معرفی شرکت ها
apoc-0.9.0
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشترتوضیحات
Accelerated Pixel and Object Classifiers based on OpenCL
| ویژگی | مقدار |
|---|---|
| سیستم عامل | - |
| نام فایل | apoc-0.9.0 |
| نام | apoc |
| نسخه کتابخانه | 0.9.0 |
| نگهدارنده | [] |
| ایمیل نگهدارنده | [] |
| نویسنده | haesleinhuepf |
| ایمیل نویسنده | robert.haase@tu-dresden.de |
| آدرس صفحه اصلی | https://github.com/haesleinhuepf/apoc |
| آدرس اینترنتی | https://pypi.org/project/apoc/ |
| مجوز | - |
# Accelerated Pixel and Object Classifiers (APOC)
[](https://github.com/haesleinhuepf/apoc/raw/main/LICENSE)
[](https://pypi.org/project/apoc)
[](https://python.org)
[](https://github.com/haesleinhuepf/apoc/actions)
[](https://codecov.io/gh/haesleinhuepf/apoc)
[](https://en.wikipedia.org/wiki/Software_release_life_cycle#Alpha)
[](https://zenodo.org/badge/latestdoi/412505712)
[clesperanto](https://github.com/clEsperanto/pyclesperanto_prototype) meets [scikit-learn](https://scikit-learn.org/stable/) to classify pixels and objects in images, on a [GPU](https://en.wikipedia.org/wiki/Graphics_processing_unit) using [OpenCL](https://www.khronos.org/opencl/).
This repository contains the backend for python developers. User-friendly plugins for [Fiji](https://fiji.sc) and [napari](https://napari.org) can be found here:
* [napari-accelerated-pixel-and-object-classification](https://github.com/haesleinhuepf/napari-accelerated-pixel-and-object-classification)
* [clijx-accelerated-pixel-and-object-classification](https://github.com/clij/clijx-accelerated-pixel-and-object-classification)
For training classifiers from pairs of image and label-mask folders, please see
[this notebook](https://github.com/haesleinhuepf/apoc/blob/main/demo/train_on_folders.ipynb).
## Object segmentation
With a given blobs image and a corresponding annotation...
```python
import apoc
from skimage.io import imread, imshow
import pyclesperanto_prototype as cle
image = imread('blobs.tif')
imshow(image)
```
```python
manual_annotations = imread('annotations.tif')
imshow(manual_annotations, vmin=0, vmax=3)
```
... objects can be segmented ([see full example](https://github.com/haesleinhuepf/apoc/blob/main/demo/demo_object_segmenter.ipynb)):
```python
# define features: original image, a blurred version and an edge image
features = apoc.PredefinedFeatureSet.medium_quick.value
# Training
clf = apoc.ObjectSegmenter(opencl_filename='object_segmenter.cl', positive_class_identifier=2)
clf.train(features, manual_annotations, image)
# Prediction
segmentation_result = clf.predict(image=image)
cle.imshow(segmentation_result, labels=True)
```
## Object classification
With a given annotation, blobs can also be classified according to their shape ([see full example](https://github.com/haesleinhuepf/apoc/blob/main/demo/demo_object_classification.ipynb)).
```python
features = 'area,mean_max_distance_to_centroid_ratio,standard_deviation_intensity'
# Create an object classifier
classifier = apoc.ObjectClassifier("object_classifier.cl")
# Training
classifier.train(features, segmentation_result, annotation, image)
# Prediction / determine object classification
classification_result = classifier.predict(segmentation_result, image)
cle.imshow(classification_result, labels=True)
```
## Object selector
If the desired analysis goal is to select objects of a specific class, the object selector can be used ([see full example](https://github.com/haesleinhuepf/apoc/blob/main/demo/demo_object_selector.ipynb)).
```python
features = 'area,mean_max_distance_to_centroid_ratio,standard_deviation_intensity'
cl_filename = "object_selector.cl"
# Create an object classifier
apoc.erase_classifier(cl_filename) # delete it if it was existing before
classifier = apoc.ObjectSelector(cl_filename, positive_class_identifier=1)
# train it
classifier.train(features, labels, annotation, image)
result = classifier.predict(labels, image)
cle.imshow(result, labels=True)
```
## Object merger
APOC also comes with a `ObjectMerger` allowing to train a classifier on label edges for deciding to merge them or to keep them.
([See full example](https://github.com/haesleinhuepf/apoc/blob/main/demo/merge_objects.ipynb))
```python
feature_definition = "touch_portion mean_touch_intensity"
classifier_filename = "label_merger.cl"
apoc.erase_classifier(classifier_filename)
classifier = apoc.ObjectMerger(opencl_filename=classifier_filename)
classifier.train(features=feature_definition,
labels=oversegmented,
sparse_annotation=annotation,
image=background_subtracted)
merged_labels = classifier.predict(labels=oversegmented, image=background_subtracted)
cle.imshow(merged_labels, labels=True)
```
## More detailed examples
* [Object segmentation](https://nbviewer.jupyter.org/github/haesleinhuepf/apoc/blob/main/demo/demo_object_segmenter.ipynb)
* [Object classification](https://nbviewer.jupyter.org/github/haesleinhuepf/apoc/blob/main/demo/demo_object_classification.ipynb)
* [Object classification based on custom measurement tables](https://nbviewer.jupyter.org/github/haesleinhuepf/apoc/blob/main/demo/table_row_classification.ipynb)
* [Pixel classifier (including benchmarking)](https://nbviewer.jupyter.org/github/haesleinhuepf/apoc/blob/main/demo/benchmarking_pixel_classifier.ipynb).
* [Output probability maps](https://nbviewer.jupyter.org/github/haesleinhuepf/apoc/blob/main/demo/demo_probability_mapper.ipynb)
* [Continue training of pixel classifiers using multiple training image pairs](https://nbviewer.jupyter.org/github/haesleinhuepf/apoc/blob/main/demo/demp_pixel_classifier_continue_training.ipynb)
* [Generating custom feature stacks](https://nbviewer.jupyter.org/github/haesleinhuepf/apoc/blob/main/demo/feature_stacks.ipynb)
## Installation
You can install `apoc` using conda or pip:
conda install -c conda-forge apoc-backend
OR:
conda install pyopencl
pip install apoc
Mac-users please also install this:
conda install -c conda-forge ocl_icd_wrapper_apple
Linux users please also install this:
conda install -c conda-forge ocl-icd-system
## Contributing
Contributions are very welcome. Tests can be run with `pytest`, please ensure
the coverage at least stays the same before you submit a pull request.
## License
Distributed under the terms of the BSD-3 license,
"apoc" is free and open source software
## Issues
If you encounter any problems, please [open a thread on image.sc](https://image.sc) along with a detailed description and tag [@haesleinhuepf](https://github.com/haesleinhuepf).
نیازمندی
| مقدار | نام |
|---|---|
| >=1.21 | numpy |
| >=0.24.2 | scikit-learn |
| >=0.21.1 | pyclesperanto-prototype |
| - | pandas |
زبان مورد نیاز
| مقدار | نام |
|---|---|
| >=3.6 | Python |
نحوه نصب
نصب پکیج whl apoc-0.9.0:
pip install apoc-0.9.0.whl
نصب پکیج tar.gz apoc-0.9.0:
pip install apoc-0.9.0.tar.gz