Shanmuk4622 commited on
Commit
369eeee
·
verified ·
1 Parent(s): 5591ebb

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +29 -4
README.md CHANGED
@@ -21,6 +21,19 @@ co2_eq_emissions:
21
  hardware_used: NVIDIA GeForce GTX 1080 Ti
22
  dataset_info:
23
  dataset_size: "~450,000 images – 300 classes (224 px)"
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  ---
25
 
26
  # EDEN-UNet-Custom-ImageNet300 — *EDEN Classic*
@@ -28,7 +41,9 @@ dataset_info:
28
  > **Primary KPI:** EAG (Energy-to-Accuracy Gradient) = `N/A` 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 +84,25 @@ This model is part of **Project EDEN (Energy-Driven Evolution of Networks)**, im
69
  | Estimated CO₂ | 0.0000 kg CO₂e |
70
  | Training Log | `test3\unet_classifier_EDEN_CustomImageNet300_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: "~450,000 images – 300 classes (224 px)"
24
+ model-index:
25
+ - name: EDEN-UNet-Custom-ImageNet300
26
+ results:
27
+ - task:
28
+ type: image-classification
29
+ name: Image Classification
30
+ dataset:
31
+ name: Custom-ImageNet300
32
+ type: imagenet
33
+ metrics:
34
+ - type: accuracy
35
+ value: 0.9959
36
+ name: Accuracy
37
  ---
38
 
39
  # EDEN-UNet-Custom-ImageNet300 — *EDEN Classic*
 
41
  > **Primary KPI:** EAG (Energy-to-Accuracy Gradient) = `N/A` ΔAcc/ΔJoules
42
 
43
  ## Abstract
44
+ This model is part of **Project EDEN (Energy-Driven Evolution of Networks)**, implementing the
45
+ **E2AM (Energy Efficient Advanced Model)** Framework. The goal is to shift AI benchmarking from
46
+ pure accuracy to *Green SOTA* — maximising predictive power per Joule consumed.
47
 
48
  **Applied Technique:** Phase 2 – EDEN Classic Energy-Aware Sparse Training
49
 
 
84
  | Estimated CO₂ | 0.0000 kg CO₂e |
85
  | Training Log | `test3\unet_classifier_EDEN_CustomImageNet300_stats.csv` |
86
 
87
+ ## 📊 Training Visualizations
88
+
89
+ ### EAG Metric Trajectory
90
+ > EAG = ΔAccuracy / ΔJoules — positive means learning more per Joule than baseline
91
+
92
+ ![EAG Curve](eag_curve.png)
93
 
94
+ ### Project-Wide Overview
95
+ *All EDEN models: energy vs accuracy*
96
+
97
+ ![Collection Overview](https://huggingface.co/Shanmuk4622/EDEN-Core-Scripts/resolve/main/energy_accuracy_overview.png)
98
+
99
+ ## Cite This Research
100
  ```bibtex
101
  @misc{eden2025,
102
  title = {Project EDEN: Energy-Driven Evolution of Networks},
103
  author = {EDEN Research Team},
104
  year = {2025},
105
+ note = {Hugging Face: Shanmuk4622},
106
  url = {https://huggingface.co/Shanmuk4622}
107
  }
108
  ```