pyclesperanto

pyclesperanto is a prototype for clEsperanto - a multi-platform multi-language framework for GPU-accelerated image processing. It uses OpenCL kernels from CLIJ.

For users convenience, there are code generators available for napari and Fiji.

Reference

The full reference is available as part of the CLIJ2 documentation.

Installation

Get a python environment, e.g. via mini-conda. If you never used python/conda environments before, please follow the instructions here first.
Install pyopencl.

If installation of pyopencl for Windows fails, consider downloading a precompiled wheel (e.g. from here ) and installing it manually. Note that "cl12" and "cp38" in the filename matter: They allow you using OpenCL 1.2 compatible GPU devices from Python 3.8.

pip install pyopencl-2019.1.1+cl12-cp37-cp37m-win_amd64.whl

Alternatively, installing via conda also works:

conda install -c conda-forge pyopencl=2020.3.1

Afterwards, install pyclesperanto:

pip install pyclesperanto-prototype

Troubleshooting installation

If you receive an error like

DLL load failed: The specified procedure could not be found.

Try downloading and installing a pyopencl with a lower cl version, e.g. cl12 : pyopencl-2020.1+cl12-cp37-cp37m-win_amd64

Example code

A basic image procressing workflow loads blobs.gif and counts the number of gold particles:

import pyclesperanto_prototype as cle

from skimage.io import imread, imsave

# initialize GPU
cle.select_device("GTX")
print("Used GPU: " + cle.get_device().name)

# load data
image = imread('https://imagej.nih.gov/ij/images/blobs.gif')
print("Loaded image size: " + str(image.shape))

# push image to GPU memory
input = cle.push(image)
print("Image size in GPU: " + str(input.shape))

# process the image
inverted = cle.subtract_image_from_scalar(image, scalar=255)
blurred = cle.gaussian_blur(inverted, sigma_x=1, sigma_y=1)
binary = cle.threshold_otsu(blurred)
labeled = cle.connected_components_labeling_box(binary)

# The maxmium intensity in a label image corresponds to the number of objects
num_labels = cle.maximum_of_all_pixels(labeled)

# print out result
print("Num objects in the image: " + str(num_labels))

# for debugging: print out image
print(labeled)

# for debugging: save image to disc
imsave("result.tif", cle.pull(labeled))

Example gallery

	Select GPU
	Counting blobs
	Crop and paste images
	Inspecting 3D image data
	Rotation, scaling, translation, affine transforms
	Multiply vectors and matrices
	Matrix multiplication
	Working with spots, pointlist and matrices
	Mesh between centroids
	Mesh between touching neighbors
	Mesh with distances
	Mesh nearest_neighbors
	Neighborhood definitions
	Tissue neighborhood quantification
	Neighbors of neighbors
	Voronoi diagrams
	Shape descriptors based on neighborhood graphs
	Tribolium morphometry + Napari
	Tribolium morphometry
	napari+dask timelapse processing
	pyclesperanto assistant