Model wrapper for Pytorch, which can training, predict, evaluate, etc.
Project description
Usage Sample ''''''''''''
.. code:: python
from model_wrapper import SplitClassModelWrapper
classes = ['class1', 'class2', 'class3'...]
X = [[...], [...],]
y = [0, 0, 1, 2, 1...]
model = ...
wrapper = SplitClassModelWrapper(model, classes=classes)
wrapper.train(X, y, val_size=0.2)
X_test = [[...], [...],]
y_test = [0, 1, 1, 2, 1...]
result = wrapper.evaluate(X_test, y_test)
# 0.953125
result = wrapper.predict(X_test)
# [0, 1]
result = wrapper.predict_classes(X_test)
# ['class1', 'class2']
result = wrapper.predict_proba(X_test)
# ([0, 1], array([0.99439645, 0.99190724], dtype=float32))
result = wrapper.predict_classes_proba(X_test)
# (['class1', 'class2'], array([0.99439645, 0.99190724], dtype=float32))
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
model-wrapper-0.3.0.tar.gz
(14.9 kB
view details)
File details
Details for the file model-wrapper-0.3.0.tar.gz.
File metadata
- Download URL: model-wrapper-0.3.0.tar.gz
- Upload date:
- Size: 14.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.9.18
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
aca30dfed5a06ba408c7e428e72783e11e5a98a29f48f26f8e175d739070dc9f
|
|
| MD5 |
52b317786bff7728d1f671ba83263ea3
|
|
| BLAKE2b-256 |
6427f7129205fcf1d8bcc405e0e1becc5ccc2fa9e71a7165b69c47ec65aaf2cf
|
