sagnik1511/Conv-AE-Tensorflow-Keras

Convolutional Auto Encoder in Tensorflow >= 2.2.0

20
/ 100
Experimental

This project helps machine learning practitioners learn how to implement a convolutional autoencoder for image processing. It takes a dataset of images, specifically Pokemon images in its example, and trains a model to compress and then reconstruct them. The output includes the trained model and visualizations of its performance, showing how well it can recreate images. This tool is ideal for developers, data scientists, and machine learning engineers looking to understand or apply autoencoders for tasks like image denoising or anomaly detection.

No commits in the last 6 months.

Use this if you are a developer or machine learning engineer who wants a practical example of implementing a convolutional autoencoder using TensorFlow and Keras, especially with image data.

Not ideal if you are a non-technical user looking for a ready-to-use application to process images without writing code.

deep-learning image-processing machine-learning-engineering tensorflow keras
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

7

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 11, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sagnik1511/Conv-AE-Tensorflow-Keras"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.