cell-data-loader 0.0.38__tar.gz → 0.0.41__tar.gz

{cell_data_loader-0.0.38 → cell_data_loader-0.0.41}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cell_data_loader
-Version: 0.0.38
+Version: 0.0.41
 Summary: Converts general images of cells into formats and labels for deep learning pipelines
 Project-URL: Homepage, https://github.com/mleming/CellDataLoader
 Author-email: Matt Leming <mleming@mgh.harvard.edu>
@@ -9,6 +9,7 @@ License: MIT License
 Keywords: biomedical,cell,cell image,cellpose,csz,dataloader
 Requires-Python: >=3.8
 Requires-Dist: cellpose==3.1.0
+Requires-Dist: hashlib
 Requires-Dist: numpy>=1.22.0
 Requires-Dist: opencv-python>=4.5.4
 Requires-Dist: pillow

{cell_data_loader-0.0.38 → cell_data_loader-0.0.41}/pyproject.toml

@@ -2,7 +2,7 @@
 
 name = "cell_data_loader"
 
-version = "0.0.38"
+version = "0.0.41"
 
 
 dependencies = [
@@ -14,7 +14,8 @@ dependencies = [
   "slideio==2.4.1",
   "scikit-image",
   "pillow",
-  "cellpose==3.1.0"
+  "cellpose==3.1.0",
+  "hashlib"
 ]
 requires-python = ">=3.8"
 

{cell_data_loader-0.0.38 → cell_data_loader-0.0.41}/src/cell_data_loader/__init__.py

@@ -1,3 +1,3 @@
-__version__ = "0.0.38"
+__version__ = "0.0.41"
 
 from .cell_data_loader import *

{cell_data_loader-0.0.38 → cell_data_loader-0.0.41}/src/cell_data_loader/cell_data_loader.py

@@ -15,7 +15,7 @@ import torch,torchvision
 #torchvision.disable_beta_transforms_warning()
 from .util import *
 import torchvision.transforms as transforms
-import gc
+import gc, hashlib
 #import openslide
 #import czifile
 try:
@@ -24,6 +24,16 @@ except:
 	warnings.warn("""No valid slideio installed, SVS and CZI files cannot 
 		be read in -- run `pip install slideio` for support""")
 
+def hash_det(input_string: str) -> int:
+    # 1. Encode string to bytes
+    byte_data = input_string.encode('utf-8')
+    
+    # 2. Generate SHA-256 hex string
+    hex_digest = hashlib.sha256(byte_data).hexdigest()
+    
+    # 3. Convert hex string to base-10 integer
+    return int(hex_digest, 16)
+
 class ImageLabelObject(BaseDataset):
 	def __init__(self,
 			filename,
@@ -930,7 +940,7 @@ class CellDataloader():#BaseDataset):
 							assert all([isinstance(_,int) for _ in s1])
 							assert all([ _ < s2 for _ in s1])
 							assert all([ _ >= 0 for _ in s1])
-							h = hash(filename)
+							h = hash_det(filename)
 							if h % s2 not in s1:
 								continue
 						skip = False