|
Download README.md from AbstractPhil/gated-david: direct link, hf CLI and curl.
- Browser
- Download file 5.76 kB
-
https://huggingface.co/AbstractPhil/gated-david/resolve/39a7beeec97ffc24be6dd49ba76725ed2203e5fa/README.md
- Command line
-
hf download hf://AbstractPhil/gated-david@39a7beeec97ffc24be6dd49ba76725ed2203e5fa/README.md
-
curl -L -o README.md https://huggingface.co/AbstractPhil/gated-david/resolve/39a7beeec97ffc24be6dd49ba76725ed2203e5fa/README.md
5.76 kB
| language: en | |
| license: mit | |
| tags: | |
| - image-classification | |
| - imagenet | |
| - multi-scale | |
| - crystal-geometry | |
| - david | |
| datasets: | |
| - imagenet-1k | |
| metrics: | |
| - accuracy | |
| model-index: | |
| - name: David-partial_shared-deep_efficiency | |
| results: | |
| - task: | |
| type: image-classification | |
| dataset: | |
| name: ImageNet-1K | |
| type: imagenet-1k | |
| metrics: | |
| - type: accuracy | |
| value: 83.66 | |
| # David: Multi-Scale Crystal Classifier | |
| **David** is a multi-scale deep learning classifier that uses crystal geometry (pentachora/4-simplexes) | |
| as class prototypes with role-weighted similarity computation (Rose Loss). | |
| ## Model Details | |
| ### Architecture | |
| - **Preset**: clip_vit_bigg14 | |
| - **Sharing Mode**: partial_shared | |
| - **Fusion Mode**: deep_efficiency | |
| - **Scales**: [384, 512, 768, 1024, 1280, 1536, 1792, 2048] | |
| - **Feature Dim**: 1280 | |
| - **Parameters**: 60,814,373 | |
| ### Training Configuration | |
| - **Dataset**: AbstractPhil/imagenet-clip-features-orderly | |
| - **Model Variant**: clip_vit_laion_bigg14 | |
| - **Epochs**: 10 | |
| - **Batch Size**: 1024 | |
| - **Learning Rate**: 0.001 | |
| - **Rose Loss Weight**: 0.1 β 0.5 | |
| - **Cayley Loss**: False | |
| ## Performance | |
| ### Best Results | |
| - **Validation Accuracy**: 83.66% | |
| - **Best Epoch**: 0 | |
| - **Final Train Accuracy**: 82.11% | |
| ### Per-Scale Performance | |
| - **Scale 384**: 83.27% | |
| - **Scale 512**: 83.31% | |
| - **Scale 768**: 83.59% | |
| - **Scale 1024**: 83.50% | |
| - **Scale 1280**: 83.66% | |
| - **Scale 1536**: 83.51% | |
| - **Scale 1792**: 83.40% | |
| - **Scale 2048**: 83.60% | |
| ## Usage | |
| ### Quick Model Lookup | |
| **Check `MODELS_INDEX.json` in the repo root** - it lists all trained models sorted by accuracy with links to weights and configs. | |
| ### Repository Structure | |
| ``` | |
| AbstractPhil/gated-david/ | |
| βββ MODELS_INDEX.json # π Master index of all models (sorted by accuracy) | |
| βββ README.md # This file | |
| βββ best_model.json # Latest best model info | |
| βββ weights/ | |
| β βββ david_clip_vit_bigg14/ | |
| β βββ 20251012_181608/ | |
| β βββ MODEL_SUMMARY.txt # π― Human-readable performance summary | |
| β βββ training_history.json # π Epoch-by-epoch training curve | |
| β βββ best_model_acc83.66.safetensors # β Accuracy in filename! | |
| β βββ best_model_acc83.66_metadata.json | |
| β βββ final_model.safetensors | |
| β βββ checkpoint_epoch_X_accYY.YY.safetensors | |
| β βββ david_config.json | |
| β βββ train_config.json | |
| βββ runs/ | |
| βββ david_clip_vit_bigg14/ | |
| βββ 20251012_181608/ | |
| βββ events.out.tfevents.* # TensorBoard logs | |
| ``` | |
| ### Loading the Model | |
| ```python | |
| from geovocab2.train.model.core.david import David, DavidArchitectureConfig | |
| from huggingface_hub import hf_hub_download | |
| # Browse available models in MODELS_INDEX.json first! | |
| # Specify model variant and run | |
| model_name = "david_clip_vit_bigg14" | |
| run_id = "20251012_181608" | |
| accuracy = "83.66" # From MODELS_INDEX.json | |
| # Download config | |
| config_path = hf_hub_download( | |
| repo_id="AbstractPhil/gated-david", | |
| filename=f"weights/{model_name}/{run_id}/david_config.json" | |
| ) | |
| config = DavidArchitectureConfig.from_json(config_path) | |
| # Download weights (accuracy in filename!) | |
| weights_path = hf_hub_download( | |
| repo_id="AbstractPhil/gated-david", | |
| filename=f"weights/{model_name}/{run_id}/best_model_acc{accuracy}.safetensors" | |
| ) | |
| # Download training history (optional - see full training curve) | |
| history_path = hf_hub_download( | |
| repo_id="AbstractPhil/gated-david", | |
| filename=f"weights/{model_name}/{run_id}/training_history.json" | |
| ) | |
| # Load model | |
| from safetensors.torch import load_file | |
| david = David.from_config(config) | |
| david.load_state_dict(load_file(weights_path)) | |
| david.eval() | |
| ``` | |
| ### Inference | |
| ```python | |
| import torch | |
| import torch.nn.functional as F | |
| # Assuming you have CLIP features (512-dim for ViT-B/16) | |
| features = get_clip_features(image) # [1, 512] | |
| # Load anchors | |
| anchors_dict = torch.load("anchors.pth") | |
| # Forward pass | |
| with torch.no_grad(): | |
| logits, _ = david(features, anchors_dict) | |
| predictions = logits.argmax(dim=-1) | |
| ``` | |
| ## Architecture Overview | |
| ### Multi-Scale Processing | |
| David processes inputs at multiple scales (384, 512, 768, 1024, 1280, 1536, 1792, 2048), | |
| allowing it to capture both coarse and fine-grained features. | |
| ### Crystal Geometry | |
| Each class is represented by a pentachoron (4-simplex) in embedding space with 5 vertices: | |
| - **Anchor**: Primary class representative | |
| - **Need**: Complementary direction | |
| - **Relation**: Contextual alignment | |
| - **Purpose**: Functional direction | |
| - **Observer**: Meta-perspective | |
| ### Rose Loss | |
| Similarity computation uses role-weighted cosine similarities: | |
| ``` | |
| score = w_anchor * sim(z, anchor) + w_need * sim(z, need) + ... | |
| ``` | |
| ### Fusion Strategy | |
| **deep_efficiency**: Intelligently combines predictions from multiple scales. | |
| ## Training Details | |
| ### Loss Components | |
| - **Cross-Entropy**: Standard classification loss | |
| - **Rose Loss**: Pentachora role-weighted margin loss (weight: 0.1β0.5) | |
| - **Cayley Loss**: Geometric regularization (disabled) | |
| ### Optimization | |
| - **Optimizer**: AdamW | |
| - **Weight Decay**: 1e-05 | |
| - **Scheduler**: cosine_restarts | |
| - **Gradient Clip**: 10.0 | |
| - **Mixed Precision**: False | |
| ## Citation | |
| ```bibtex | |
| @software{david_classifier_2025, | |
| title = {David: Multi-Scale Crystal Classifier}, | |
| author = {AbstractPhil}, | |
| year = {2025}, | |
| url = {https://huggingface.co/AbstractPhil/gated-david}, | |
| note = {Run ID: 20251012_181608} | |
| } | |
| ``` | |
| ## License | |
| MIT License | |
| ## Acknowledgments | |
| Built with crystal lattice geometry and multi-scale deep learning. | |
| Special thanks to Claude (Anthropic) for debugging assistance. | |
| --- | |
| *Generated on 2025-10-12 18:19:44* | |