Image Classification
Keras
LiteRT
TF-Keras
Safetensors
English
efficientnetv2-s
efficientnetv2
fgic
transfer-learning
gem-pooling
focal-loss
swa
grad-cam
calibration
temperature-scaling
computer-vision
tensorflow.js
Eval Results (legacy)
Instructions to use 0xgr3y/Arch-Building-Image-Classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use 0xgr3y/Arch-Building-Image-Classification with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://0xgr3y/Arch-Building-Image-Classification") - Notebooks
- Google Colab
- Kaggle
Fix: dataset ref 0xgr3y, add GitHub link, update Files table
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ tags:
|
|
| 16 |
library_name: keras
|
| 17 |
language: en
|
| 18 |
datasets:
|
| 19 |
-
-
|
| 20 |
widget:
|
| 21 |
- structure:
|
| 22 |
src: https://cdn-uploads.huggingface.co/production/uploads/66cdac913f233bf2c7b4f590/HzXxNze2jmCkV5KPY_fpQ.png
|
|
@@ -122,6 +122,10 @@ Output (6 classes)
|
|
| 122 |
|------|-------------|
|
| 123 |
| `best_phase2_swa.keras` | Best model — SWA averaged weights (val_acc=95.93%) |
|
| 124 |
| `best_phase2.keras` | Phase 2 checkpoint (val_acc=93.35%) |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 125 |
| `config.json` | Full model configuration and evaluation metrics |
|
| 126 |
| `label_mapping.json` | Class name <-> ID mapping |
|
| 127 |
| `preprocessor_config.json` | Input preprocessing specification |
|
|
@@ -173,6 +177,12 @@ preds = model.predict(arr, verbose=0)[0]
|
|
| 173 |
print(f"Predicted: {LABELS[np.argmax(preds)]} ({np.max(preds)*100:.1f}%)")
|
| 174 |
```
|
| 175 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 176 |
## Intended Use
|
| 177 |
|
| 178 |
- Architectural style classification from building photographs
|
|
|
|
| 16 |
library_name: keras
|
| 17 |
language: en
|
| 18 |
datasets:
|
| 19 |
+
- 0xgr3y/arch-building-dataset
|
| 20 |
widget:
|
| 21 |
- structure:
|
| 22 |
src: https://cdn-uploads.huggingface.co/production/uploads/66cdac913f233bf2c7b4f590/HzXxNze2jmCkV5KPY_fpQ.png
|
|
|
|
| 122 |
|------|-------------|
|
| 123 |
| `best_phase2_swa.keras` | Best model — SWA averaged weights (val_acc=95.93%) |
|
| 124 |
| `best_phase2.keras` | Phase 2 checkpoint (val_acc=93.35%) |
|
| 125 |
+
| `saved_model/` | TensorFlow SavedModel format (portable, for TF Serving) |
|
| 126 |
+
| `tflite/model.tflite` | TensorFlow Lite model (mobile/embedded) |
|
| 127 |
+
| `tflite/label.txt` | Class label names for TF-Lite |
|
| 128 |
+
| `tfjs_model/` | TensorFlow.js model (browser) |
|
| 129 |
| `config.json` | Full model configuration and evaluation metrics |
|
| 130 |
| `label_mapping.json` | Class name <-> ID mapping |
|
| 131 |
| `preprocessor_config.json` | Input preprocessing specification |
|
|
|
|
| 177 |
print(f"Predicted: {LABELS[np.argmax(preds)]} ({np.max(preds)*100:.1f}%)")
|
| 178 |
```
|
| 179 |
|
| 180 |
+
## Links
|
| 181 |
+
|
| 182 |
+
- **Gradio Demo:** [arch-building-classifier Space](https://huggingface.co/spaces/0xgr3y/arch-building-classifier)
|
| 183 |
+
- **Dataset:** [0xgr3y/arch-building-dataset](https://huggingface.co/datasets/0xgr3y/arch-building-dataset)
|
| 184 |
+
- **GitHub:** [arcxteam/arch-building-classifier](https://github.com/arcxteam/arch-building-classifier)
|
| 185 |
+
|
| 186 |
## Intended Use
|
| 187 |
|
| 188 |
- Architectural style classification from building photographs
|