Skip to main content

No project description provided

Project description

CIFAR-100 Utils

This package provides simple utility functions to help you work with the CIFAR-100 dataset. With just a couple of functions, you can easily access the class names and superclasses of CIFAR-100.

What is CIFAR-100?

CIFAR-100 is a popular dataset used in machine learning. It contains 100 different classes of images, each with 600 images. These classes range from animals like 'dog' and 'cat', to objects like 'car' and 'plane'.

What does this package do?

This package gives you two useful functions:

  • get_classes(): This function returns a list of 100 fine-grained class names (e.g., 'apple', 'dog', 'airplane').
  • get_super_classes(): This function returns a list of 20 broad superclasses (e.g., 'aquatic mammals', 'flowers', 'vehicles').

These functions are useful when you're working with the CIFAR-100 dataset and want easy access to the class names for training, testing, or visualization.

Installation

You can easily install the package using pip:

pip install cifar_utils

## Installation

Once you've installed the package, you can use it in your Python code like this:

### 1. Get all class names:

The `get_classes()` function returns a list of 100 fine-grained class names from the CIFAR-100 dataset.

```python
from cifar_utils import get_classes

# Get all class names from CIFAR-100
class_names = get_classes()

# Print the first 10 class names
print(class_names[:10])  

### 2. Get all super class names:

from cifar_utils import get_super_classes

# Get all superclasses
super_classes = get_super_classes()

# Print the first 10 superclasses
print(super_classes[:10])

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cifar_utils-0.1.1.tar.gz (2.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

cifar_utils-0.1.1-py3-none-any.whl (2.6 kB view details)

Uploaded Python 3

File details

Details for the file cifar_utils-0.1.1.tar.gz.

File metadata

  • Download URL: cifar_utils-0.1.1.tar.gz
  • Upload date:
  • Size: 2.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.13.1

File hashes

Hashes for cifar_utils-0.1.1.tar.gz
Algorithm Hash digest
SHA256 8c080eee2607cd07d5bbcacfc3b033218fa7d70381b4fede3a7f4c03056bf9b8
MD5 1c822710b8741a6b7906950409a8ec0e
BLAKE2b-256 afb7272355b61d786db74e627cda55786a5d830edbdb8c974c79d47d5fbe5aae

See more details on using hashes here.

File details

Details for the file cifar_utils-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: cifar_utils-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 2.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.13.1

File hashes

Hashes for cifar_utils-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 d05de4e359340b92dd3101ac04d18c1841edaff5427ef5b2c92ccecb1abb1e15
MD5 ee597d5e591e9c3b892272fb324abc85
BLAKE2b-256 b63e4111afba88606fb2c25c43b0cbb7df5442fdc7723a8e45c177d9ebfc9dfa

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page