Metadata-Version: 2.1
Name: zeroshot
Version: 0.1.6
Summary: Image classifier with zero-shot learning.
Home-page: https://github.com/moonshinelabs/zeroshot-python
License: MIT
Keywords: zeroshot,classifier,cv
Author: Nate Harada
Author-email: hello@usezeroshot.com
Requires-Python: >=3.10,<3.13
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Requires-Dist: mypy (>=1.6.0,<2.0.0)
Requires-Dist: numpy (>=1.26.0,<2.0.0)
Requires-Dist: onnxruntime (>=1.16.1,<2.0.0)
Requires-Dist: pillow (>=10.0.1,<11.0.0)
Requires-Dist: requests (>=2.31.0,<3.0.0)
Requires-Dist: types-pillow (>=10.0.0.3,<11.0.0.0)
Project-URL: Repository, https://github.com/moonshinelabs/zeroshot-python
Description-Content-Type: text/markdown

# Zeroshot (Python)

Image classification for the masses

## Installation

Install via pip: `pip install zeroshot`

## Usage

First, go to usezeroshot.com and create a classifier. See [here](<>) for more instructions.

Then, in Python (`image` should be an RGB numpy array with channels last):

```python
import zeroshot

# Create the classifier and preprocessing function.
classifier = zeroshot.Classifier("your model string or path")
preprocess_fn = zeroshot.create_preprocess_fn()

# Run the model!
prediction = classifier.predict(preprocess_fn(image))
print(f"The image is class {prediction}")
```

## Read the docs

See the [docs](docs/getting_started.md) folder for some details.

