1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
|
import torch, torch.nn as nn
from torchvision.datasets import MNIST
from torch.utils.data import DataLoader
from torchvision import transforms
class MNIST_MLP(nn.Module):
def __init__(self, hidden_dim):
super().__init__()
self.layers = nn.Sequential(
nn.Flatten(),
nn.Linear(28 * 28, hidden_dim),
nn.ReLU(),
nn.Linear(hidden_dim, 10),
)
def forward(self, x):
return self.layers(x)
train_dataset = MNIST('./', download=True, transform=transforms.ToTensor(), train=True)
trainloader = DataLoader(train_dataset, batch_size=128, shuffle=True)
def train_model(name: str, dim):
net = MNIST_MLP(hidden_dim=dim)
loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(net.parameters(), lr=0.5e-4)
print(f"Training {name} ({dim} neurons)...")
for epoch in range(10):
global loss
for data in trainloader:
inputs, targets = data
optimizer.zero_grad()
outputs = net(inputs)
loss = loss_fn(outputs, targets)
loss.backward()
optimizer.step()
print(f" Epoch {epoch+1}, Loss: {loss.item():.4f}")
return net
if __name__ == "__main__":
torch_net_a = train_model("Network A", 6).eval()
torch_net_b = train_model("Network B", 12).eval()
torch.onnx.export(torch_net_a, (torch.randn(1, 28, 28),), "mnist_a.onnx")
torch.onnx.export(torch_net_b, (torch.randn(1, 28, 28),), "mnist_b.onnx")
|
