# py-clesperanto
[](https://forum.image.sc/tag/clesperanto)
[](http://clesperanto.net)
[](https://pypi.org/project/pyclesperanto-prototype)
[](https://anaconda.org/conda-forge/pyclesperanto-prototype)
[](https://github.com/clEsperanto/pyclesperanto_prototype/graphs/contributors)
[](https://pypistats.org/packages/pyclesperanto_prototype)
[](https://github.com/clEsperanto/pyclesperanto_prototype/)
[](https://github.com/clEsperanto/pyclesperanto_prototype/)
[](https://github.com/haesleinhuepf/pyclesperanto_prototype/raw/master/LICENSE)
[](https://python.org)
[](https://github.com/clesperanto/pyclesperanto_prototype/actions)
[](https://codecov.io/gh/clesperanto/pyclesperanto_prototype)
[](https://en.wikipedia.org/wiki/Software_release_life_cycle#Alpha)
[](https://zenodo.org/badge/latestdoi/248206619)
py-clesperanto is a prototype for [clesperanto](http://clesperanto.net) - a multi-platform multi-language framework for GPU-accelerated image processing.
We mostly use it in the life sciences for analysing 3- and 4-dimensional microsopy data, e.g. as we face it developmental biology when segmenting cells and studying
their individual properties as well as properties of compounds of cells forming tissues.
Image data source: Daniela Vorkel, Myers lab, MPI-CBG, rendered using [napari](https://github.com/napari/napari)
clesperanto uses [OpenCL kernels](https://github.com/clEsperanto/clij-opencl-kernels/tree/development/src/main/java/net/haesleinhuepf/clij/kernels) from [CLIJ](http://clij.github.io/).
For users convenience, there are code generators available for [napari](https://clesperanto.github.io/napari_pyclesperanto_assistant/) and [Fiji](https://clij.github.io/assistant/).
Also check out the [napari workflow optimizer](https://github.com/haesleinhuepf/napari-workflow-optimizer) for semi-automatic parameter tuning of clesperanto-functions.
## Reference
The preliminary API reference is available [here](https://clesperanto.github.io/pyclesperanto_prototype/docs/_build/html/).
Furthermore, parts of the [reference](https://clij.github.io/clij2-docs/reference__pyclesperanto) are also available within the CLIJ2 documentation.
## Installation
* Get a conda/python environment, e.g. via [mamba-forge](https://github.com/conda-forge/miniforge#mambaforge).
* If you never used python/conda environments before, please follow [these instructions](https://biapol.github.io/blog/mara_lampert/getting_started_with_mambaforge_and_python/readme.html) first.
```
conda create --name cle_39 python=3.9
conda activate cle_39
```
* Install pyclesperanto-prototype using [mamba / conda](https://focalplane.biologists.com/2022/12/08/managing-scientific-python-environments-using-conda-mamba-and-friends/):
```
mamba install -c conda-forge pyclesperanto-prototype
```
OR using pip:
```
pip install pyclesperanto-prototype
```
## Troubleshooting: Graphics cards drivers
In case error messages contain "ImportError: DLL load failed while importing cl: The specified procedure could not be found" [see also](https://github.com/clEsperanto/pyclesperanto_prototype/issues/55) or "clGetPlatformIDs failed: PLATFORM_NOT_FOUND_KHR", please install recent drivers for your graphics card and/or OpenCL device. Select the right driver source depending on your hardware from this list:
* [AMD drivers](https://www.amd.com/en/support)
* [NVidia drivers](https://www.nvidia.com/download/index.aspx)
* [Intel GPU drivers](https://www.intel.com/content/www/us/en/download/726609/intel-arc-graphics-windows-dch-driver.html)
* [Microsoft Windows OpenCL support](https://www.microsoft.com/en-us/p/opencl-and-opengl-compatibility-pack/9nqpsl29bfff)
Sometimes, mac-users need to install this:
mamba install -c conda-forge ocl_icd_wrapper_apple
Sometimes, linux users need to install this:
mamba install -c conda-forge ocl-icd-system
Linux user may have to install packages such as `intel-opencl-icd` or `rocm-opencl-runtime` depending on their GPU.
## Computing on Central Processing units (CPUs)
If no OpenCL-compatible GPU is available, pyclesperanto-prototype can make use of CPUs instead.
Just install [oclgrind](https://github.com/jrprice/Oclgrind)
or [pocl](http://portablecl.org/), e.g. using mamba / conda. Oclgrind is recommended for Windows systems, PoCL for Linux. MacOS typically comes with OpenCL support for CPUs.
```
mamba install oclgrind -c conda-forge
```
OR
```
mamba install pocl -c conda-forge
```
Owners of compatible Intel Xeon CPUs can also install a driver to use them for computing:
* [Intel CPU OpenCL drivers](https://www.intel.com/content/www/us/en/developer/articles/tool/opencl-drivers.html#latest_CPU_runtime)
## Example code
A basic image processing workflow loads blobs.gif and counts the number of objects:
```python
import pyclesperanto_prototype as cle
from skimage.io import imread, imsave
# initialize / select GPU with "TX" in their name
device = cle.select_device("TX")
print("Used GPU: ", device)
# load data
image = imread('https://imagej.nih.gov/ij/images/blobs.gif')
# 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 maximium intensity in a label image corresponds to the number of objects
num_labels = labeled.max()
print(f"Number of objects in the image: {num_labels}")
# save image to disc
imsave("result.tif", labeled)
```
## Example gallery
<table border="0">
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_select_GPU.png" width="300"/>
</td><td>
[Select GPU](https://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/select_GPU.py)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/jupyter.png" width="300"/>
</td><td>
[Image processing in Jupyter Notebooks](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/interoperability/jupyter.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_count_blobs.png" width="300"/>
</td><td>
[Counting blobs](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/count_blobs.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/voronoi_otsu_labeling.png" width="300"/>
</td><td>
[Voronoi-Otsu labeling](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/segmentation/voronoi_otsu_labeling.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/segmentation_3d.png" width="300"/>
</td><td>
[3D Image segmentation ](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/segmentation/Segmentation_3D.ipynb)
</td></tr>
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/segmentation_2d_membranes.png" width="300"/>
</td><td>
[Cell segmentation based on membranes](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/segmentation/segmentation_2d_membranes.ipynb)
</td></tr>
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/counting_nuclei_multichannel.png" width="300"/>
</td><td>
[Counting nuclei according to expression in multiple channels](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/measurement/counting_nuclei_multichannel.ipynb)
</td></tr>
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/differentiate_nuclei_intensity.png" width="300"/>
</td><td>
[Differentiating nuclei according to signal intensity](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/measurement/differentiate_nuclei_intensity.ipynb)
</td></tr>
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/bead_segmentation.png" width="300"/>
</td><td>
[Detecting beads and measuring their size](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/segmentation/bead_segmentation.ipynb)
</td></tr>
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/label_statistics.png" width="300"/>
</td><td>
[Label statistics](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/label_statistics.ipynb)
</td></tr>
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/parametric_maps.png" width="300"/>
</td><td>
[Parametric maps](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/tissues/parametric_maps.ipynb)
</td></tr>
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/intensities_along_lines.png" width="300"/>
</td><td>
[Measure intensity along lines](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/measurement/intensities_along_lines.ipynb)
</td></tr>
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_crop_and_paste_images.png" width="300"/>
</td><td>
[Crop and paste images](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/crop_and_paste_images.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_inspecting_3d_images.png" width="300"/>
</td><td>
[Inspecting 3D image data](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/inspecting_3d_images.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_affine_transforms.png" width="300"/>
</td><td>
[Rotation, scaling, translation, affine transforms](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/transforms/affine_transforms.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_deskew.png" width="300"/>
</td><td>
[Deskewing](https://github.com/clEsperanto/pyclesperanto_prototype/blob/master/demo/transforms/deskew.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_multiply_vectors_and_matrices.png" width="300"/>
</td><td>
[Multiply vectors and matrices](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/multiply_vectors_and_matrices.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_multiply_matrices.png" width="300"/>
</td><td>
[Matrix multiplication](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/multiply_matrices.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_spots_pointlists_matrices_tables.png" width="300"/>
</td><td>
* [Working with spots, pointlist and matrices](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/spots_pointlists_matrices_tables.ipynb)
* [Lists of nonzero pixel coordinates](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/nonzero.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/mesh_between_centroids.png" width="300"/>
</td><td>
[Mesh between centroids](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/mesh_between_centroids.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/mesh_between_touching_neighbors.png" width="300"/>
</td><td>
[Mesh between touching neighbors](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/mesh_between_touching_neighbors.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/mesh_with_distances.png" width="300"/>
</td><td>
[Mesh with distances](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/mesh_with_distances.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/mesh_nearest_neighbors.png" width="300"/>
</td><td>
[Mesh nearest_neighbors](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/mesh_nearest_neighbors.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/ipgraph_networkx.png" width="300"/>
</td><td>
[Export to igraph and networkx](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/ipgraph_networkx.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/neighborhood_definitions.png" width="300"/>
</td><td>
[Neighborhood definitions](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/neighborhood_definitions.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/tissue_neighborhood_quantification.png" width="300"/>
</td><td>
[Tissue neighborhood quantification](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/tissues/tissue_neighborhood_quantification.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/neighbors_of_neighbors.png" width="300"/>
</td><td>
[Neighbors of neighbors](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/neighbors_of_neighbors.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_voronoi_diagrams.png" width="300"/>
</td><td>
[Voronoi diagrams](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/voronoi_diagrams.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/shape_descriptors_based_on_neighborhood_graphs.png" width="300"/>
</td><td>
[Shape descriptors based on neighborhood graphs](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/shape_descriptors_based_on_neighborhood_graphs.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/distance_to_other_labels.png" width="300"/>
</td><td>
[Measuring distances between labels in two label images](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/distance_to_other_labels.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_tribolium_napari.png" width="300"/>
</td><td>
[Tribolium morphometry + Napari](https://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/tribolium_morphometry/tribolium.py)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_tribolium_morphometry.png" width="300"/>
</td><td>
[Tribolium morphometry](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/tribolium_morphometry/tribolium_morphometry2.ipynb)
[(archived version)](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/tribolium_morphometry/tribolium_morphometry.ipynb)
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_napari_dask.png" width="300"/>
</td><td>
[napari+dask timelapse processing](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/napari_gui/napari_dask.ipynb)
</td></tr>
</table>
## Technical insights
<table border="0"><tr><td>
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/browse_operations.png" width="300"/>
</td><td>
[Browsing operations](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/browse_operations.ipynb)
</td></tr>
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/interactive_widgets.gif" width="300"/>
</td><td>
[Interactive widgets](https://colab.research.google.com/github/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/browse_operations.ipynb)
</td></tr>
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/optimize_blobs_segmentation.png" width="300"/>
</td><td>
[Automatic workflow optimization](https://colab.research.google.com/github/clEsperanto/pyclesperanto_prototype/tree/master/demo/optimization/optimize_blobs_segmentation.ipynb)
</td></tr>
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/memory_management.png" width="300"/>
</td><td>
[Tracing memory consumtion on NVidia GPUs](https://github.com/clEsperanto/pyclesperanto_prototype/blob/master/demo/optimization/memory_management.ipynb)
</td></tr>
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/switching_gpus.png" width="300"/>
</td><td>
[Exploring and switching between GPUs](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/switching_gpus.ipynb)
</td></tr>
<tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/cupy_compatibility.png" width="300"/>
</td><td>
[Interoperability with cupy](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/interoperability_cupy.ipynb)
[Using the cupy backend](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/select_backend.ipynb)
</td></tr>
<tr><td>
<img src="./docs/images/dask.jpg" width="300"/>
</td><td>
[Big data handling with Dask GPU clusters](./demo/interoperability/dask.ipynb)
</td></tr>
</table>
## Related projects
<table border="0"><tr><td>
<img src="https://github.com/clesperanto/napari_pyclesperanto_assistant/raw/master/docs/images/screenshot.png" width="300"/>
</td><td>
[napari-pyclesperanto-assistant](https://github.com/clesperanto/napari_pyclesperanto_assistant):
A graphical user interface for general purpose GPU-accelerated image processing and analysis in napari.
</td></tr><tr><td>
<img src="https://github.com/haesleinhuepf/napari-accelerated-pixel-and-object-classification/raw/main/images/screenshot.png" width="300"/>
</td><td>
[napari-accelerated-pixel-and-object-classification](https://github.com/haesleinhuepf/napari-accelerated-pixel-and-object-classification):
GPU-accelerated Random Forest Classifiers for pixel and labeled object classification
</td></tr><tr><td>
<img src="https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/napari-clusters-plotter.png" width="300"/>
</td><td>
[napari-clusters-plotter](https://github.com/BiAPoL/napari-clusters-plotter):
Clustering of objects according to their quantitative properties
</td></tr></table>
## Benchmarking
We implemented some basic benchmarking notebooks allowing to see performance differences between pyclesperanto and
some other image processing libraries, typically using the CPU. Such benchmarking results vary heavily depending on
image size, kernel size, used operations, parameters and used hardware. Feel free to use those notebooks, adapt them to
your use-case scenario and benchmark on your target hardware. If you have different scenarios or use-cases, you are very
welcome to submit your notebook as pull-request!
* [Affine transforms](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/affine_transforms.ipynb)
* [Background subtraction](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/top_hat.ipynb)
* [Gaussian blur](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/gaussian_blur.ipynb)
* [Convolution](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/convolution.ipynb)
* [Otsu's thresholding](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/threshold_otsu.ipynb)
* [Connected component labeling](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/connected_component_labeling.ipynb)
* [Extend labels](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/extend_labels.ipynb)
* [Statistics of labeled pixels / regionprops](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/statistics_of_labeled_pixels.ipynb)
* [Histograms](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/histograms.ipynb)
* [Matrix multiplication](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/matrix_multiplication.ipynb)
* [Pixel-wise comparison](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/pixelwise_comparison.ipynb)
* [Intensity projections](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/intensity_projections.ipynb)
* [Axis transposition](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/transpose.ipynb)
* [Nonzero](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/nonzero.ipynb)
## See also
There are other libraries for code acceleration and GPU-acceleration for image processing.
* [numba](https://numba.pydata.org/)
* [cupy](https://cupy.dev)
* [cucim](https://github.com/rapidsai/cucim)
* [clij](https://clij.github.io)
## Feedback welcome!
clesperanto is developed in the open because we believe in the open source community. See our [community guidelines](https://clij.github.io/clij2-docs/community_guidelines). Feel free to drop feedback as [github issue](https://github.com/clEsperanto/pyclesperanto_prototype/issues) or via [image.sc](https://image.sc)
Raw data
{
"_id": null,
"home_page": "https://github.com/clEsperanto/pyclesperanto_prototype",
"name": "pyclesperanto-prototype",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": null,
"keywords": null,
"author": "Robert Haase",
"author_email": "robert.haase@uni-leipzig.de",
"download_url": "https://files.pythonhosted.org/packages/59/ae/fa33875c73625e24d4a1eaada7287269a39c9e68496e18e4dc288ed43a80/pyclesperanto_prototype-0.24.5.tar.gz",
"platform": null,
"description": "# py-clesperanto\r\n[](https://forum.image.sc/tag/clesperanto)\r\n[](http://clesperanto.net)\r\n[](https://pypi.org/project/pyclesperanto-prototype)\r\n[](https://anaconda.org/conda-forge/pyclesperanto-prototype)\r\n[](https://github.com/clEsperanto/pyclesperanto_prototype/graphs/contributors)\r\n[](https://pypistats.org/packages/pyclesperanto_prototype)\r\n[](https://github.com/clEsperanto/pyclesperanto_prototype/)\r\n[](https://github.com/clEsperanto/pyclesperanto_prototype/)\r\n[](https://github.com/haesleinhuepf/pyclesperanto_prototype/raw/master/LICENSE)\r\n[](https://python.org)\r\n[](https://github.com/clesperanto/pyclesperanto_prototype/actions)\r\n[](https://codecov.io/gh/clesperanto/pyclesperanto_prototype)\r\n[](https://en.wikipedia.org/wiki/Software_release_life_cycle#Alpha)\r\n[](https://zenodo.org/badge/latestdoi/248206619)\r\n\r\npy-clesperanto is a prototype for [clesperanto](http://clesperanto.net) - a multi-platform multi-language framework for GPU-accelerated image processing. \r\nWe mostly use it in the life sciences for analysing 3- and 4-dimensional microsopy data, e.g. as we face it developmental biology when segmenting cells and studying\r\ntheir individual properties as well as properties of compounds of cells forming tissues.\r\n\r\n\r\nImage data source: Daniela Vorkel, Myers lab, MPI-CBG, rendered using [napari](https://github.com/napari/napari)\r\n\r\nclesperanto uses [OpenCL kernels](https://github.com/clEsperanto/clij-opencl-kernels/tree/development/src/main/java/net/haesleinhuepf/clij/kernels) from [CLIJ](http://clij.github.io/).\r\n\r\nFor users convenience, there are code generators available for [napari](https://clesperanto.github.io/napari_pyclesperanto_assistant/) and [Fiji](https://clij.github.io/assistant/).\r\nAlso check out the [napari workflow optimizer](https://github.com/haesleinhuepf/napari-workflow-optimizer) for semi-automatic parameter tuning of clesperanto-functions.\r\n\r\n## Reference\r\nThe preliminary API reference is available [here](https://clesperanto.github.io/pyclesperanto_prototype/docs/_build/html/).\r\nFurthermore, parts of the [reference](https://clij.github.io/clij2-docs/reference__pyclesperanto) are also available within the CLIJ2 documentation.\r\n\r\n## Installation\r\n* Get a conda/python environment, e.g. via [mamba-forge](https://github.com/conda-forge/miniforge#mambaforge). \r\n* If you never used python/conda environments before, please follow [these instructions](https://biapol.github.io/blog/mara_lampert/getting_started_with_mambaforge_and_python/readme.html) first.\r\n\r\n```\r\nconda create --name cle_39 python=3.9\r\nconda activate cle_39\r\n```\r\n\r\n* Install pyclesperanto-prototype using [mamba / conda](https://focalplane.biologists.com/2022/12/08/managing-scientific-python-environments-using-conda-mamba-and-friends/):\r\n\r\n```\r\nmamba install -c conda-forge pyclesperanto-prototype\r\n```\r\n\r\nOR using pip:\r\n\r\n```\r\npip install pyclesperanto-prototype\r\n```\r\n\r\n## Troubleshooting: Graphics cards drivers\r\n\r\nIn case error messages contain \"ImportError: DLL load failed while importing cl: The specified procedure could not be found\" [see also](https://github.com/clEsperanto/pyclesperanto_prototype/issues/55) or \"clGetPlatformIDs failed: PLATFORM_NOT_FOUND_KHR\", please install recent drivers for your graphics card and/or OpenCL device. Select the right driver source depending on your hardware from this list:\r\n\r\n* [AMD drivers](https://www.amd.com/en/support)\r\n* [NVidia drivers](https://www.nvidia.com/download/index.aspx)\r\n* [Intel GPU drivers](https://www.intel.com/content/www/us/en/download/726609/intel-arc-graphics-windows-dch-driver.html)\r\n* [Microsoft Windows OpenCL support](https://www.microsoft.com/en-us/p/opencl-and-opengl-compatibility-pack/9nqpsl29bfff)\r\n\r\nSometimes, mac-users need to install this:\r\n\r\n mamba install -c conda-forge ocl_icd_wrapper_apple\r\n\r\nSometimes, linux users need to install this:\r\n\r\n mamba install -c conda-forge ocl-icd-system\r\n\r\nLinux user may have to install packages such as `intel-opencl-icd` or `rocm-opencl-runtime` depending on their GPU.\r\n\r\n## Computing on Central Processing units (CPUs)\r\n\r\nIf no OpenCL-compatible GPU is available, pyclesperanto-prototype can make use of CPUs instead. \r\nJust install [oclgrind](https://github.com/jrprice/Oclgrind)\r\nor [pocl](http://portablecl.org/), e.g. using mamba / conda. Oclgrind is recommended for Windows systems, PoCL for Linux. MacOS typically comes with OpenCL support for CPUs.\r\n\r\n```\r\nmamba install oclgrind -c conda-forge\r\n```\r\n\r\nOR \r\n\r\n```\r\nmamba install pocl -c conda-forge\r\n```\r\n\r\nOwners of compatible Intel Xeon CPUs can also install a driver to use them for computing:\r\n* [Intel CPU OpenCL drivers](https://www.intel.com/content/www/us/en/developer/articles/tool/opencl-drivers.html#latest_CPU_runtime)\r\n\r\n## Example code\r\nA basic image processing workflow loads blobs.gif and counts the number of objects:\r\n\r\n```python\r\nimport pyclesperanto_prototype as cle\r\n\r\nfrom skimage.io import imread, imsave\r\n\r\n# initialize / select GPU with \"TX\" in their name\r\ndevice = cle.select_device(\"TX\")\r\nprint(\"Used GPU: \", device)\r\n\r\n# load data\r\nimage = imread('https://imagej.nih.gov/ij/images/blobs.gif')\r\n\r\n# process the image\r\ninverted = cle.subtract_image_from_scalar(image, scalar=255)\r\nblurred = cle.gaussian_blur(inverted, sigma_x=1, sigma_y=1)\r\nbinary = cle.threshold_otsu(blurred)\r\nlabeled = cle.connected_components_labeling_box(binary)\r\n\r\n# The maximium intensity in a label image corresponds to the number of objects\r\nnum_labels = labeled.max()\r\nprint(f\"Number of objects in the image: {num_labels}\")\r\n\r\n# save image to disc\r\nimsave(\"result.tif\", labeled)\r\n```\r\n\r\n## Example gallery \r\n\r\n<table border=\"0\">\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_select_GPU.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Select GPU](https://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/select_GPU.py)\r\n\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/jupyter.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Image processing in Jupyter Notebooks](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/interoperability/jupyter.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_count_blobs.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Counting blobs](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/count_blobs.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/voronoi_otsu_labeling.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Voronoi-Otsu labeling](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/segmentation/voronoi_otsu_labeling.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/segmentation_3d.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[3D Image segmentation ](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/segmentation/Segmentation_3D.ipynb)\r\n\r\n</td></tr>\r\n\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/segmentation_2d_membranes.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Cell segmentation based on membranes](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/segmentation/segmentation_2d_membranes.ipynb)\r\n\r\n</td></tr>\r\n\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/counting_nuclei_multichannel.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Counting nuclei according to expression in multiple channels](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/measurement/counting_nuclei_multichannel.ipynb)\r\n\r\n</td></tr>\r\n\r\n\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/differentiate_nuclei_intensity.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Differentiating nuclei according to signal intensity](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/measurement/differentiate_nuclei_intensity.ipynb)\r\n\r\n</td></tr>\r\n\r\n\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/bead_segmentation.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Detecting beads and measuring their size](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/segmentation/bead_segmentation.ipynb)\r\n\r\n</td></tr>\r\n\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/label_statistics.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Label statistics](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/label_statistics.ipynb)\r\n\r\n</td></tr>\r\n\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/parametric_maps.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Parametric maps](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/tissues/parametric_maps.ipynb)\r\n\r\n</td></tr>\r\n\r\n\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/intensities_along_lines.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Measure intensity along lines](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/measurement/intensities_along_lines.ipynb)\r\n\r\n</td></tr>\r\n\r\n\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_crop_and_paste_images.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Crop and paste images](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/crop_and_paste_images.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_inspecting_3d_images.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Inspecting 3D image data](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/inspecting_3d_images.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_affine_transforms.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Rotation, scaling, translation, affine transforms](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/transforms/affine_transforms.ipynb)\r\n\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_deskew.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Deskewing](https://github.com/clEsperanto/pyclesperanto_prototype/blob/master/demo/transforms/deskew.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_multiply_vectors_and_matrices.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Multiply vectors and matrices](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/multiply_vectors_and_matrices.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_multiply_matrices.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Matrix multiplication](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/multiply_matrices.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_spots_pointlists_matrices_tables.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n* [Working with spots, pointlist and matrices](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/spots_pointlists_matrices_tables.ipynb)\r\n* [Lists of nonzero pixel coordinates](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/nonzero.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/mesh_between_centroids.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Mesh between centroids](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/mesh_between_centroids.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/mesh_between_touching_neighbors.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Mesh between touching neighbors](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/mesh_between_touching_neighbors.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/mesh_with_distances.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Mesh with distances](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/mesh_with_distances.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/mesh_nearest_neighbors.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Mesh nearest_neighbors](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/mesh_nearest_neighbors.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/ipgraph_networkx.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Export to igraph and networkx](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/ipgraph_networkx.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/neighborhood_definitions.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Neighborhood definitions](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/neighborhood_definitions.ipynb)\r\n\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/tissue_neighborhood_quantification.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Tissue neighborhood quantification](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/tissues/tissue_neighborhood_quantification.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/neighbors_of_neighbors.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Neighbors of neighbors](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/neighbors_of_neighbors.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_voronoi_diagrams.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Voronoi diagrams](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/voronoi_diagrams.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/shape_descriptors_based_on_neighborhood_graphs.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Shape descriptors based on neighborhood graphs](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/shape_descriptors_based_on_neighborhood_graphs.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/distance_to_other_labels.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Measuring distances between labels in two label images](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/neighbors/distance_to_other_labels.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_tribolium_napari.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Tribolium morphometry + Napari](https://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/tribolium_morphometry/tribolium.py)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_tribolium_morphometry.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Tribolium morphometry](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/tribolium_morphometry/tribolium_morphometry2.ipynb)\r\n[(archived version)](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/tribolium_morphometry/tribolium_morphometry.ipynb)\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/screenshot_napari_dask.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[napari+dask timelapse processing](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/napari_gui/napari_dask.ipynb)\r\n\r\n</td></tr>\r\n</table>\r\n\r\n## Technical insights\r\n\r\n<table border=\"0\"><tr><td>\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/browse_operations.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Browsing operations](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/browse_operations.ipynb)\r\n\r\n</td></tr>\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/interactive_widgets.gif\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Interactive widgets](https://colab.research.google.com/github/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/browse_operations.ipynb)\r\n\r\n</td></tr>\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/optimize_blobs_segmentation.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Automatic workflow optimization](https://colab.research.google.com/github/clEsperanto/pyclesperanto_prototype/tree/master/demo/optimization/optimize_blobs_segmentation.ipynb)\r\n\r\n</td></tr>\r\n\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/memory_management.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Tracing memory consumtion on NVidia GPUs](https://github.com/clEsperanto/pyclesperanto_prototype/blob/master/demo/optimization/memory_management.ipynb)\r\n\r\n</td></tr>\r\n\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/switching_gpus.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Exploring and switching between GPUs](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/switching_gpus.ipynb)\r\n\r\n</td></tr>\r\n<tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/cupy_compatibility.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Interoperability with cupy](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/interoperability_cupy.ipynb)\r\n\r\n[Using the cupy backend](http://github.com/clEsperanto/pyclesperanto_prototype/tree/master/demo/basics/select_backend.ipynb)\r\n\r\n</td></tr>\r\n<tr><td>\r\n\r\n<img src=\"./docs/images/dask.jpg\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[Big data handling with Dask GPU clusters](./demo/interoperability/dask.ipynb)\r\n\r\n\r\n</td></tr>\r\n</table>\r\n\r\n## Related projects\r\n\r\n<table border=\"0\"><tr><td>\r\n\r\n<img src=\"https://github.com/clesperanto/napari_pyclesperanto_assistant/raw/master/docs/images/screenshot.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[napari-pyclesperanto-assistant](https://github.com/clesperanto/napari_pyclesperanto_assistant):\r\nA graphical user interface for general purpose GPU-accelerated image processing and analysis in napari.\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/haesleinhuepf/napari-accelerated-pixel-and-object-classification/raw/main/images/screenshot.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[napari-accelerated-pixel-and-object-classification](https://github.com/haesleinhuepf/napari-accelerated-pixel-and-object-classification):\r\nGPU-accelerated Random Forest Classifiers for pixel and labeled object classification\r\n\r\n</td></tr><tr><td>\r\n\r\n<img src=\"https://github.com/clEsperanto/pyclesperanto_prototype/raw/master/docs/images/napari-clusters-plotter.png\" width=\"300\"/>\r\n\r\n</td><td>\r\n\r\n[napari-clusters-plotter](https://github.com/BiAPoL/napari-clusters-plotter):\r\nClustering of objects according to their quantitative properties\r\n\r\n</td></tr></table>\r\n\r\n## Benchmarking\r\nWe implemented some basic benchmarking notebooks allowing to see performance differences between pyclesperanto and \r\nsome other image processing libraries, typically using the CPU. Such benchmarking results vary heavily depending on \r\nimage size, kernel size, used operations, parameters and used hardware. Feel free to use those notebooks, adapt them to \r\nyour use-case scenario and benchmark on your target hardware. If you have different scenarios or use-cases, you are very \r\nwelcome to submit your notebook as pull-request!\r\n\r\n* [Affine transforms](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/affine_transforms.ipynb)\r\n* [Background subtraction](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/top_hat.ipynb)\r\n* [Gaussian blur](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/gaussian_blur.ipynb)\r\n* [Convolution](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/convolution.ipynb)\r\n* [Otsu's thresholding](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/threshold_otsu.ipynb)\r\n* [Connected component labeling](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/connected_component_labeling.ipynb) \r\n* [Extend labels](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/extend_labels.ipynb)\r\n* [Statistics of labeled pixels / regionprops](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/statistics_of_labeled_pixels.ipynb)\r\n* [Histograms](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/histograms.ipynb)\r\n* [Matrix multiplication](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/matrix_multiplication.ipynb)\r\n* [Pixel-wise comparison](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/pixelwise_comparison.ipynb)\r\n* [Intensity projections](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/intensity_projections.ipynb)\r\n* [Axis transposition](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/transpose.ipynb)\r\n* [Nonzero](http://github.com/clEsperanto/pyclesperanto_prototype/blob/master/benchmarks/nonzero.ipynb)\r\n\r\n## See also\r\nThere are other libraries for code acceleration and GPU-acceleration for image processing.\r\n* [numba](https://numba.pydata.org/)\r\n* [cupy](https://cupy.dev)\r\n* [cucim](https://github.com/rapidsai/cucim)\r\n* [clij](https://clij.github.io)\r\n\r\n## Feedback welcome!\r\nclesperanto is developed in the open because we believe in the open source community. See our [community guidelines](https://clij.github.io/clij2-docs/community_guidelines). Feel free to drop feedback as [github issue](https://github.com/clEsperanto/pyclesperanto_prototype/issues) or via [image.sc](https://image.sc)\r\n",
"bugtrack_url": null,
"license": "BSD-3-Clause",
"summary": "GPU-accelerated image processing in python using OpenCL",
"version": "0.24.5",
"project_urls": {
"Bug Tracker": "https://github.com/clEsperanto/pyclesperanto_prototype/issues",
"Documentation": "https://github.com/clEsperanto/pyclesperanto_prototype#README.md",
"Homepage": "https://github.com/clEsperanto/pyclesperanto_prototype",
"Source Code": "https://github.com/clEsperanto/pyclesperanto_prototype",
"User Support": "https://github.com/clEsperanto/pyclesperanto_prototype/issues"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "431ae24cfe9505e0585cbdafb8ca00248db306149d3334680d469a2ce96ee78e",
"md5": "083a5cc594ce7c519f6adb8b457684f7",
"sha256": "c4b00515744db9c8460710c59b31e67b93de2b15be0de9023cf66cb7d59119c7"
},
"downloads": -1,
"filename": "pyclesperanto_prototype-0.24.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "083a5cc594ce7c519f6adb8b457684f7",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 624032,
"upload_time": "2024-09-29T13:11:26",
"upload_time_iso_8601": "2024-09-29T13:11:26.916228Z",
"url": "https://files.pythonhosted.org/packages/43/1a/e24cfe9505e0585cbdafb8ca00248db306149d3334680d469a2ce96ee78e/pyclesperanto_prototype-0.24.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "59aefa33875c73625e24d4a1eaada7287269a39c9e68496e18e4dc288ed43a80",
"md5": "7d631bb5493d78e7f85bf1379d4b3f83",
"sha256": "aa38b346e9beaa716fafeb205c7999302aed1b20c07b9749f52d290c278359bc"
},
"downloads": -1,
"filename": "pyclesperanto_prototype-0.24.5.tar.gz",
"has_sig": false,
"md5_digest": "7d631bb5493d78e7f85bf1379d4b3f83",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 208470,
"upload_time": "2024-09-29T13:11:28",
"upload_time_iso_8601": "2024-09-29T13:11:28.761001Z",
"url": "https://files.pythonhosted.org/packages/59/ae/fa33875c73625e24d4a1eaada7287269a39c9e68496e18e4dc288ed43a80/pyclesperanto_prototype-0.24.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-29 13:11:28",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "clEsperanto",
"github_project": "pyclesperanto_prototype",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "pyclesperanto-prototype"
}
JSON
