Upload folder using huggingface_hub

README.md

@@ -8,24 +8,24 @@ This model recognizes sign language gestures using landmark data from hand, pose
 - **Framework**: TensorFlow/Keras
 - **Input**: Landmark sequences (x, y, z coordinates)
 - **Output**: Sign language class predictions
-- **Classes**: {processor.sign_count} different signs
-- **Parameters**: {model.count_params():,}
+- **Classes**: 60 different signs
+- **Parameters**: 1763418
 
 ## Model Architecture
 
-- **Input Shape**: {model.input_shape}
-- **Output Shape**: {model.output_shape}
-- **Max Sequence Length**: {config.max_len}
-- **Embedding Dimension**: {config.dim}
+- **Input Shape**: (,384,708)
+- **Output Shape**: (,60)
+- **Max Sequence Length**: (384)
+- **Embedding Dimension**: (192)
 
 ## Training Details
 
-- **Epochs**: {config.epoch}
-- **Batch Size**: {config.batch_size}
-- **Learning Rate**: {config.lr}
-- **Weight Decay**: {config.weight_decay}
-- **Best Validation Loss**: {min(history.history['val_loss']):.4f}
-- **Best Validation Accuracy**: {max(history.history['val_accuracy']):.4f}
+- **Epochs**: 69
+- **Batch Size**: 32
+- **Learning Rate**: 0.0005
+- **Weight Decay**: 0.1
+- **Best Validation Loss**: 3.1850430965423584
+- **Best Validation Accuracy**: 0.25550660490989685
 
 ## Usage
 
@@ -59,4 +59,8 @@ predicted_classes = np.argmax(predictions, axis=1)
 
 ## Requirements
 
-See `requirements.txt` for the complete list of dependencies.
+See `requirements.txt` for the complete list of dependencies.
+
+## Training Notebook
+
+The training notebook will be provided in future updates