If you are new to Scivision, start with the website.

The Scivision project is building:

• Some things hosted in this GitHub repository:
  • A catalog of community-curated computer vision models and datasets from the sciences and humanities
  • A Python package, for conveniently downloading and using these models and datasets from Python (scivision on PyPI)
  • Documentation for the above (documentation website)
• A gallery of notebooks using Scivision models and datasets
• a community of computer vision practitioners in the sciences and humanities (mailing list, get Slack invitation)
• A (nascent) ecosystem of computer vision tools and utilities

Submit a bug or feature request here.

If you would like a link to a model or datasource to be listed in the catalog, such a contribution would be gratefully received. See the Contributing Guide for how to set up and submit a new entry. Pull requests for code changes are also welcome.

The Scivision project is funded by the Alan Turing Institute.

Repository contents

The main project repository on GitHub hosts

• development of the Python package (in the root directory)
• development of the website (in frontend)
• the documentation sources (in docs)

Getting Started

A quick overview of using the Scivision.Py python package.

Install Scivision.Py

$ pip install scivision

• Full installation guide

Load a Scivision model

from scivision import load_pretrained_model

resnet18 = load_pretrained_model(
    # The model URL
    "https://github.com/alan-turing-institute/scivision_classifier",

    # A Scivision model can contain several variants -- below we select the one to use
    model_selection='resnet18',

    # Allow the model and its dependencies to be installed if they are not already
    # (including tensorflow in this example)
    allow_install=True
)

We can give an image as input to the model. Any image data compatible with numpy (an 'Array_like') is accepted. We can obtain some image data by loading a Scivision datasource.

• More about Scivision models

Load a Scivision datasource

from scivision import load_pretrained_model

dataset = load_dataset('https://github.com/alan-turing-institute/scivision-test-data')

# 'dataset' provides several named arrays.  This datasource provides one named 'test_image':
# the keys can be looked up with `list(dataset)` (or by consulting the datasource documentation)
#
test_image = dataset['test_image'].read()

Optionally, inspect the image (with matplotlib, for example):

import matplotlib.pyplot as plt

plt.imshow(test_image)

• More about datasources

Run a Scivision model

resnet18.predict(test_image)

Output: koala : 99.78%

Query the model and datasource catalogs

from scivision import default_catalog

# The datasource catalog as a Pandas dataframe
default_catalog.datasources.to_dataframe()

# Similarly for the model catalog
default_catalog.models.to_dataframe()

Output:

	name	description	tasks	url	pkg_url	format	scivision_usable	pretrained	labels_required	institution	tags
0	stardist	Single class object detection and segementation of star-convex polygons	(<TaskEnum.object_detection: 'object-detection'>, <TaskEnum.segmentation: 'segmentation'>)	https://github.com/stardist/stardist	git+https://github.com/stardist/stardist.git@master	image	False	True	True	('epfl',)	('2D', '3D', 'optical-microscopy', 'xray', 'microtomography', 'cell-counting', 'plant-phenotyping', 'climate-change-and-agriculture')
1	PlantCV	Open-source image analysis software package targeted for plant phenotyping	(<TaskEnum.segmentation: 'segmentation'>, <TaskEnum.thresholding: 'thresholding'>, <TaskEnum.object_detection: 'object-detection'>)	https://github.com/danforthcenter/plantcv	git+https://github.com/danforthcenter/plantcv@main	image	False	True	True	('danforthcenter',)	('2D', 'hyperspectral', 'multispectral', 'near-infrared', 'infrared', 'plant-phenotyping', 'climate-change-and-agriculture')
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮

• Contributing an entry to the catalog
• The catalogs are browsable online:
  • model catalog
  • datasource catalog

Contributors

Thanks goes to these wonderful people (emoji key):

Aida Mehonic 📋 📖 🤔	Alan R Lowe 💻 🤔 📖 🚇 🔍	Alejandro © 💻 🤔 🎨 💡	Beatriz Costa Gomes 💻 🤔 📖 🎨 💡	Ben Evans 🤔	Ed Chalstrey 💻 🤔 📖 🚇	Eriol Fox 🤔 🎨
Evangeline Corcoran 💻 🤔 📖 🚇	Isabel Fenton 💻 🤔 📖 🚇	James Parkhurst 🤔 🔣 🔌	JamesAliScott 🤔 🔣	Kasra Hosseini 💻 🤔 📖 🚇	Martin Rogers 🔣 💡 💻 🤔	Miquel Massot 💻 🤔 📖 🔌
Robert Blackwell 🤔	Samuel Tonks 💻 🤔 📖 🚇	Scott Hosking 🔍 🤔	Seb Hickman 💡 📢	louisavz 🤔 📣 📝	nbarlowATI 🤔 📋 💡	ots22 💻 🤔 📖 🚇
pwochner 🤔 📋 💡	vimode 🤔 🎨 💻 ️️️️♿️

This project follows the all-contributors specification. Contributions of any kind welcome!