Examples/segment blockwise script (#273)

.gitignore

@@ -29,4 +29,5 @@ tmp/
 # daisy logs
 daisy_logs/
 
-*.csv
+*.csv
+*.private

dacapo/blockwise/empanada_function.py

@@ -50,7 +50,7 @@ def segment_function(input_array, block, **parameters):
 
     Args:
         input_array (np.ndarray): The 3D array to segment.
-        block (dask.array.core.Block): The block object.
+        block (daisy.Block): The block object.
         **parameters: Parameters for the empanada-napari segmenter.
     Returns:
         np.ndarray: The segmented 3D array.

examples/blockwise/segment_config.yaml

@@ -0,0 +1,7 @@
+
+steps:
+  gaussian_smooth:
+    sigma: 2.0
+  threshold:
+    threshold: 200
+  label: {}

examples/blockwise/segment_function.py

@@ -0,0 +1,38 @@
+import logging
+
+import scipy.ndimage
+import yaml
+
+logger = logging.getLogger(__file__)
+
+
+def segment_function(input_array, block, config_path):
+    """
+    Segment a 3D block using a small numpy-based post-processing script.
+
+    Args:
+        input_array (np.ndarray): The 3D array to segment.
+        block (daisy.Block): The block object.
+        config_path (str): The path to the configuration yaml file.
+    Returns:
+        np.ndarray: The segmented 3D array.
+    """
+    data = input_array.to_ndarray(block.read_roi)
+    steps = yaml.load(config_path, Loader=yaml.FullLoader)
+
+    # Apply the segmentation function here
+    for step, params in steps.items():
+        if step == "gaussian_smooth":
+            sigma = params.get("sigma", 1.0)
+            logger.info(f"Applying Gaussian smoothing with sigma={sigma}")
+            data = scipy.ndimage.gaussian_filter(data, sigma=sigma)
+        elif step == "threshold":
+            threshold = params.get("threshold", 0.5)
+            logger.info(f"Applying thresholding with threshold={threshold}")
+            data = data > threshold
+        elif step == "label":
+            structuring_element = params.get("structuring_element", None)
+            logger.info("Applying labeling")
+            data, _ = scipy.ndimage.label(data, structuring_element)  # type: ignore
+
+    return data

examples/blockwise/segment_script.sh

@@ -0,0 +1,25 @@
+# This file contains the commands used to run an example of the segment-blockwise command.
+# The arguments to the segment-blockwise command are:
+# -sf: path to the python file with the segmentation_function (in this case the empanada_function.py file)
+# -tr: Total ROI to process. It is a list of 3 elements, each one is a list with the start and end of the ROI in the x, y and z axis respectively.
+# e.g. -tr "[320000:330000, 100000:110000, 10000:20000]" \
+# -rr: ROI to read. It is a list of 3 elements, each one is a list with the start and end of the ROI in the x, y and z axis respectively.
+# -wr: ROI to write. It is a list of 3 elements, each one is a list with the start and end of the ROI in the x, y and z axis respectively.
+# -nw: Number of workers to use.
+# -ic: Input container. It is the path to the input zarr file.
+# -id: Input dataset. It is the path to the input dataset inside the input zarr file.
+# -oc: Output container. It is the path to the output zarr file.
+# -od: Output dataset. It is the path to the output dataset inside the output zarr file.
+# --config_path: Path to the config yaml file.
+
+
+dacapo segment-blockwise \
+-sf segment_function.py \
+-rr "[256,256,256]" \
+-wr "[256,256,256]" \
+-nw 32 \
+-ic predictions/c-elegen/bw/c_elegen_bw_op50_ld_scratch_0_300000.zarr \
+-id ld/ld \
+-oc predictions/c-elegen/bw/jrc_c-elegans-bw-1_postprocessed.zarr \
+-od ld \
+--config_path segment_config.yaml