Alif Al Hasan
commited on
Commit
·
5e9d5a8
1
Parent(s):
b3c1899
[Task] Updated README
Browse files[Description] Added model card feature.
[Author]
@alifalhasan
README.md
CHANGED
@@ -10,6 +10,52 @@ pinned: false
|
|
10 |
license: mit
|
11 |
---
|
12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
# Top 5 EPL Teams' Emblem Identifier
|
14 |
A simple and well designed web app to identify the emblem of the top 5 teams of **EPL(English Premier League)** namely **Arsenal, Chelsea, Liverpool, Manchester City** and **Manchester United**.
|
15 |
|
|
|
10 |
license: mit
|
11 |
---
|
12 |
|
13 |
+
# Model Card
|
14 |
+
|
15 |
+
## Overview
|
16 |
+
|
17 |
+
- **Model name:** Top 5 EPL Teams' Emblem Identifier
|
18 |
+
- **Model description:** Identifies the emblem of the top 5 English Premier League (EPL) teams from images using a convolutional neural network (CNN).
|
19 |
+
- **Authors:** Alif Al Hasan
|
20 |
+
- **Repository link:** https://huggingface.co/spaces/alifalhasan/deep-learning-1
|
21 |
+
- **License:** MIT
|
22 |
+
- **Contact information:** [email protected]
|
23 |
+
|
24 |
+
## Performance
|
25 |
+
|
26 |
+
- **Metrics:** Accuracy (100%)
|
27 |
+
- **Dataset:** Approximately 5,000 images of EPL team emblems, balanced across classes. Sources and preprocessing steps described in detail further below.
|
28 |
+
|
29 |
+
## Data
|
30 |
+
|
31 |
+
- **Training data:**
|
32 |
+
- Size: 5,000 images
|
33 |
+
- Class distribution: Balanced (1,000 images per class)
|
34 |
+
- Sources: [English Premier League Logo Detection](https://www.kaggle.com/datasets/alexteboul/english-premier-league-logo-detection-20k-images)
|
35 |
+
- Preprocessing: Resizing to 224x224 pixels, normalization
|
36 |
+
- **Potential biases:** Currently unknown biases in the dataset.
|
37 |
+
|
38 |
+
## Inference
|
39 |
+
|
40 |
+
- **Input:**
|
41 |
+
- Format: JPEG or PNG images
|
42 |
+
- Size: 224x224 pixels
|
43 |
+
- Color space: RGB
|
44 |
+
- **Output:** Predicted class probabilities for each of the 5 EPL teams.
|
45 |
+
- **Usage instructions:** See the "How To Run" section below for detailed instructions.
|
46 |
+
|
47 |
+
## Ethics
|
48 |
+
|
49 |
+
- **Potential biases:** The model may inherit biases from the training data, such as over- or under-representation of certain team emblems.
|
50 |
+
- **Mitigation strategies:** Further exploration of dataset biases and potential augmentation techniques to address them.
|
51 |
+
- **Ethical considerations:**
|
52 |
+
- Awareness of potential biases and limitations in the model's predictions.
|
53 |
+
- Responsible use of the model, avoiding harmful generalizations or discrimination.
|
54 |
+
- Respect for the rights and privacy of individuals and organizations associated with the EPL teams.
|
55 |
+
|
56 |
+
---
|
57 |
+
|
58 |
+
|
59 |
# Top 5 EPL Teams' Emblem Identifier
|
60 |
A simple and well designed web app to identify the emblem of the top 5 teams of **EPL(English Premier League)** namely **Arsenal, Chelsea, Liverpool, Manchester City** and **Manchester United**.
|
61 |
|