 1,  # Number of fake test example
+  }
+
+  # If you are calling `download/download_and_extract` with a dict, like:
+  #   dl_manager.download({'some_key': 'http://a.org/out.txt', ...})
+  # then the tests needs to provide the fake output paths relative to the
+  # fake data directory
+  # DL_EXTRACT_RESULT = {'some_key': 'output_file1.txt', ...}
+
+
+if __name__ == '__main__':
+  tfds.testing.test_main()

deeptrack/datasets/segmentation_fluorescence_u2os/__init__.py

@@ -0,0 +1,3 @@
+"""segmentation_fluorescence_u2os dataset."""
+
+from .segmentation_fluorescence_u2os import SegmentationFluorescenceU2os

deeptrack/datasets/segmentation_fluorescence_u2os/checksums.tsv

@@ -0,0 +1,3 @@
+# TODO(segmentation_fluorescence_u2os): If your dataset downloads files, then the checksums
+# will be automatically added here when running
+# `tfds build --register_checksums`.