cell-data-loader 0.0.2__tar.gz → 0.0.3__tar.gz

{cell_data_loader-0.0.2 → cell_data_loader-0.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cell_data_loader
-Version: 0.0.2
+Version: 0.0.3
 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>
@@ -10,6 +10,8 @@ Keywords: biomedical,cell,cell image,cellpose,csz,dataloader
 Requires-Python: >=3.8
 Requires-Dist: numpy
 Requires-Dist: opencv-python>=4.5.4
+Requires-Dist: pillow
+Requires-Dist: scikit-image
 Requires-Dist: scipy
 Requires-Dist: slideio==2.4.1
 Requires-Dist: torch
@@ -23,7 +25,7 @@ Cell Data Loader is a simple AI support tool in Python that can take in images o
 
 To install Cell Data Loader, simply type into a standard UNIX terminal
 
-    pip install cell-data-loader==0.0.1
+    pip install cell-data-loader
 
 The simplest way to use Cell Data Loader is to instantiate a dataloader as such:
 
@@ -90,8 +92,10 @@ imfolder = '/path/to/folder'
 dataloader = CellDataloader(imfolder,
 			dim = (64,64),
 			batch_size = 32,
-			dtype = "numpy",
-			n_channels = 3, #This is detected in the first read image by default, if not provided; it re-samples all images to force this number of channels
+			dtype = "numpy", # Can also be "torch"
+			label_regex = None,
+			n_channels = 3, # This is detected in the first read image by default, if not provided; it re-samples all images to force this number of channels
+			match_labels = False, # Outputs proportional amounts of each label in the dataset
 			)
 ~~~
 
@@ -101,15 +105,22 @@ Dependencies
 
 Strict dependencies:
 
-	scipy
 	numpy
-	pytorch
-	open-cv
+	torch
+	torchvision
+	opencv-python>=4.5.4
+	slideio==2.4.1
+	scipy
+	scikit-image
+	pillow
 
 Soft dependencies:
 
 	CellPose # For cell segmentation support
-	slideio # For reading .SVS and .CZI files
+	Tensorflow
+
+Note that some of the dependencies are not strict and vary depending on usage. Numpy is a hard requirement, but Tensorflow is not if the user only uses the Torch capabilities. If the user attempts to load cell images in "cell" mode without a working Cellpose installation, CellDataLoader will throw an error. Cellpose needs be be installed separately to use "cell" mode:
 
+	pip install cellpose
 
-Note that some of the dependencies are not strict and vary depending on usage. Numpy is a hard requirement, but Torch is not if the user only uses Tensorflow. If the user attempts to load cell images in "cell" mode without a working Cellpose installation, CellDataLoader will throw an error.
+And GPU integration is a separate matter.

{cell_data_loader-0.0.2 → cell_data_loader-0.0.3}/README.md

@@ -5,7 +5,7 @@ Cell Data Loader is a simple AI support tool in Python that can take in images o
 
 To install Cell Data Loader, simply type into a standard UNIX terminal
 
-    pip install cell-data-loader==0.0.1
+    pip install cell-data-loader
 
 The simplest way to use Cell Data Loader is to instantiate a dataloader as such:
 
@@ -72,8 +72,10 @@ imfolder = '/path/to/folder'
 dataloader = CellDataloader(imfolder,
 			dim = (64,64),
 			batch_size = 32,
-			dtype = "numpy",
-			n_channels = 3, #This is detected in the first read image by default, if not provided; it re-samples all images to force this number of channels
+			dtype = "numpy", # Can also be "torch"
+			label_regex = None,
+			n_channels = 3, # This is detected in the first read image by default, if not provided; it re-samples all images to force this number of channels
+			match_labels = False, # Outputs proportional amounts of each label in the dataset
 			)
 ~~~
 
@@ -83,15 +85,22 @@ Dependencies
 
 Strict dependencies:
 
-	scipy
 	numpy
-	pytorch
-	open-cv
+	torch
+	torchvision
+	opencv-python>=4.5.4
+	slideio==2.4.1
+	scipy
+	scikit-image
+	pillow
 
 Soft dependencies:
 
 	CellPose # For cell segmentation support
-	slideio # For reading .SVS and .CZI files
+	Tensorflow
+
+Note that some of the dependencies are not strict and vary depending on usage. Numpy is a hard requirement, but Tensorflow is not if the user only uses the Torch capabilities. If the user attempts to load cell images in "cell" mode without a working Cellpose installation, CellDataLoader will throw an error. Cellpose needs be be installed separately to use "cell" mode:
 
+	pip install cellpose
 
-Note that some of the dependencies are not strict and vary depending on usage. Numpy is a hard requirement, but Torch is not if the user only uses Tensorflow. If the user attempts to load cell images in "cell" mode without a working Cellpose installation, CellDataLoader will throw an error.
+And GPU integration is a separate matter.

{cell_data_loader-0.0.2 → cell_data_loader-0.0.3}/example_numpy.py

@@ -6,11 +6,18 @@ import numpy
 import os
 
 def example_numpy():
+
+	"""
+	Replace whese with folders locally on your computer -- script will not work
+	without new folders.
+	"""
 	wd = os.path.dirname(os.path.realpath(__file__))
-	imfolder_test = os.path.join(os.path.dirname(wd),'cell_data_loader_data','3368914_4_non_tumor')
-	imfolder_train = os.path.join(os.path.dirname(wd),'cell_data_loader_data','4173633_5')
-	model = resnet50()
+	imfolder_test = os.path.join(os.path.dirname(wd),'cell_data_loader_data',
+		'3368914_4_non_tumor')
+	imfolder_train = os.path.join(os.path.dirname(wd),'cell_data_loader_data',
+		'4173633_5')
 
+	model = resnet50()
 	model = tf.keras.applications.resnet50.ResNet50(
 		include_top=True,
 		weights='imagenet',
@@ -36,7 +43,6 @@ def example_numpy():
 	# Test
 
 	model.eval()
-
 	dataloader_test = CellDataloader(imfolder_test,imfolder_train,dtype="torch",
 		verbose=False)
 	total_images = 0

{cell_data_loader-0.0.2 → cell_data_loader-0.0.3}/example_torch.py

@@ -6,9 +6,16 @@ import torch
 import os
 
 def example_torch():
+
+	"""
+	Replace whese with folders locally on your computer -- script will not work
+	without new folders.
+	"""
 	wd = os.path.dirname(os.path.realpath(__file__))
-	imfolder_test = os.path.join(os.path.dirname(wd),'cell_data_loader_data','3368914_4_non_tumor')
-	imfolder_train = os.path.join(os.path.dirname(wd),'cell_data_loader_data','4173633_5')
+	imfolder_test = os.path.join(os.path.dirname(wd),'cell_data_loader_data',
+		'3368914_4_non_tumor')
+	imfolder_train = os.path.join(os.path.dirname(wd),'cell_data_loader_data',
+		'4173633_5')
 	model = resnet50()
 
 	# Train

cell_data_loader-0.0.3/pypi_push.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+rm -r dist
+python3 -m build --sdist
+twine upload dist/*

{cell_data_loader-0.0.2 → cell_data_loader-0.0.3}/pyproject.toml

@@ -2,7 +2,7 @@
 
 name = "cell_data_loader"
 
-version = "0.0.2"
+version = "0.0.3"
 
 dependencies = [
   "numpy",
@@ -10,7 +10,9 @@ dependencies = [
   "torch",
   "torchvision",
   "opencv-python>=4.5.4",
-  "slideio==2.4.1"
+  "slideio==2.4.1",
+  "scikit-image",
+  "pillow"
 ]
 requires-python = ">=3.8"
 

{cell_data_loader-0.0.2 → cell_data_loader-0.0.3}/src/cell_data_loader/cell_data_loader.py

@@ -174,9 +174,9 @@ class ImageLabelObject(BaseDataset):
 			return imslice
 		elif self.mode == "cell":
 			if len(self.get_cell_box_label()) == 0:
-				print("len self: %d" % len(self))
+				#print("len self: %d" % len(self))
 				return -1
-				raise Exception("No cells in this image — should not call")
+				#raise Exception("No cells in this image — should not call")
 				#warnings.warn("No cells found in %s" % self.filename)
 				#return -1
 			index = index % len(self.get_cell_box_label())
@@ -359,7 +359,8 @@ class CellDataloader():#BaseDataset):
 			if self.dtype == "numpy":
 				self.label_batch = np.zeros((self.batch_size,self.n_labels))
 			elif self.dtype == "torch":
-				self.label_batch = torch.zeros(self.batch_size,self.n_labels)
+				self.label_batch = torch.zeros(self.batch_size,self.n_labels,
+					device = self.gpu_ids)
 		sample = self.image_objects[0]
 		if n_channels is None:
 			self.n_channels = sample.get_n_channels()

{cell_data_loader-0.0.2 → cell_data_loader-0.0.3}/tests/unit_tests.py

@@ -151,6 +151,29 @@ class TestSimple(unittest.TestCase):
 			counts[int(np.argmax(y))] += 1
 		self.assertEqual(counts[0],counts[1])
 		self.assertEqual(counts[1],counts[2])
+	def test_gpu(self):
+		batch_size = 5
+		dim = (6,7)
+		for dtype in ["torch","numpy"]:
+			if dtype == "torch":
+				if not torch.cuda.is_available():
+					print("No available GPU for torch -- skipping")
+					continue
+				device = torch.cuda.current_device()
+			elif dtype == "numpy":
+				continue
+			dataset = CellDataloader(imfolder1,imfolder2,imfolder3,dim=dim,
+				batch_size=batch_size,dtype=dtype,match_labels=True,
+				gpu_ids = device)
+			for x,y in dataset:
+				if dtype == "torch":
+					self.assertEquals(device,x.device.index)
+					self.assertEquals(device,y.device.index)
+					break
+				elif dtype == "numpy":
+					break
+				else:
+					break
 
 if __name__ == "__main__":
 	unittest.main()