Eyüp İpler commited on
Commit
c5278fc
1 Parent(s): 589f8dc

Update Main Models/bai-2.1/README.md

Browse files
Files changed (1) hide show
  1. Main Models/bai-2.1/README.md +81 -42
Main Models/bai-2.1/README.md CHANGED
@@ -1,43 +1,82 @@
1
- # bai-2.1 (338787 parametre)
2
-
3
- ## EEG üzerinden duygu sınıflandırması yapan "bai-2.1" modeli, bir önceki model olan "bai-2.0" modeline göre overfitting ihtimali azaltılmış ve optimize edilmiş versiyonudur. Tüm işlevleri aynıdır.
4
-
5
- #### NOT: Gerçek zamanlı EEG veri takibi uygulamasına modeli entegre ederseniz, gerçek zamanlı olarak duygu tahmini yapabilmektedir. Uygulamaya erişebilmek için: https://github.com/neurazum/Realtime-EEG-Monitoring
6
-
7
- ## -----------------------------------------------------------------------------------
8
-
9
- # bai-2.1 (338787 parameters)
10
-
11
- ## The "bai-2.1" model, which performs emotion classification over EEG, is an optimised version of the previous model "bai-2.0" with reduced overfitting probability. All functions are the same.
12
-
13
- #### NOTE: If you integrate the model into a real-time EEG data tracking application, it can predict emotions in real time. To access the application: https://github.com/neurazum/Realtime-EEG-Monitoring
14
-
15
- **Doğruluk/Accuracy: %97.93621013133207**
16
-
17
- ## -----------------------------------------------------------------------------------
18
-
19
- # Kullanım / Usage:
20
-
21
- ```python
22
- import numpy as np
23
- import pandas as pd
24
- from sklearn.preprocessing import StandardScaler
25
- from tensorflow.keras.models import load_model
26
- import matplotlib.pyplot as plt
27
-
28
- model_path = 'model-path'
29
-
30
- model = load_model(model_path)
31
-
32
- model_name = model_path.split('/')[-1].split('.')[0]
33
-
34
- plt.figure(figsize=(10, 6))
35
- plt.title(f'Duygu Tahmini ({model_name}.1)')
36
- plt.xlabel('Zaman')
37
- plt.ylabel('Sınıf')
38
- plt.legend(loc='upper right')
39
- plt.grid(True)
40
- plt.show()
41
- model.summary()
42
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  ```
 
1
+ # bai-2.1 (338787 parametre)
2
+
3
+ ## EEG üzerinden duygu sınıflandırması yapan "bai-2.1" modeli, bir önceki model olan "bai-2.0" modeline göre overfitting ihtimali azaltılmış ve optimize edilmiş versiyonudur. Tüm işlevleri aynıdır.
4
+
5
+ #### NOT: Gerçek zamanlı EEG veri takibi uygulamasına modeli entegre ederseniz, gerçek zamanlı olarak duygu tahmini yapabilmektedir. Uygulamaya erişebilmek için: https://github.com/neurazum/Realtime-EEG-Monitoring
6
+
7
+ ## -----------------------------------------------------------------------------------
8
+
9
+ # bai-2.1 (338787 parameters)
10
+
11
+ ## The "bai-2.1" model, which performs emotion classification over EEG, is an optimised version of the previous model "bai-2.0" with reduced overfitting probability. All functions are the same.
12
+
13
+ #### NOTE: If you integrate the model into a real-time EEG data tracking application, it can predict emotions in real time. To access the application: https://github.com/neurazum/Realtime-EEG-Monitoring
14
+
15
+ **Doğruluk/Accuracy: %97.93621013133207**
16
+
17
+ ## -----------------------------------------------------------------------------------
18
+
19
+ # Kullanım / Usage
20
+
21
+ ```python
22
+ import numpy as np
23
+ import pandas as pd
24
+ from sklearn.preprocessing import StandardScaler
25
+ from tensorflow.keras.models import load_model
26
+ import matplotlib.pyplot as plt
27
+
28
+ model_path = 'model-path'
29
+
30
+ model = load_model(model_path)
31
+
32
+ model_name = model_path.split('/')[-1].split('.')[0]
33
+
34
+ plt.figure(figsize=(10, 6))
35
+ plt.title(f'Duygu Tahmini ({model_name}.1)')
36
+ plt.xlabel('Zaman')
37
+ plt.ylabel('Sınıf')
38
+ plt.legend(loc='upper right')
39
+ plt.grid(True)
40
+ plt.show()
41
+ model.summary()
42
+ ```
43
+
44
+ # Tahmin / Prediction
45
+
46
+ ```python
47
+ import numpy as np
48
+ import pandas as pd
49
+ from sklearn.preprocessing import StandardScaler
50
+ from tensorflow.keras.models import load_model
51
+
52
+ model_path = 'model-path'
53
+
54
+ model = load_model(model_path)
55
+
56
+ scaler = StandardScaler()
57
+
58
+ predictions = model.predict(X_new_reshaped)
59
+ predicted_labels = np.argmax(predictions, axis=1)
60
+
61
+ label_mapping = {'NEGATIVE': 0, 'NEUTRAL': 1, 'POSITIVE': 2}
62
+ label_mapping_reverse = {v: k for k, v in label_mapping.items()}
63
+
64
+ #new_input = np.array([[23, 465, 12, 9653] * 637])
65
+ new_input = np.random.rand(1, 2548) # 1 örnek ve 2548 özellik
66
+ new_input_scaled = scaler.fit_transform(new_input)
67
+ new_input_reshaped = new_input_scaled.reshape((new_input_scaled.shape[0], 1, new_input_scaled.shape[1]))
68
+
69
+ new_prediction = model.predict(new_input_reshaped)
70
+ predicted_label = np.argmax(new_prediction, axis=1)[0]
71
+ predicted_emotion = label_mapping_reverse[predicted_label]
72
+
73
+ if predicted_emotion == 'NEGATIVE':
74
+ predicted_emotion = 'Negatif'
75
+ elif predicted_emotion == 'NEUTRAL':
76
+ predicted_emotion = 'Nötr'
77
+ elif predicted_emotion == 'POSITIVE':
78
+ predicted_emotion = 'Pozitif'
79
+
80
+ print(f'Giriş Verileri: {new_input}')
81
+ print(f'Tahmin Edilen Duygu: {predicted_emotion}')
82
  ```