CVX2 · PyPI

Usage Sample ''''''''''''

.. code:: python

    from torch import nn
    from cvx2 import WidthBlock
    from cvx2.wrapper import ImageClassifyModelWrapper

    model = nn.Sequential(
        WidthBlock(c1=1, c2=32),
        nn.MaxPool2d(kernel_size=2, stride=2),
        WidthBlock(c1=32, c2=64),
        nn.MaxPool2d(kernel_size=2, stride=2),
        nn.Flatten(),
        nn.Linear(in_features=64*49, out_features=1024),
        nn.Dropout(0.2),
        nn.SiLU(inplace=True),
        nn.Linear(in_features=1024, out_features=2),
    )

    data_dir
     |__train
     |   |__class1
     |   |   |__001.jpg
     |   |   |__002.jpg
     |   |__class2
     |      |__001.jpg
     |      |__002.jpg
     |__test
     |   |__class1
     |   |   |__001.jpg
     |   |   |__002.jpg
     |   |__class2
     |      |__001.jpg
     |      |__002.jpg
     |__val
         |__class1
         |   |__001.jpg
         |   |__002.jpg
         |__class2
            |__001.jpg
            |__002.jpg

    model_wrapper = ImageClassifyModelWrapper(model)
    model_wrapper.train(data='data_dir', imgsz=28)
    result = model_wrapper.predict('data_dir/test/class1/001.jpg', imgsz=28)

Release files for CVX2 0.6.6

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for CVX2 0.6.6
File	Size	Uploaded
cvx2-0.6.6.tar.gz	25.3 kB	Jun 20, 2026	Details

Release files / cvx2-0.6.6.tar.gz

Download URL	cvx2-0.6.6.tar.gz
Size	25.3 kB
Tags	Source
SHA-256 checksum How to use checksums	`7cb9df2c8255af1758b15ed167b058184ba49c71203692d3bd3712780032b8e4`
BLAKE2b-256 checksum How to use checksums	`6ffe5d15c992370ba426d336d250d82bcaa23565d2c7729d32b8e0fbce6c1b6c`
Upload date	Jun 20, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/5.0.0 CPython/3.9.18`