gperdrizet/compression_autoencoder

Image compression autoencoder

A convolutional autoencoder trained to compress 256×256 RGB images into a compact 1024-dimensional latent representation, achieving 192× compression ratio.

Model description

This model learns to compress high-quality images by encoding them into a compact latent space, then reconstructing them with minimal quality loss. The encoder reduces a 196,608-value image (256×256×3) to just 1024 numbers, while the decoder reconstructs the original image from this compressed representation.

Architecture:

• Encoder: Convolutional layers with downsampling (256×256×3 → 2048)
• Decoder: Transposed convolutional layers with upsampling (2048 → 256×256×3)
• Activation: LeakyReLU and Sigmoid
• Normalization: Batch normalization

Performance:

• Compression ratio: 96×
• PSNR: ~22 dB dB
• SSIM: >0.52

Intended use

This model is designed for educational purposes to demonstrate how autoencoders can learn compression automatically from data, rather than using hand-crafted rules like JPEG or PNG.

Use cases:

• Understanding autoencoder architectures
• Learning about lossy compression
• Exploring latent space representations
• Teaching AI/ML concepts in bootcamps

Training data

Trained on DF2K_OST, a combined dataset of 26.8k high-quality images from:

• DIV2K
• Flickr2K
• OutdoorSceneTraining

All images resized to 256×256 pixels using Lanczos resampling.

Training details

Hyperparameters:

• Optimizer: Adam (lr=1e-3)
• Loss function: Mean Squared Error (MSE)
• Batch size: 4
• Epochs: Up to 100 (with early stopping)
• Train/validation split: 90/10

Callbacks:

• Early stopping (patience=10, monitoring validation loss)
• Learning rate reduction (factor=0.5, patience=5)
• Model checkpoint (best validation loss)

Hardware:

• Single NVIDIA P100 GPU with memory growth enabled

How to use

import shutil

from tensorflow import keras
from huggingface_hub import hf_hub_download

# Download model
downloaded_model = hf_hub_download(
    repo_id='gperdrizet/compression_autoencoder',
    filename='models/compression_ae.keras',
    repo_type='model'
)

# Load model
autoencoder = keras.models.load_model(downloaded_model)

# Use for compression/decompression
compressed = autoencoder.predict(images)  # images shape: (N, 256, 256, 3)

For complete examples, see the training notebook.

Limitations

• Fixed input size (256×256 RGB images)
• Lossy compression (some quality loss)
• Not optimized for specific image types
• Slower than traditional codecs
• Educational model, not production-ready

Project repository

Full code, training notebooks, and interactive demo: gperdrizet/autoencoders

Citation

If you use this model for educational purposes, please reference the project repository.