🧠 Autoencoder Image Bottleneck Sandbox

Explore how deep neural networks compress, reconstruct, and denoise raw images. By training an autoencoder on just this single image, you can observe how limiting the latent bottleneck restricts the reconstruction capability—forcing the network to blur details or filter noise!

🛠️ Step 1: Input & Parameters

Upload Source Image

Training Resolution

Pick a preset (n x n or n x m), use the image's native size, or set a custom width/height below.

Custom Width

Only used when 'Custom' is selected above.

8 512

Custom Height

Only used when 'Custom' is selected above.

8 512

Latent Dimension (Bottleneck)

Lower values yield abstract, blurry representations ('not 1:1').

1 256

Hidden Dimension

Size of the intermediate neural network layers.

16 512

Number of Hidden Layers

Deepens the feature extraction depth.

1 3

📊 Step 2: Live Training Output

Model Input (Noisy / Resized)

Live Model Reconstruction

Training Diagnostics

Click Begin Real-Time Training to launch the network optimization loop.

Live Loss Curve