Metadata-Version: 2.1
Name: instancelib-onnx
Version: 0.1.0
Summary: A wrapper for ONNX models that adheres to instancelib
Home-page: UNKNOWN
Author: Michiel Bron
Author-email: m.p.bron@uu.nl
License: GNU LGPL v3
Platform: UNKNOWN
Classifier: License :: OSI Approved :: GNU Lesser General Public License v3 or later (LGPLv3+)
Classifier: Programming Language :: Python
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: instancelib (>=0.3.8.0)
Requires-Dist: onnxruntime
Requires-Dist: onnx
Requires-Dist: onnxmltools
Requires-Dist: skl2onnx
Provides-Extra: doc2vec
Requires-Dist: gensim ; extra == 'doc2vec'
Provides-Extra: hdf5
Requires-Dist: tables ; extra == 'hdf5'

# instancelib-onnx
ONNX extension for instancelib

```python
import instancelib as il
import instancelib as ilonnx

# Specify the model location and the label translation 
model = ilonnx.build_data_model("example_models/data-model.onnx", 
                                {0: "Bedrijfsnieuws", 1: "Games", 2: "Smartphones"})
```

Then you can use the normal instancelib functionality to interact with the model.

```python
# Load a dataset with instancelib
env = il.read_excel_dataset("datasets/testdataset.xlsx", ["fulltext"], ["label"])

# Assess the performance like any other instancelib model
performance = il.classifier_performance(read_data_model, env.dataset, env.labels)
performance.confusion_matrix
```

