beleata74 commited on
Commit
7f14eba
·
verified ·
1 Parent(s): ac9cae2

Upload saranet_fashion_mnist.py with huggingface_hub

Browse files
Files changed (1) hide show
  1. saranet_fashion_mnist.py +124 -0
saranet_fashion_mnist.py ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import torch
2
+ import torch.nn as nn
3
+ import torch.optim as optim
4
+ import torchvision
5
+ import torchvision.transforms as transforms
6
+ import time
7
+ import os
8
+
9
+ class SaraNetFashionBottleneck(nn.Module):
10
+ def __init__(self, in_features=784, out_features=10):
11
+ super().__init__()
12
+ self.input_layer = nn.Linear(in_features, 128)
13
+
14
+ # Обединени огледални матрици чрез групова 1D конволюция.
15
+ # Входът е 256 (128 плюсове + 128 минуси).
16
+ # groups=2 гарантира, че плюсовете се умножават само по първата половина тегла,
17
+ # а минусите - само по втората, БЕЗ да се бъркат!
18
+ self.mirror1 = nn.Conv1d(in_channels=256, out_channels=128, kernel_size=1, groups=2)
19
+
20
+ self.meeting_room = nn.Linear(128, 128)
21
+
22
+ # Същото за второто огледало
23
+ self.mirror2 = nn.Conv1d(in_channels=256, out_channels=128, kernel_size=1, groups=2)
24
+
25
+ self.judge = nn.Linear(128, out_features)
26
+
27
+ def forward(self, x):
28
+ x = x.view(x.size(0), -1)
29
+ z_in = self.input_layer(x)
30
+
31
+ # Огледало 1 (Оптимизация с ReLU и изваждане)
32
+ pos_signal1 = torch.relu(z_in)
33
+ neg_signal1 = z_in - pos_signal1
34
+ # Слепваме ги и добавяме 3-то измерение (за Conv1d) -> [batch, 256, 1]
35
+ combined_1 = torch.cat([pos_signal1, neg_signal1], dim=-1).unsqueeze(2)
36
+ # Резултатът е [batch, 128, 1], премахваме последното измерение
37
+ room_in = self.mirror1(combined_1).squeeze(2)
38
+
39
+ # Заседателна зала
40
+ z_room = self.meeting_room(room_in)
41
+
42
+ # Огледало 2 (Оптимизация с ReLU и изваждане)
43
+ pos_signal2 = torch.relu(z_room)
44
+ neg_signal2 = z_room - pos_signal2
45
+ combined_2 = torch.cat([pos_signal2, neg_signal2], dim=-1).unsqueeze(2)
46
+ m2_out = self.mirror2(combined_2).squeeze(2)
47
+
48
+ # Съдия
49
+ out = self.judge(m2_out)
50
+ return out
51
+
52
+ def run_experiment():
53
+ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
54
+ print(f"Устройство за обучение: {device}")
55
+
56
+ transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))])
57
+ data_path = os.path.join(os.path.dirname(__file__), 'data')
58
+
59
+ # Зареждаме данните веднъж
60
+ trainset = torchvision.datasets.FashionMNIST(root=data_path, train=True, download=True, transform=transform)
61
+ trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)
62
+
63
+ testset = torchvision.datasets.FashionMNIST(root=data_path, train=False, download=True, transform=transform)
64
+ testloader = torch.utils.data.DataLoader(testset, batch_size=64, shuffle=False)
65
+
66
+ num_runs = 10
67
+ epochs = 5
68
+ test_accuracies = []
69
+
70
+ print(f"Започваме {num_runs} независими тренировки на SaraNet Bottleneck (64->128->64) за по {epochs} епохи...")
71
+
72
+ start_total = time.time()
73
+
74
+ for run in range(num_runs):
75
+ seed = run + 42 # Различен seed за всеки рън
76
+ torch.manual_seed(seed)
77
+ if torch.cuda.is_available():
78
+ torch.cuda.manual_seed_all(seed)
79
+
80
+ model = SaraNetFashionBottleneck().to(device)
81
+ criterion = nn.CrossEntropyLoss()
82
+ optimizer = optim.Adam(model.parameters(), lr=0.001)
83
+
84
+ for epoch in range(epochs):
85
+ model.train()
86
+ for inputs, labels in trainloader:
87
+ inputs, labels = inputs.to(device), labels.to(device)
88
+ optimizer.zero_grad()
89
+ outputs = model(inputs)
90
+ loss = criterion(outputs, labels)
91
+ loss.backward()
92
+ optimizer.step()
93
+
94
+ # Тест след края на 5-те епохи
95
+ model.eval()
96
+ correct = 0
97
+ total = 0
98
+ with torch.no_grad():
99
+ for inputs, labels in testloader:
100
+ inputs, labels = inputs.to(device), labels.to(device)
101
+ outputs = model(inputs)
102
+ _, predicted = torch.max(outputs.data, 1)
103
+ total += labels.size(0)
104
+ correct += (predicted == labels).sum().item()
105
+
106
+ acc = 100 * correct / total
107
+ test_accuracies.append(acc)
108
+ print(f"Рън {run+1:02d}/{num_runs} (Seed: {seed}) -> Тестова точност: {acc:.2f}%")
109
+
110
+ avg_acc = sum(test_accuracies) / num_runs
111
+ max_acc = max(test_accuracies)
112
+ min_acc = min(test_accuracies)
113
+
114
+ total_time = time.time() - start_total
115
+
116
+ print("\n--- Финална статистика (10 ръна) ---")
117
+ print(f"Средна точност: {avg_acc:.2f}%")
118
+ print(f"Минимална точност: {min_acc:.2f}%")
119
+ print(f"Максимална точност: {max_acc:.2f}%")
120
+ print(f"Време за всички 10 ръна: {total_time:.1f} секунди")
121
+ print(f"Всички точности: {[round(a, 2) for a in test_accuracies]}")
122
+
123
+ if __name__ == "__main__":
124
+ run_experiment()