Update README - Run 20251012_194945

README.md

@@ -5,7 +5,7 @@ tags:
 - image-classification
 - imagenet
 - multi-scale
-- crystal-geometry
+- feature-geometry
 - david
 datasets:
 - imagenet-1k
@@ -21,14 +21,18 @@ model-index:
       type: imagenet-1k
     metrics:
     - type: accuracy
-      value: 73.69
+      value: 69.48
 ---
 
-# David: Multi-Scale Crystal Classifier
+# David: Multi-Scale Feature Classifier
 
-**David** is a multi-scale deep learning classifier that uses crystal geometry (pentachora/4-simplexes) 
+**David** is a multi-scale deep learning classifier that uses feature geometry (pentachora/4-simplexes) 
 as class prototypes with role-weighted similarity computation (Rose Loss).
 
+This version is using multiple variations of clip-vit inputs simultaneously into shared space.
+The experiment will determine if entirely deviant variations such as clip-vit-b-patch32 and patch16 can
+exist simultaneously in the same shared space with the correct checks and spacings applied.
+
 ## Model Details
 
 ### Architecture
@@ -41,7 +45,7 @@ as class prototypes with role-weighted similarity computation (Rose Loss).
 
 ### Training Configuration
 - **Dataset**: AbstractPhil/imagenet-clip-features-orderly
-- **Model Variant**: ['clip_vit_b32', 'clip_vit_laion_b32']
+- **Model Variant**: ['clip_vit_b16', 'clip_vit_laion_b32']
 - **Epochs**: 10
 - **Batch Size**: 1024
 - **Learning Rate**: 0.01
@@ -51,15 +55,12 @@ as class prototypes with role-weighted similarity computation (Rose Loss).
 ## Performance
 
 ### Best Results
-- **Validation Accuracy**: 73.69%
-- **Best Epoch**: 9
-- **Final Train Accuracy**: 81.77%
+- **Validation Accuracy**: 69.48%
+- **Best Epoch**: 0
+- **Final Train Accuracy**: 58.63%
 
 ### Per-Scale Performance
-- **Scale 256**: 71.84%
-- **Scale 512**: 73.69%
-- **Scale 768**: 73.94%
-- **Scale 1024**: 74.06%
+- **Scale 256**: 69.48%
 
 
 ## Usage
@@ -77,18 +78,18 @@ AbstractPhil/david-shared-space/
 ├── best_model.json                   # Latest best model info
 ├── weights/
 │   └── david_balanced/
-│       └── 20251012_191456/
+│       └── 20251012_194945/
 │           ├── MODEL_SUMMARY.txt     # 🎯 Human-readable performance summary
 │           ├── training_history.json # 📈 Epoch-by-epoch training curve
-│           ├── best_model_acc73.69.safetensors  # ⭐ Accuracy in filename!
-│           ├── best_model_acc73.69_metadata.json
+│           ├── best_model_acc69.48.safetensors  # ⭐ Accuracy in filename!
+│           ├── best_model_acc69.48_metadata.json
 │           ├── final_model.safetensors
 │           ├── checkpoint_epoch_X_accYY.YY.safetensors
 │           ├── david_config.json
 │           └── train_config.json
 └── runs/
     └── david_balanced/
-        └── 20251012_191456/
+        └── 20251012_194945/
             └── events.out.tfevents.* # TensorBoard logs
 ```
 
@@ -102,8 +103,8 @@ from huggingface_hub import hf_hub_download
 
 # Specify model variant and run
 model_name = "david_balanced"
-run_id = "20251012_191456"
-accuracy = "73.69"  # From MODELS_INDEX.json
+run_id = "20251012_194945"
+accuracy = "69.48"  # From MODELS_INDEX.json
 
 # Download config
 config_path = hf_hub_download(
@@ -158,7 +159,7 @@ allowing it to capture both coarse and fine-grained features.
 ### Shared Representation Space
 This variation shares multiple versions of clip-vit models in the same representation space.
 
-### Crystal Geometry
+### Feature Geometry
 Each class is represented by a pentachoron (4-simplex) in embedding space with 5 vertices:
 - **Anchor**: Primary class representative
 - **Need**: Complementary direction
@@ -193,11 +194,11 @@ score = w_anchor * sim(z, anchor) + w_need * sim(z, need) + ...
 
 ```bibtex
 @software{david_classifier_2025,
-  title = {David: Multi-Scale Crystal Classifier},
+  title = {David: Multi-Scale Feature Classifier},
   author = {AbstractPhil},
   year = {2025},
   url = {https://huggingface.co/AbstractPhil/david-shared-space},
-  note = {Run ID: 20251012_191456}
+  note = {Run ID: 20251012_194945}
 }
 ```
 
@@ -207,9 +208,9 @@ MIT License
 
 ## Acknowledgments
 
-Built with crystal lattice geometry and multi-scale deep learning.
+Built with feature lattice geometry and multi-scale deep learning.
 Special thanks to Claude (Anthropic) for debugging assistance.
 
 ---
 
-*Generated on 2025-10-12 19:48:31*
+*Generated on 2025-10-12 19:53:35*