rhdang commited on
Commit
e9b94c6
·
verified ·
1 Parent(s): 2fe881c

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +36 -0
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## Friend Facial Recognition Model Card
2
+
3
+ # Model Description
4
+
5
+ The Friend Facial Recognition model is a convolutional neural network (CNN) designed to recognize friends in images. The model is trained using Python and utilizes the Discord bot integration for real-time image prediction within Discord.
6
+
7
+ # Model Details
8
+
9
+ - **Input Format**: RGB images with dimensions 300x350 pixels.
10
+ - **Output Format**: Predicted class label (e.g., friend's name).
11
+ - **Training Data**: Labeled images of friends organized into appropriate directories for different classes.
12
+ - **Training Procedure**: The model is trained using the RMSprop optimizer with a learning rate of 1e-5 for 50 epochs.
13
+
14
+ # Performance Metrics
15
+
16
+ - **Accuracy**: Achieves an accuracy of approximately 90% on a validation dataset.
17
+
18
+ # Use Cases
19
+
20
+ - Recognizing friends in images shared within Discord channels or servers.
21
+ - Personal project or hobby use for fun and entertainment purposes.
22
+
23
+ # Ethical Considerations
24
+
25
+ - **Biases**: The model's performance may be influenced by biases in the training data, potentially leading to differential accuracy across different demographic groups.
26
+ - **Fairness**: Ensure fairness in model predictions and mitigate any unintended biases by regularly monitoring and evaluating model performance across diverse datasets.
27
+ - **Privacy**: Respect the privacy of individuals by obtaining consent before using their images for training or testing the model.
28
+
29
+ # Limitations
30
+
31
+ - The model's performance may degrade when presented with images containing multiple individuals or poor lighting conditions.
32
+ - Limited to recognizing only a predefined set of friends for whom the model has been trained.
33
+
34
+ # License
35
+
36
+ This model is licensed under the [MIT License](LICENSE).