Layout and minimal changes (#23)

* don't move to gpu inside prepare_data

* switch to src layout

* run black

* change python -m pytest to pytest in README

---------

Co-authored-by: marshrossney <[email protected]>

.gitignore

@@ -3,3 +3,4 @@
 **/__pycache__/
 vectors/
 *.ipynb
+*.egg-info/

README.md

@@ -25,11 +25,11 @@ Please note that this is specifically pinned to python 3.9 due to dependency ver
 
 Get started by cloning this repository and running
 
-`pip install -e .`
+`python -m pip install -e .`
 
 ### Running tests
 
-`python -m pytest` or `py.test`
+`pytest` or `py.test`
 
 ## Contents
 

pyproject.toml

@@ -1,12 +1,22 @@
+[build-system]
+requires = ["setuptools >= 61.0"]
+build-backend = "setuptools.build_meta"
+
 [project]
 name = "cyto_ml"
-version = "0.1"
+version = "0.1.0"
+requires-python = "==3.9.*"
 description = "This package supports the processing and analysis of plankton sample data"
 readme = "README.md"
-requires-python = "==3.9.*"
-
-[tool.setuptools]
-py-modules = []
 
 [tool.jupytext]
 formats = "ipynb,md"
+
+[tool.pytest.ini_options]
+filterwarnings = [
+    "ignore::DeprecationWarning",
+]
+
+[tool.black]
+target-version = ["py39"]
+line-length = 88

scripts/intake_metadata.py

@@ -7,6 +7,7 @@
 Via https://gallery.pangeo.io/repos/pangeo-data/pangeo-tutorial-gallery/intake.html#Build-an-intake-catalog
 
 """
+
 import os
 from cyto_ml.data.intake import intake_yaml
 from cyto_ml.data.s3 import s3_endpoint, image_index

cyto_ml/models/scivision.py → src/cyto_ml/models/scivision.py

@@ -34,20 +34,18 @@ def prepare_image(image: DataArray):
     Take an xarray of image data and prepare it to pass through the model
     a) Converts the image data to a PyTorch tensor
     b) Accepts a single image or batch (no need for torch.stack)
-    c) Uses a CUDA device if available
     """
+    # Computes the DataArray and returns a numpy array
+    image_numpy = image.to_numpy()
+
     # Convert the image data to a PyTorch tensor
-    tensor_image = torchvision.transforms.ToTensor()(image.to_numpy())
+    tensor_image = torchvision.transforms.ToTensor()(image_numpy)
 
     # Check if the input is a single image or a batch
     if len(tensor_image.shape) == 3:
         # Single image, add a batch dimension
         tensor_image = tensor_image.unsqueeze(0)
 
-    # Check if CUDA is available and move the tensor to the CUDA device
-    if torch.cuda.is_available():
-        tensor_image = tensor_image.cuda()
-
     return tensor_image