YasirUsman/vet-anomaly-vae-dog-health

🐕 Vet-Anomaly-VAE: Dog Health Diagnostics

This repository contains a Deep Variational Autoencoder (VAE) trained to identify biological anomalies in canine biomarker data. By learning the "normal" physiological baseline of 50 dogs across various breeds, this model can flag individuals that show unusual health signatures.

📊 Performance Metrics

• Reconstruction Accuracy: 97.11%
• Mean Squared Error (MSE): 0.1172
• Model Type: Deep VAE (32-16-4 Latent Space)

[Image of VAE architecture with encoder and decoder layers]

🛠️ How to Use

Since this is a custom PyTorch architecture, use the following code to load the model and run inference:

import torch
import torch.nn as nn

# Define the architecture
class DeepVAE(nn.Module):
    def __init__(self, input_dim=15, latent_dim=4):
        super(DeepVAE, self).__init__()
        self.encoder = nn.Sequential(
            nn.Linear(input_dim, 32), nn.ReLU(),
            nn.Linear(32, 16), nn.ReLU(),
            nn.Linear(16, latent_dim * 2) 
        )
        self.decoder = nn.Sequential(
            nn.Linear(latent_dim, 16), nn.ReLU(),
            nn.Linear(16, 32), nn.ReLU(),