metadata
language: en
license: apache-2.0
tags:
- image-classification
- green-ai
- energy-efficiency
- computer-vision
- inceptionv3
- eden-framework
- reference-study
- sustainable-ai
datasets:
- cifar10
metrics:
- accuracy
EDEN-InceptionV3-CIFAR-10 — Baseline – Standard Full Training (Reference Study)
Primary KPI: EAG (Energy-to-Accuracy Gradient) — see Green Delta Table below.
Abstract
This model is part of Project EDEN (Energy-Driven Evolution of Networks). It serves as the Brute-Force Baseline for the InceptionV3 architecture on CIFAR-10, providing a transparent energy reference for EAG benchmarking against EDEN-optimized models.
Applied Technique: Baseline – Standard Full Training (Reference Study)
Profiling Environment
| Component | Specification |
|---|---|
| GPU | NVIDIA GeForce GTX 1080 Ti (11 GB VRAM, 250 W TDP) |
| CPU | Intel Xeon W-2125 (4 cores / 8 threads @ 4.00 GHz) |
| RAM | 63.66 GB System RAM |
| Dataset | CIFAR-10 — 60,000 images – 10 classes (32×32 px) |
🟢 Green Delta Table
This is the reference baseline. Compare against EDEN-optimized models for EAG.
| Metric | InceptionV3 Baseline | EDEN Optimized | Δ |
|---|---|---|---|
| Accuracy | See CSV log | See SOTA repo | — |
| Total Energy (J) | See CSV log | See SOTA repo | — |
| EAG Score | — | See SOTA repo | ΔAcc/ΔJoules |
E2AM Algorithm — Applied Phase
Standard full fine-tuning used as the Brute-Force Baseline for energy comparison. All layers trained from epoch 1 with a fixed learning rate and no gradient accumulation. Included for transparent EAG benchmarking.
Cite This Research
@misc{eden2025,
title = {Project EDEN: Energy-Driven Evolution of Networks},
author = {EDEN Research Team},
year = {2025},
note = {Hugging Face: Shanmuk4622},
url = {https://huggingface.co/Shanmuk4622}
}