Shanmuk4622 commited on
Commit
5fddc26
·
verified ·
1 Parent(s): e3bef49

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +37 -4
README.md CHANGED
@@ -21,6 +21,22 @@ co2_eq_emissions:
21
  hardware_used: NVIDIA GeForce GTX 1080 Ti
22
  dataset_info:
23
  dataset_size: "60,000 images – 100 classes (32×32 px)"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  ---
25
 
26
  # EDEN-AlexNet-CIFAR-100 — *EDEN Classic*
@@ -28,7 +44,9 @@ dataset_info:
28
  > **Primary KPI:** EAG (Energy-to-Accuracy Gradient) = `4.5587e-09` ΔAcc/ΔJoules
29
 
30
  ## Abstract
31
- 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* — maximizing predictive power per Joule consumed.
 
 
32
 
33
  **Applied Technique:** Phase 2 – EDEN Classic Energy-Aware Sparse Training
34
 
@@ -69,15 +87,30 @@ This model is part of **Project EDEN (Energy-Driven Evolution of Networks)**, im
69
  | Estimated CO₂ | 3.6739 kg CO₂e |
70
  | Training Log | `test3\alexnet_EDEN_CIFAR100_stats.csv` |
71
 
72
- ## Cite This Research
73
- If you use this model, please cite the **EDEN / E2AM Framework**:
 
 
 
 
 
 
 
74
 
 
 
 
 
 
 
 
 
75
  ```bibtex
76
  @misc{eden2025,
77
  title = {Project EDEN: Energy-Driven Evolution of Networks},
78
  author = {EDEN Research Team},
79
  year = {2025},
80
- note = {Hugging Face Organization: ProjectEDEN},
81
  url = {https://huggingface.co/Shanmuk4622}
82
  }
83
  ```
 
21
  hardware_used: NVIDIA GeForce GTX 1080 Ti
22
  dataset_info:
23
  dataset_size: "60,000 images – 100 classes (32×32 px)"
24
+ model-index:
25
+ - name: EDEN-AlexNet-CIFAR-100
26
+ results:
27
+ - task:
28
+ type: image-classification
29
+ name: Image Classification
30
+ dataset:
31
+ name: CIFAR-100
32
+ type: cifar100
33
+ metrics:
34
+ - type: accuracy
35
+ value: 0.8933
36
+ name: Accuracy
37
+ - type: f1
38
+ value: 0.8932
39
+ name: F1 Score
40
  ---
41
 
42
  # EDEN-AlexNet-CIFAR-100 — *EDEN Classic*
 
44
  > **Primary KPI:** EAG (Energy-to-Accuracy Gradient) = `4.5587e-09` ΔAcc/ΔJoules
45
 
46
  ## Abstract
47
+ This model is part of **Project EDEN (Energy-Driven Evolution of Networks)**, implementing the
48
+ **E2AM (Energy Efficient Advanced Model)** Framework. The goal is to shift AI benchmarking from
49
+ pure accuracy to *Green SOTA* — maximising predictive power per Joule consumed.
50
 
51
  **Applied Technique:** Phase 2 – EDEN Classic Energy-Aware Sparse Training
52
 
 
87
  | Estimated CO₂ | 3.6739 kg CO₂e |
88
  | Training Log | `test3\alexnet_EDEN_CIFAR100_stats.csv` |
89
 
90
+ ## 📊 Training Visualizations
91
+
92
+ ### Accuracy & Energy over Training
93
+ > Green = accuracy (left axis) · Orange dashed = cumulative energy (right axis)
94
+
95
+ ![Training Curve](training_curve.png)
96
+
97
+ ### EAG Metric Trajectory
98
+ > EAG = ΔAccuracy / ΔJoules — positive means learning more per Joule than baseline
99
 
100
+ ![EAG Curve](eag_curve.png)
101
+
102
+ ### Project-Wide Overview
103
+ *All EDEN models: energy vs accuracy*
104
+
105
+ ![Collection Overview](https://huggingface.co/Shanmuk4622/EDEN-Core-Scripts/resolve/main/energy_accuracy_overview.png)
106
+
107
+ ## Cite This Research
108
  ```bibtex
109
  @misc{eden2025,
110
  title = {Project EDEN: Energy-Driven Evolution of Networks},
111
  author = {EDEN Research Team},
112
  year = {2025},
113
+ note = {Hugging Face: Shanmuk4622},
114
  url = {https://huggingface.co/Shanmuk4622}
115
  }
116
  ```