cellfinder 1.1.3__py3-none-any.whl → 1.2.0__py3-none-any.whl

cellfinder/napari/detect/detect_containers.py

@@ -1,8 +1,9 @@
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Optional
+from typing import List, Optional
 
 import numpy
+from brainglobe_utils.cells.cells import Cell
 
 from cellfinder.napari.input_container import InputContainer
 from cellfinder.napari.utils import html_label_widget
@@ -59,6 +60,8 @@ class DataInputs(InputContainer):
 class DetectionInputs(InputContainer):
     """Container for cell candidate detection inputs."""
 
+    skip_detection: bool = False
+    detected_cells: Optional[List[Cell]] = None
     soma_diameter: float = 16.0
     ball_xy_size: float = 6
     ball_z_size: float = 15
@@ -75,6 +78,7 @@ class DetectionInputs(InputContainer):
     def widget_representation(cls) -> dict:
         return dict(
             detection_options=html_label_widget("Detection:"),
+            skip_detection=dict(value=cls.defaults()["skip_detection"]),
             soma_diameter=cls._custom_widget("soma_diameter"),
             ball_xy_size=cls._custom_widget(
                 "ball_xy_size", custom_label="Ball filter (xy)"
@@ -107,6 +111,7 @@ class DetectionInputs(InputContainer):
 class ClassificationInputs(InputContainer):
     """Container for classification inputs."""
 
+    skip_classification: bool = False
     use_pre_trained_weights: bool = True
     trained_model: Optional[Path] = Path.home()
 
@@ -123,6 +128,9 @@ class ClassificationInputs(InputContainer):
                 value=cls.defaults()["use_pre_trained_weights"]
             ),
             trained_model=dict(value=cls.defaults()["trained_model"]),
+            skip_classification=dict(
+                value=cls.defaults()["skip_classification"]
+            ),
         )
 
 

cellfinder/napari/detect/thread_worker.py

@@ -1,3 +1,4 @@
+from magicgui.widgets import ProgressBar
 from napari.qt.threading import WorkerBase, WorkerBaseSignals
 from qtpy.QtCore import Signal
 
@@ -41,6 +42,19 @@ class Worker(WorkerBase):
         self.classification_inputs = classification_inputs
         self.misc_inputs = misc_inputs
 
+    def connect_progress_bar_callback(self, progress_bar: ProgressBar):
+        """
+        Connects the progress bar to the work so that updates are shown on
+        the bar.
+        """
+
+        def update_progress_bar(label: str, max: int, value: int):
+            progress_bar.label = label
+            progress_bar.max = max
+            progress_bar.value = value
+
+        self.update_progress_bar.connect(update_progress_bar)
+
     def work(self) -> list:
         self.update_progress_bar.emit("Setting up detection...", 1, 0)
 

cellfinder/napari/train/train.py

@@ -8,11 +8,7 @@ from napari.utils.notifications import show_info
 from qtpy.QtWidgets import QScrollArea
 
 from cellfinder.core.train.train_yml import run as train_yml
-from cellfinder.napari.utils import (
-    header_label_widget,
-    html_label_widget,
-    widget_header,
-)
+from cellfinder.napari.utils import cellfinder_header, html_label_widget
 
 from .train_containers import (
     MiscTrainingInputs,
@@ -41,7 +37,6 @@ def run_training(
 
 def training_widget() -> FunctionGui:
     @magicgui(
-        header=header_label_widget,
         training_label=html_label_widget("Network training", tag="h3"),
         **TrainingDataInputs.widget_representation(),
         **OptionalNetworkInputs.widget_representation(),
@@ -52,7 +47,6 @@ def training_widget() -> FunctionGui:
         scrollable=True,
     )
     def widget(
-        header: dict,
         training_label: dict,
         data_options: dict,
         yaml_files: Path,
@@ -161,8 +155,7 @@ def training_widget() -> FunctionGui:
             )
             worker.start()
 
-    widget.header.value = widget_header
-    widget.header.native.setOpenExternalLinks(True)
+    widget.native.layout().insertWidget(0, cellfinder_header())
 
     @widget.reset_button.changed.connect
     def restore_defaults():

cellfinder/napari/train/train_containers.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from magicgui.types import FileDialogMode
 
-from cellfinder.core.download.models import model_weight_urls
+from cellfinder.core.download.download import model_filenames
 from cellfinder.core.train.train_yml import models
 from cellfinder.napari.input_container import InputContainer
 from cellfinder.napari.utils import html_label_widget
@@ -46,7 +46,7 @@ class OptionalNetworkInputs(InputContainer):
     trained_model: Optional[Path] = Path.home()
     model_weights: Optional[Path] = Path.home()
     model_depth: str = list(models.keys())[2]
-    pretrained_model: str = str(list(model_weight_urls.keys())[0])
+    pretrained_model: str = str(list(model_filenames.keys())[0])
 
     def as_core_arguments(self) -> dict:
         arguments = super().as_core_arguments()
@@ -65,7 +65,7 @@ class OptionalNetworkInputs(InputContainer):
             ),
             pretrained_model=cls._custom_widget(
                 "pretrained_model",
-                choices=list(model_weight_urls.keys()),
+                choices=list(model_filenames.keys()),
             ),
         )
 

cellfinder/napari/utils.py

@@ -1,24 +1,10 @@
 from typing import List, Tuple
 
 import napari
+import napari.layers
 import numpy as np
-import pandas as pd
 from brainglobe_utils.cells.cells import Cell
-from pkg_resources import resource_filename
-
-brainglobe_logo = resource_filename(
-    "cellfinder", "napari/images/brainglobe.png"
-)
-
-
-widget_header = """
-<p>Efficient cell detection in large images.</p>
-<p><a href="https://brainglobe.info" style="color:gray;">Website</a></p>
-<p><a href="https://brainglobe.info/documentation/cellfinder/user-guide/napari-plugin/index.html" style="color:gray;">Documentation</a></p>
-<p><a href="https://github.com/brainglobe/cellfinder" style="color:gray;">Source</a></p>
-<p><a href="https://doi.org/10.1371/journal.pcbi.1009074" style="color:gray;">Citation</a></p>
-<p><small>For help, hover the cursor over each parameter.</small>
-"""  # noqa: E501
+from brainglobe_utils.qtpy.logo import header_widget
 
 
 def html_label_widget(label: str, *, tag: str = "b") -> dict:
@@ -31,25 +17,42 @@ def html_label_widget(label: str, *, tag: str = "b") -> dict:
     )
 
 
-header_label_widget = html_label_widget(
-    f"""
-<img src="{brainglobe_logo}"width="100">
-<p>cellfinder</p>
-""",
-    tag="h1",
-)
+def cellfinder_header():
+    """
+    Create the header containing the brainglobe logo and documentation links
+    for all cellfinder widgets.
+    """
+    return header_widget(
+        "cellfinder",
+        "Efficient cell detection in large images.",
+        documentation_path="cellfinder/user-guide/napari-plugin/index.html",
+        citation_doi="https://doi.org/10.1371/journal.pcbi.1009074",
+        help_text="For help, hover the cursor over each parameter.",
+    )
+
+
+# the xyz axis order in napari relative to ours. I.e. our zeroth axis is the
+# napari last axis. Ours is XYZ.
+napari_points_axis_order = 2, 1, 0
+# the xyz axis order in brainglobe relative to napari. I.e. napari's zeroth
+# axis is our last axis - it's just flipped
+brainglobe_points_axis_order = napari_points_axis_order
 
 
-def add_layers(points: List[Cell], viewer: napari.Viewer) -> None:
+def add_classified_layers(
+    points: List[Cell],
+    viewer: napari.Viewer,
+    unknown_name: str = "Rejected",
+    cell_name: str = "Detected",
+) -> None:
     """
-    Adds classified cell candidates as two separate point layers to the napari
-    viewer.
+    Adds cell candidates as two separate point layers - unknowns and cells, to
+    the napari viewer. Does not add any other cell types, only Cell.UNKNOWN
+    and Cell.CELL from the list of cells.
     """
-    detected, rejected = cells_to_array(points)
-
     viewer.add_points(
-        rejected,
-        name="Rejected",
+        cells_to_array(points, Cell.UNKNOWN, napari_order=True),
+        name=unknown_name,
         size=15,
         n_dimensional=True,
         opacity=0.6,
@@ -59,8 +62,8 @@ def add_layers(points: List[Cell], viewer: napari.Viewer) -> None:
         metadata=dict(point_type=Cell.UNKNOWN),
     )
     viewer.add_points(
-        detected,
-        name="Detected",
+        cells_to_array(points, Cell.CELL, napari_order=True),
+        name=cell_name,
         size=15,
         n_dimensional=True,
         opacity=0.6,
@@ -70,23 +73,61 @@ def add_layers(points: List[Cell], viewer: napari.Viewer) -> None:
     )
 
 
-def cells_df_as_np(
-    cells_df: pd.DataFrame,
-    new_order: List[int] = [2, 1, 0],
-    type_column: str = "type",
+def add_single_layer(
+    points: List[Cell],
+    viewer: napari.Viewer,
+    name: str,
+    cell_type: int,
+) -> None:
+    """
+    Adds all cells of cell_type Cell.TYPE to a new point layer in the napari
+    viewer, with given name.
+    """
+    viewer.add_points(
+        cells_to_array(points, cell_type, napari_order=True),
+        name=name,
+        size=15,
+        n_dimensional=True,
+        opacity=0.6,
+        symbol="ring",
+        face_color="lightskyblue",
+        visible=True,
+        metadata=dict(point_type=cell_type),
+    )
+
+
+def cells_to_array(
+    cells: List[Cell], cell_type: int, napari_order: bool = True
 ) -> np.ndarray:
     """
-    Convert a dataframe to an array, dropping *type_column* and re-ordering
-    the columns with *new_order*.
+    Converts all the cells of the given type as a 2D pos array.
+    The column order is either XYZ, otherwise it's the napari ordering
+    of the 3 axes (napari_points_axis_order).
     """
-    cells_df = cells_df.drop(columns=[type_column])
-    cells = cells_df[cells_df.columns[new_order]]
-    cells = cells.to_numpy()
-    return cells
+    cells = [c for c in cells if c.type == cell_type]
+    if not cells:
+        # make sure we return 2d array if cells is empty
+        return np.zeros((0, 3), dtype=np.int_)
+    points = np.array([(c.x, c.y, c.z) for c in cells])
 
+    if napari_order:
+        return points[:, napari_points_axis_order]
+    return points
 
-def cells_to_array(cells: List[Cell]) -> Tuple[np.ndarray, np.ndarray]:
-    df = pd.DataFrame([c.to_dict() for c in cells])
-    points = cells_df_as_np(df[df["type"] == Cell.CELL])
-    rejected = cells_df_as_np(df[df["type"] == Cell.UNKNOWN])
-    return points, rejected
+
+def napari_array_to_cells(
+    points: napari.layers.Points,
+    cell_type: int,
+    brainglobe_order: Tuple[int, int, int] = brainglobe_points_axis_order,
+) -> List[Cell]:
+    """
+    Takes a napari Points layer and returns a list of cell objects, one for
+    each point in the layer.
+    """
+    data = np.asarray(points.data)[:, brainglobe_order].tolist()
+
+    cells = []
+    for row in data:
+        cells.append(Cell(pos=row, cell_type=cell_type))
+
+    return cells

{cellfinder-1.1.3.dist-info → cellfinder-1.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cellfinder
-Version: 1.1.3
+Version: 1.2.0
 Summary: Automated 3D cell detection in large microscopy images
 Author-email: "Adam Tyson, Christian Niedworok, Charly Rousseau" <code@adamltyson.com>
 License: BSD-3-Clause
@@ -22,7 +22,7 @@ Classifier: Topic :: Scientific/Engineering :: Image Recognition
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: brainglobe-utils >=0.4.2
+Requires-Dist: brainglobe-utils >=0.5.0
 Requires-Dist: brainglobe-napari-io >=0.3.4
 Requires-Dist: dask[array]
 Requires-Dist: fancylog >=0.0.7
@@ -54,17 +54,17 @@ Requires-Dist: napari[pyqt5] ; extra == 'napari'
 Requires-Dist: pooch >=1 ; extra == 'napari'
 Requires-Dist: qtpy ; extra == 'napari'
 
-[![Python Version](https://img.shields.io/pypi/pyversions/cellfinder-core.svg)](https://pypi.org/project/cellfinder)
-[![PyPI](https://img.shields.io/pypi/v/cellfinder-core.svg)](https://pypi.org/project/cellfinder)
-[![Downloads](https://pepy.tech/badge/cellfinder-core)](https://pepy.tech/project/cellfinder)
-[![Wheel](https://img.shields.io/pypi/wheel/cellfinder-core.svg)](https://pypi.org/project/cellfinder)
-[![Development Status](https://img.shields.io/pypi/status/cellfinder-core.svg)](https://github.com/brainglobe/cellfinder)
+[![Python Version](https://img.shields.io/pypi/pyversions/cellfinder.svg)](https://pypi.org/project/cellfinder)
+[![PyPI](https://img.shields.io/pypi/v/cellfinder.svg)](https://pypi.org/project/cellfinder)
+[![Downloads](https://pepy.tech/badge/cellfinder)](https://pepy.tech/project/cellfinder)
+[![Wheel](https://img.shields.io/pypi/wheel/cellfinder.svg)](https://pypi.org/project/cellfinder)
+[![Development Status](https://img.shields.io/pypi/status/cellfinder.svg)](https://github.com/brainglobe/cellfinder)
 [![Tests](https://img.shields.io/github/actions/workflow/status/brainglobe/cellfinder/test_and_deploy.yml?branch=main)](https://github.com/brainglobe/cellfinder/actions)
-[![codecov](https://codecov.io/gh/brainglobe/cellfinder-core/branch/main/graph/badge.svg?token=nx1lhNI7ox)](https://codecov.io/gh/brainglobe/cellfinder)
+[![codecov](https://codecov.io/gh/brainglobe/cellfinder/branch/main/graph/badge.svg?token=nx1lhNI7ox)](https://codecov.io/gh/brainglobe/cellfinder)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/python/black)
 [![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
-[![Contributions](https://img.shields.io/badge/Contributions-Welcome-brightgreen.svg)](https://brainglobe.info/developers/index.html)
+[![Contributions](https://img.shields.io/badge/Contributions-Welcome-brightgreen.svg)](https://brainglobe.info/community/developers/index.html)
 [![Twitter](https://img.shields.io/twitter/follow/brain_globe?style=social)](https://twitter.com/brain_globe)
 
 # cellfinder

{cellfinder-1.1.3.dist-info → cellfinder-1.2.0.dist-info}/RECORD

@@ -1,7 +1,7 @@
-cellfinder/__init__.py,sha256=XwXxMZJgw62dOHhrAKMQk0CE3378WRQWoC-kpf5LLpE,935
+cellfinder/__init__.py,sha256=7H9UKFWCk-TNkFLwk-D4EVU5-rJZsGxfo0qcaFVcfKY,1035
 cellfinder/cli_migration_warning.py,sha256=gPtNrtnXvWpl5q0k_EGAQZg0DwcpCmuBTgpg56n5NfA,1578
 cellfinder/core/__init__.py,sha256=pRFuQsl78HEK0S6gvhJw70QLbjjSBzP-GFO0AtVaGtk,62
-cellfinder/core/main.py,sha256=3Wg4QvBUlaHq04Yltjg9FSiePAhtGeFL1C-6Z1SI0Gk,3900
+cellfinder/core/main.py,sha256=Y-4Wt9d9K7o2l3IO7acZbtNuhqZzF5UU-rMJksb6k94,4392
 cellfinder/core/types.py,sha256=lTqWE4v0SMM0qLAZJdyAzqV1nLgDtobEpglNJcXt160,106
 cellfinder/core/classify/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cellfinder/core/classify/augment.py,sha256=8dMbM7KhimM6NMgdMC53oHoCfYj1CIB-h3Yk8CZAxPw,6321
@@ -12,7 +12,7 @@ cellfinder/core/classify/tools.py,sha256=UqABKS9KnkwR3PIhGRl7xHJbADP0mgVRSxXI5dy
 cellfinder/core/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cellfinder/core/config/cellfinder.conf,sha256=5i8axif7ekMutKDiVnZRs-LiJrgVQljg_beltidqtNk,56
 cellfinder/core/detect/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cellfinder/core/detect/detect.py,sha256=bsiOPyxM3D_YZiYxqyauTxe7C4C2-rb_9yYiJiYaylM,9102
+cellfinder/core/detect/detect.py,sha256=iEYaYuYCSR4VJXmlFbEE1ti9Pjpv6m4rSfFILSOYmhE,9592
 cellfinder/core/detect/filters/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cellfinder/core/detect/filters/setup_filters.py,sha256=sUyZ2dKbfwhn4YTq3kLVTHkckZZ460AVozLfoz7hJK8,2084
 cellfinder/core/detect/filters/plane/__init__.py,sha256=lybcPbVDnurEQeq2FiLq0zR8p_ztarQOlajhdh1Q2-4,40
@@ -20,44 +20,41 @@ cellfinder/core/detect/filters/plane/classical_filter.py,sha256=Nton_nrvv6LhNlK1
 cellfinder/core/detect/filters/plane/plane_filter.py,sha256=PWcAHDKB3qn3i9aSmQzUTEi3tgmccrf24DipjnYbOg0,2746
 cellfinder/core/detect/filters/plane/tile_walker.py,sha256=lhKrq-MB35bR0_JYgj7WMR4otuaZ6XRDDhJhKyH1yS8,3001
 cellfinder/core/detect/filters/volume/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cellfinder/core/detect/filters/volume/ball_filter.py,sha256=nNGYAjDWst4Ufh6o6LAb5CVi5hFqYi2ObyrwgChbkQw,11175
-cellfinder/core/detect/filters/volume/structure_detection.py,sha256=8lSyDFiqn5lYoE_mDLpXTUOsWGVm2-suGttZBdDAqmA,9152
-cellfinder/core/detect/filters/volume/structure_splitting.py,sha256=VuXKAOHG6f63ommPxZC08JRoegbQgZUReZAmvY5nm_U,7656
-cellfinder/core/detect/filters/volume/volume_filter.py,sha256=nBc9kZhsZ2jsyuzizXcx6s0i5-Vc7BfUfDqtIxhGUSo,6873
+cellfinder/core/detect/filters/volume/ball_filter.py,sha256=ZEg8FNty-VD5N9j4FLZ18G-BuSvxjHs2-QTblwKcZgw,13894
+cellfinder/core/detect/filters/volume/structure_detection.py,sha256=mTHi0_A9FCK39I6fZm2dfMpDxIkfaidOIf6eCjTw-70,11307
+cellfinder/core/detect/filters/volume/structure_splitting.py,sha256=XzTYguVT8VdTu2h4-Jdt5Yyeu8VBYmdRo5jmwwLwuck,7660
+cellfinder/core/detect/filters/volume/volume_filter.py,sha256=BJ8bStlNvMWsGlBekeqXpS8d9YKoLe3ifMfrEPpva2Q,7035
 cellfinder/core/download/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cellfinder/core/download/cli.py,sha256=uejrDBoveybeyMq-tcn8460r2Hf3iC1FhpEC2sXs7EI,1807
-cellfinder/core/download/download.py,sha256=oKxo6Ch3wCAbVmyzjvIhnaSUb0sF5P8mJYGbJCU9Gag,3933
-cellfinder/core/download/models.py,sha256=mLb6wAUn-tH1FtgvQU6ooLXqXetTP4D5Jd4_gPN-kJo,1359
-cellfinder/core/tools/IO.py,sha256=q-euCP1s3iuWYvD2V72sPSBfwr5A1ETcL6Z_K41mLV0,1235
+cellfinder/core/download/cli.py,sha256=X9L9ZIkWqs58hX8G8q_0AKN4gk8BhydGxI9nLpdHQQE,1764
+cellfinder/core/download/download.py,sha256=YQP4NMM9Xt0rECRJEV5z6RCZNi5uCFhohFnDreH0qHA,3277
 cellfinder/core/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cellfinder/core/tools/array_operations.py,sha256=LDbqWA_N2YtxeKS877QYdJRL2FCMC1R1ExJtdb6-vEA,3371
 cellfinder/core/tools/geometry.py,sha256=xlEQQmVQ9jcXqRzUqU554P8VxkaWkc5J_YhjkkKlI0Q,1124
 cellfinder/core/tools/image_processing.py,sha256=z27bGjf3Iv3G4Nt1OYzpEnIYQNc4nNomj_QitqvZB78,2269
-cellfinder/core/tools/prep.py,sha256=A1tfHZmkGFpbb7cjLdfP8KavZNqRwzdum92NW8Et01o,2553
-cellfinder/core/tools/source_files.py,sha256=NCPeA_kvnPWgS_fxWarc-9nBNjxkgL1xMFg-Co_kPlA,791
+cellfinder/core/tools/prep.py,sha256=hGWwXxeP88ahp6ji2bkBu9FOz8BmrZsVwI-CEv4qxQ4,2473
+cellfinder/core/tools/source_files.py,sha256=vvwsIMe1ULKvXg_x22L75iqvCyMjEbUjJsDFQk3GYzY,856
 cellfinder/core/tools/system.py,sha256=6iSOLrz2mtKgOIdwjp_VS0-74XQCuaQYCvWAViJgEus,2232
 cellfinder/core/tools/tf.py,sha256=jNU97-gIB51rLube9EoZ9bREkbqWRk-xPZhDTXG_jE4,1713
 cellfinder/core/tools/tiff.py,sha256=NzIz6wq2GzxmcIhawFMwZADe-uQO2rIG46H7xkpGKLs,2899
 cellfinder/core/tools/tools.py,sha256=G8oDGNRuWkzEJDnnC4r3SNGgpVbqbelCZR5ODk9JRzs,4867
 cellfinder/core/train/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cellfinder/core/train/train_yml.py,sha256=TO_8e6Uz1S-P49o53gB_4i97Afz6RCHqmyyIrA70TZ8,13214
+cellfinder/core/train/train_yml.py,sha256=0iiROBdxNoMyMoPGYC8tq6bGM3jzAKlGA2LABgoqd6M,13139
 cellfinder/napari/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cellfinder/napari/curation.py,sha256=jz7GekuuzOdwiEFLarvvO5Bho68k8eL7AjObMdEoPXw,21447
 cellfinder/napari/input_container.py,sha256=tkm0dkPt7kSL8Xkvs1fh8M6vKWw57QLIt_wv74HFkGk,2150
 cellfinder/napari/napari.yaml,sha256=WMR1CIAmYIVyQngbdbomTRZLvlDbb6LxsXsvTRClQnE,921
 cellfinder/napari/sample_data.py,sha256=oUST23q09MM8dxHbUCmO0AjtXG6OlR_32LLqP0EU2UA,732
-cellfinder/napari/utils.py,sha256=mCy4Lr_gE2wWgRUSEiApNUjgLLAz0SSahTZnmUnRbgQ,2592
+cellfinder/napari/utils.py,sha256=AwTs76M9azutHhHj2yuaKErDEQ5F6pFbIIakBfzen6M,3824
 cellfinder/napari/detect/__init__.py,sha256=BD9Bg9NTAr6yRTq2A_p58U6j4w5wbY0sdXwhPJ3MSMY,34
-cellfinder/napari/detect/detect.py,sha256=Jr4-lDGIntwcxSQ1Ne4xoA0SaKd4kf4zUT8MPyyO5ic,7443
-cellfinder/napari/detect/detect_containers.py,sha256=C_tN7qwWNHhYFRRn_2yQ7QDyxpj3pQXLZalO0UQ_cbw,5020
-cellfinder/napari/detect/thread_worker.py,sha256=BchLapCyML4SBDfihsqNLvqGM8FVcXEejaGg8MSkMCs,2604
-cellfinder/napari/images/brainglobe.png,sha256=IT2zfikD2vKTOg--e6bMRHr5mC2x3s-eOt_t0eblvQ0,21216
+cellfinder/napari/detect/detect.py,sha256=gX10U4HHcni1ff3zYXkXYX6dWMZErYpvzVde56yV80w,13658
+cellfinder/napari/detect/detect_containers.py,sha256=Xx-E2JTbe5Ih_1m5ZhQ0pCYFxfdQxVJMMfGh9EZExms,5377
+cellfinder/napari/detect/thread_worker.py,sha256=3xGUPSthycpErcVxl_yc5soIv_z0Hf0iEaZq0Yx90OM,3078
 cellfinder/napari/train/__init__.py,sha256=xo4CK-DvSecInGEc2ohcTgQYlH3iylFnGvKTCoq2WkI,35
-cellfinder/napari/train/train.py,sha256=Cv8ivPWZoJJ-Iq1vW1JUmViaSnBPeqs07jBvZfOZQLc,6061
-cellfinder/napari/train/train_containers.py,sha256=mYI_M1QssWgPBpkqViqgj1Ls32lVRUAjt6OGTqcrKI4,4390
-cellfinder-1.1.3.dist-info/LICENSE,sha256=Tw8iMytIDXLSmcIUsbQmRWojstl9yOWsPCx6ZT6dZLY,1564
-cellfinder-1.1.3.dist-info/METADATA,sha256=znQeFj56Dxn2pna6L-ZYb98Ht8c5akgzcYhzhDu7YgI,6652
-cellfinder-1.1.3.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-cellfinder-1.1.3.dist-info/entry_points.txt,sha256=cKKjU8GPiN-TRelG2sT2JCKAcB9XDCjP6g9atE9pSoY,247
-cellfinder-1.1.3.dist-info/top_level.txt,sha256=jyTQzX-tDjbsMr6s-E71Oy0IKQzmHTXSk4ZhpG5EDSE,11
-cellfinder-1.1.3.dist-info/RECORD,,
+cellfinder/napari/train/train.py,sha256=zJY7zKcLqDTDtD76thmbwViEU4tTFCmXZze-zHsTpoo,5941
+cellfinder/napari/train/train_containers.py,sha256=1wZ_GPe7B5XsLYs5XIx4m8GMw5KeVhg6SchhPtXu4V8,4386
+cellfinder-1.2.0.dist-info/LICENSE,sha256=Tw8iMytIDXLSmcIUsbQmRWojstl9yOWsPCx6ZT6dZLY,1564
+cellfinder-1.2.0.dist-info/METADATA,sha256=0_L_i066TdGFnfaRZe8zY-y0XwF7HX88F0mzV4AqLEw,6632
+cellfinder-1.2.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+cellfinder-1.2.0.dist-info/entry_points.txt,sha256=cKKjU8GPiN-TRelG2sT2JCKAcB9XDCjP6g9atE9pSoY,247
+cellfinder-1.2.0.dist-info/top_level.txt,sha256=jyTQzX-tDjbsMr6s-E71Oy0IKQzmHTXSk4ZhpG5EDSE,11
+cellfinder-1.2.0.dist-info/RECORD,,

cellfinder/core/download/models.py

@@ -1,49 +0,0 @@
-import os
-from pathlib import Path
-from typing import Literal
-
-from cellfinder.core import logger
-from cellfinder.core.download.download import download
-
-model_weight_urls = {
-    "resnet50_tv": "https://gin.g-node.org/cellfinder/models/raw/"
-    "master/resnet50_tv.h5",
-    "resnet50_all": "https://gin.g-node.org/cellfinder/models/raw/"
-    "master/resnet50_weights.h5",
-}
-
-download_requirements_gb = {
-    "resnet50_tv": 0.18,
-    "resnet50_all": 0.18,
-}
-
-model_type = Literal["resnet50_tv", "resnet50_all"]
-
-
-def main(model_name: model_type, download_path: os.PathLike) -> Path:
-    """
-    For a given model name and download path, download the model file
-    and return the path to the downloaded file.
-    """
-    download_path = Path(download_path)
-
-    model_weight_dir = download_path / "model_weights"
-    model_path = model_weight_dir / f"{model_name}.h5"
-    if not model_path.exists():
-        model_weight_dir.mkdir(parents=True)
-
-        logger.info(
-            f"Downloading '{model_name}' model. This may take a little while."
-        )
-
-        download(
-            model_path,
-            model_weight_urls[model_name],
-            model_name,
-            download_requires=download_requirements_gb[model_name],
-        )
-
-    else:
-        logger.info(f"Model already exists at {model_path}. Skipping download")
-
-    return model_path

cellfinder/core/tools/IO.py

@@ -1,48 +0,0 @@
-import glob
-import os
-from typing import Tuple
-
-import numpy as np
-from brainglobe_utils.general.system import get_sorted_file_paths
-from dask import array as da
-from dask import delayed
-from tifffile import TiffFile, imread
-
-
-def get_tiff_meta(
-    path: str,
-) -> Tuple[Tuple[int, int], np.dtype]:
-    with TiffFile(path) as tfile:
-        nz = len(tfile.pages)
-        if not nz:
-            raise ValueError(f"tiff file {path} has no pages!")
-        first_page = tfile.pages[0]
-
-    return tfile.pages[0].shape, first_page.dtype
-
-
-lazy_imread = delayed(imread)  # lazy reader
-
-
-def read_with_dask(path):
-    """
-    Based on https://github.com/tlambert03/napari-ndtiffs
-    :param path:
-    :return:
-    """
-
-    if path.endswith(".txt"):
-        with open(path, "r") as f:
-            filenames = [line.rstrip() for line in f.readlines()]
-
-    else:
-        filenames = glob.glob(os.path.join(path, "*.tif"))
-
-    shape, dtype = get_tiff_meta(filenames[0])
-    lazy_arrays = [lazy_imread(fn) for fn in get_sorted_file_paths(filenames)]
-    dask_arrays = [
-        da.from_delayed(delayed_reader, shape=shape, dtype=dtype)
-        for delayed_reader in lazy_arrays
-    ]
-    stack = da.stack(dask_arrays, axis=0)
-    return stack