Upload README.md with huggingface_hub

59215ea verified 3 months ago

4.14 kB

language: en
license: apache-2.0
tags:
  - image-classification
  - green-ai
  - energy-efficiency
  - computer-vision
  - convnextv2
  - eden-framework
  - e2am
  - sustainable-ai
datasets:
  - cifar10
metrics:
  - accuracy
co2_eq_emissions:
  emissions: 1.6822
  unit: kg
  source: Estimated via CodeCarbon (grid factor 0.475 kg CO2e/kWh)
  hardware_used: NVIDIA GeForce GTX 1080 Ti
dataset_info:
  dataset_size: 60,000 images – 10 classes (32×32 px)
model-index:
  - name: EDEN-ConvNeXtV2-CIFAR-10
    results:
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: CIFAR-10
          type: cifar10
        metrics:
          - type: accuracy
            value: 0.994
            name: Accuracy
          - type: f1
            value: 0.994
            name: F1 Score

EDEN-ConvNeXtV2-CIFAR-10 — SOTA Optimized

Primary KPI: EAG (Energy-to-Accuracy Gradient) = -2.1283e-09 ΔAcc/ΔJoules

Abstract

This model is part of Project EDEN (Energy-Driven Evolution of Networks), implementing the E2AM (Energy Efficient Advanced Model) Framework. The goal is to shift AI benchmarking from pure accuracy to Green SOTA — maximising predictive power per Joule consumed.

Applied Technique: Phase 2 – Progressive Unfreezing + AMP (E2AM SOTA)

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
OS	Windows 10
Dataset	CIFAR-10 — 60,000 images – 10 classes (32×32 px)

🟢 Green Delta Table

Comparing this model against the reference baseline (ResNet-50 equivalent)

Metric	ResNet50 Baseline	ConvNeXtV2 (EDEN)	Δ
Accuracy	0.9354	0.9940	`+5.86%`
Total Energy (J)	40,291,739	12,748,970	`68.36% saved`
CO₂ Emissions (kg)	5.3163	1.6822	—
EAG Score	—	-2.1283e-09	ΔAcc/ΔJoules

A positive EAG means this model learns more per Joule than the baseline. A negative EAG indicates a trade-off where higher accuracy required more energy investment.

E2AM Algorithm — Applied Phases

Phase 1 – Zero-Overhead Initialization: Dataset pre-loaded into pinned System RAM to eliminate disk I/O power spikes.

Phase 2 – Progressive Unfreezing: Backbone frozen for the first E_unfreeze epochs (only the classification head trains). At E_unfreeze, all layers are unfrozen and the learning rate is decayed. Gradient accumulation over N micro-batches simulates large batch sizes without proportional VRAM cost, slashing power-draw spikes.

AMP (Automated Mixed Precision): torch.cuda.amp.autocast() halves GPU memory bandwidth, reducing energy per backward pass.

Sparse Regularisation: L1 penalty λ·Σ|W| applied to trainable weights, driving dead neurons to zero and enabling future pruning.

Training Statistics

Metric	Value
Final Accuracy	0.9940 (99.40%)
Total Energy Consumed	12,748,970 J (3.5414 kWh)
Training Time	19,720 s (5.48 hrs)
Estimated CO₂	1.6822 kg CO₂e
Training Log	`test1\eden_unfrozen_cifar10_convnext.csv`

📊 Training Visualizations

Accuracy & Energy over Training

Green = accuracy (left axis) · Orange dashed = cumulative energy (right axis)

EAG Metric Trajectory

EAG = ΔAccuracy / ΔJoules — positive means learning more per Joule than baseline

Project-Wide Overview

All EDEN models: energy vs accuracy

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}
}