Update README.md

README.md

@@ -15,11 +15,11 @@ pipeline_tag: object-detection
 # Yolo11n Sea Urchin Detector
 
 ## Model Details / Overview
-This model was trained to detect sea urchins using the YOLO11 architecture. It leverages data from multiple open datasets to identify and locate urchins in various underwater images.
+This model was trained to detect sea urchins using the YOLO11 architecture. Trained on open datasets to identify and locate urchins in various underwater conditions.
 
 - **Model Architecture**: YOLO11n
 - **Task**: Object Detection (Urchin Detection)
-- **Footage Type**: Underwater Footage (Color and Grayscale)
+- **Footage Type**: Underwater Footage
 - **Classes**: 1 (urchin)
 
 ## Test Results
@@ -40,10 +40,10 @@ The model's weights can be found [here](./yolo11n_urchin_trained.pt) | Also avai
 
 # Factors
 ### Model Performance 
-- Multi-source Dataset: Trained on datasets that include color and urchin images from various angles, enabling the model to perform effectively across different visual inputs.
+- Multi-source Dataset: Trained on datasets that include urchin images from various angles.
 - Model Architecture (YOLO11n): Lightweight and optimized for real-time urchin detection in underwater footage.
-- Training Data: The dataset includes a mix of color and grayscale images, split into 70% training, 20% validation, and 10% test data.
-- Training Parameters: Configured with 50 epochs, a 0.001 learning rate, and 640x640 image size for optimal model convergence.
+- Training Data: The dataset is split into 70% training, 20% validation, and 10% test data.
+- Training Parameters: Configured with 50 epochs, a 0.001 learning rate, and 640x640 image size for convergence.
 
 ## Datasets
 The training data was collected, parsed and organized from open sources: