cellfinder 1.3.0rc1__py3-none-any.whl → 1.3.0rc2__py3-none-any.whl

cellfinder/__init__.py

@@ -26,6 +26,7 @@ except PackageNotFoundError as e:
 
 # Set the Keras backend to torch
 os.environ["KERAS_BACKEND"] = "torch"
+os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"
 
 __license__ = "BSD-3-Clause"
 

cellfinder/core/classify/classify.py

@@ -1,4 +1,5 @@
 import os
+from datetime import datetime
 from typing import Any, Callable, Dict, List, Optional, Tuple
 
 import keras
@@ -50,6 +51,8 @@ def main(
     # Too many workers doesn't increase speed, and uses huge amounts of RAM
     workers = get_num_processes(min_free_cpu_cores=n_free_cpus)
 
+    start_time = datetime.now()
+
     logger.debug("Initialising cube generator")
     inference_generator = CubeGeneratorFromFile(
         points,
@@ -90,6 +93,11 @@ def main(
         cell.type = predictions[idx] + 1
         points_list.append(cell)
 
+    time_elapsed = datetime.now() - start_time
+    print(
+        "Classfication complete - all points done in : {}".format(time_elapsed)
+    )
+
     return points_list
 
 

cellfinder/core/classify/cube_generator.py

@@ -40,7 +40,7 @@ class CubeGeneratorFromFile(Sequence):
         background_array: types.array,
         voxel_sizes: Tuple[int, int, int],
         network_voxel_sizes: Tuple[int, int, int],
-        batch_size: int = 16,
+        batch_size: int = 64,
         cube_width: int = 50,
         cube_height: int = 50,
         cube_depth: int = 20,
@@ -345,7 +345,7 @@ class CubeGeneratorFromDisk(Sequence):
         signal_list: List[Union[str, Path]],
         background_list: List[Union[str, Path]],
         labels: Optional[List[int]] = None,  # only if training or validating
-        batch_size: int = 16,
+        batch_size: int = 64,
         shape: Tuple[int, int, int] = (50, 50, 20),
         channels: int = 2,
         classes: int = 2,

cellfinder/core/main.py

@@ -18,7 +18,7 @@ def main(
     trained_model: Optional[os.PathLike] = None,
     model_weights: Optional[os.PathLike] = None,
     model: model_type = "resnet50_tv",
-    batch_size: int = 32,
+    batch_size: int = 64,
     n_free_cpus: int = 2,
     network_voxel_sizes: Tuple[int, int, int] = (5, 1, 1),
     soma_diameter: int = 16,

cellfinder/napari/curation.py

@@ -54,7 +54,7 @@ class CurationWidget(QWidget):
         self.save_empty_cubes = save_empty_cubes
         self.max_ram = max_ram
         self.voxel_sizes = [5, 2, 2]
-        self.batch_size = 32
+        self.batch_size = 64
         self.viewer = viewer
 
         self.signal_layer = None

cellfinder/napari/detect/detect.py

@@ -253,8 +253,9 @@ def detect_widget() -> FunctionGui:
         max_cluster_size: int,
         classification_options,
         skip_classification: bool,
-        trained_model: Optional[Path],
         use_pre_trained_weights: bool,
+        trained_model: Optional[Path],
+        batch_size: int,
         misc_options,
         start_plane: int,
         end_plane: int,
@@ -298,6 +299,8 @@ def detect_widget() -> FunctionGui:
             should be attempted
         use_pre_trained_weights : bool
             Select to use pre-trained model weights
+        batch_size : int
+            How many points to classify at one time
         skip_classification : bool
             If selected, the classification step is skipped and all cells from
             the detection stage are added
@@ -372,7 +375,10 @@ def detect_widget() -> FunctionGui:
         if use_pre_trained_weights:
             trained_model = None
         classification_inputs = ClassificationInputs(
-            skip_classification, use_pre_trained_weights, trained_model
+            skip_classification,
+            use_pre_trained_weights,
+            trained_model,
+            batch_size,
         )
 
         if analyse_local:

cellfinder/napari/detect/detect_containers.py

@@ -114,6 +114,7 @@ class ClassificationInputs(InputContainer):
     skip_classification: bool = False
     use_pre_trained_weights: bool = True
     trained_model: Optional[Path] = Path.home()
+    batch_size: int = 64
 
     def as_core_arguments(self) -> dict:
         args = super().as_core_arguments()
@@ -131,6 +132,7 @@ class ClassificationInputs(InputContainer):
             skip_classification=dict(
                 value=cls.defaults()["skip_classification"]
             ),
+            batch_size=dict(value=cls.defaults()["batch_size"]),
         )
 
 

cellfinder/napari/detect/thread_worker.py

@@ -72,10 +72,10 @@ class Worker(WorkerBase):
         def classify_callback(batch: int) -> None:
             self.update_progress_bar.emit(
                 "Classifying cells",
-                # Default cellfinder-core batch size is 32. This seems to give
+                # Default cellfinder-core batch size is 64. This seems to give
                 # a slight underestimate of the number of batches though, so
                 # allow for batch number to go over this
-                max(self.npoints_detected // 32 + 1, batch + 1),
+                max(self.npoints_detected // 64 + 1, batch + 1),
                 batch + 1,
             )
 

{cellfinder-1.3.0rc1.dist-info → cellfinder-1.3.0rc2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cellfinder
-Version: 1.3.0rc1
+Version: 1.3.0rc2
 Summary: Automated 3D cell detection in large microscopy images
 Author-email: "Adam Tyson, Christian Niedworok, Charly Rousseau" <code@adamltyson.com>
 License: BSD-3-Clause

{cellfinder-1.3.0rc1.dist-info → cellfinder-1.3.0rc2.dist-info}/RECORD

@@ -1,12 +1,12 @@
-cellfinder/__init__.py,sha256=rxpLq2RH-aoB3vm93M3btIrGi2lPxZRIbmzsKhkkVnI,1118
+cellfinder/__init__.py,sha256=S5oQ3EORuyQTMYC4uUuzGKZ23J3Ya6q-1DOBib1KfiA,1166
 cellfinder/cli_migration_warning.py,sha256=gPtNrtnXvWpl5q0k_EGAQZg0DwcpCmuBTgpg56n5NfA,1578
 cellfinder/core/__init__.py,sha256=pRFuQsl78HEK0S6gvhJw70QLbjjSBzP-GFO0AtVaGtk,62
-cellfinder/core/main.py,sha256=6Uby8WuJ-U6_XBzHIla-fm3WQ2q6Vu7rYjme5Igfp_8,3625
+cellfinder/core/main.py,sha256=t2mkq6iieEytbPckehBB43juwN5E-vhzstLSs620vdM,3625
 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
-cellfinder/core/classify/classify.py,sha256=aL2kNojKb4wsk7Zm26yq2QRiazRbwUO_cbbC2BJN0uc,3061
-cellfinder/core/classify/cube_generator.py,sha256=L5BvTDiHbkJ6VFeApALGtCV7Ws--jXR1foYY-bL0Buc,17125
+cellfinder/core/classify/classify.py,sha256=33ZvNDmgVabH_6p4jV9Xi8bLKwDZnVhzlImrL_TlnBk,3269
+cellfinder/core/classify/cube_generator.py,sha256=jC5aogTVy213PHouViSR9CgKkuOks3yk6csQC5kRoOE,17125
 cellfinder/core/classify/resnet.py,sha256=vGa85y_NcQnOXwAt5EtatLx5mrO8IoShCcNKtJ5-EFg,10034
 cellfinder/core/classify/tools.py,sha256=s5PEKAsZVbVuoferZ_nqMUM0f2bV_8WEKsdKe3SXEuE,2560
 cellfinder/core/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -39,21 +39,21 @@ cellfinder/core/tools/tools.py,sha256=G8oDGNRuWkzEJDnnC4r3SNGgpVbqbelCZR5ODk9JRz
 cellfinder/core/train/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cellfinder/core/train/train_yml.py,sha256=9QXv2wk24G8hYskMnBij7OngEELUWySK2fH4NFbYWw4,13260
 cellfinder/napari/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cellfinder/napari/curation.py,sha256=jz7GekuuzOdwiEFLarvvO5Bho68k8eL7AjObMdEoPXw,21447
+cellfinder/napari/curation.py,sha256=nbxCwY2bhEPM15Wf3S_Ff8qGdLSWojr4X48mmAJqD3U,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=AwTs76M9azutHhHj2yuaKErDEQ5F6pFbIIakBfzen6M,3824
 cellfinder/napari/detect/__init__.py,sha256=BD9Bg9NTAr6yRTq2A_p58U6j4w5wbY0sdXwhPJ3MSMY,34
-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/detect/detect.py,sha256=VB3SLZvqJhjuypjpaZuV9JscQ-sE8yVHG8RzEsZWfeA,13809
+cellfinder/napari/detect/detect_containers.py,sha256=j9NTsIyyDNrhlI2dc7hvc7QlxvI1NRHlCe137v7fsPg,5467
+cellfinder/napari/detect/thread_worker.py,sha256=PWM3OE-FpK-dpdhaE_Gi-2lD3u8sL-SJ13mp0pMhTyI,3078
 cellfinder/napari/train/__init__.py,sha256=xo4CK-DvSecInGEc2ohcTgQYlH3iylFnGvKTCoq2WkI,35
 cellfinder/napari/train/train.py,sha256=zJY7zKcLqDTDtD76thmbwViEU4tTFCmXZze-zHsTpoo,5941
 cellfinder/napari/train/train_containers.py,sha256=1wZ_GPe7B5XsLYs5XIx4m8GMw5KeVhg6SchhPtXu4V8,4386
-cellfinder-1.3.0rc1.dist-info/LICENSE,sha256=Tw8iMytIDXLSmcIUsbQmRWojstl9yOWsPCx6ZT6dZLY,1564
-cellfinder-1.3.0rc1.dist-info/METADATA,sha256=GiwPyIxT0EFxoHCCwWWaZs8CUnrvUPGrFcD3DWWt9Vg,6531
-cellfinder-1.3.0rc1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-cellfinder-1.3.0rc1.dist-info/entry_points.txt,sha256=cKKjU8GPiN-TRelG2sT2JCKAcB9XDCjP6g9atE9pSoY,247
-cellfinder-1.3.0rc1.dist-info/top_level.txt,sha256=jyTQzX-tDjbsMr6s-E71Oy0IKQzmHTXSk4ZhpG5EDSE,11
-cellfinder-1.3.0rc1.dist-info/RECORD,,
+cellfinder-1.3.0rc2.dist-info/LICENSE,sha256=Tw8iMytIDXLSmcIUsbQmRWojstl9yOWsPCx6ZT6dZLY,1564
+cellfinder-1.3.0rc2.dist-info/METADATA,sha256=DlFtBgJoeh7SHPbvxuQ7hn-jyLLylKYjCy6rUHBMdLA,6531
+cellfinder-1.3.0rc2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+cellfinder-1.3.0rc2.dist-info/entry_points.txt,sha256=cKKjU8GPiN-TRelG2sT2JCKAcB9XDCjP6g9atE9pSoY,247
+cellfinder-1.3.0rc2.dist-info/top_level.txt,sha256=jyTQzX-tDjbsMr6s-E71Oy0IKQzmHTXSk4ZhpG5EDSE,11
+cellfinder-1.3.0rc2.dist-info/RECORD,,