fashion-mnist and fashion

The second project, `primaryobjects/fashion`, is a complementary tool that utilizes the dataset provided by the first project, `zalandoresearch/fashion-mnist`, to build and demonstrate machine learning models.

fashion-mnist
51
Established
fashion
24
Experimental
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 25/25
Maintenance 0/25
Adoption 6/25
Maturity 1/25
Community 17/25
Stars: 12,667
Forks: 3,076
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 24
Forks: 8
Downloads:
Commits (30d): 0
Language: R
License:
Stale 6m No Package No Dependents
No License Stale 6m No Package No Dependents

About fashion-mnist

zalandoresearch/fashion-mnist

A MNIST-like fashion product database. Benchmark :point_down:

Comprises 70,000 28x28 grayscale images of Zalando clothing across 10 product categories, maintaining byte-for-byte compatibility with the original MNIST format for seamless algorithm migration. Integrated natively into TensorFlow, PyTorch, Keras, and 10+ other ML frameworks, eliminating custom data loading while presenting a more realistic computer vision task than handwritten digits. Addresses MNIST's saturation as a benchmark—modern CNNs achieve 99.7% on MNIST but face genuine classification challenges with Fashion-MNIST's subtle inter-class variations.

About fashion

primaryobjects/fashion

The Fashion-MNIST dataset and machine learning models.

Scores updated daily from GitHub, PyPI, and npm data. How scores work