1
0
Fork 0
This repository has been archived on 2024-02-17. You can view files and clone it, but cannot push or open issues or pull requests.
TP_IA/main.py

126 lines
3.4 KiB
Python

from os.path import isfile
import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor
device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Using {device} device")
def get_data(batch_size: int = 64):
# Download training data from open datasets.
training_data = datasets.CIFAR10(
root="/home/flifloo/IA/data",
train=True,
download=True,
transform=ToTensor(),
)
# Download test data from open datasets.
testing_data = datasets.CIFAR10(
root="/home/flifloo/IA/data",
train=False,
download=True,
transform=ToTensor(),
)
# Create data loaders.
train_dataloader = DataLoader(training_data, batch_size=batch_size, shuffle=True)
test_dataloader = DataLoader(testing_data, batch_size=batch_size, shuffle=True)
return train_dataloader, test_dataloader
# Define model
class NeuralNetwork(nn.Module):
def __init__(self):
super(NeuralNetwork, self).__init__()
self.conv_relu_stack = nn.Sequential(
nn.Conv2d(3, 6, (5, 5)),
nn.MaxPool2d(2, 2),
nn.ReLU(),
nn.Conv2d(6, 16, (5, 5)),
nn.MaxPool2d(2, 2),
nn.ReLU(),
)
self.linear_relu_stack = nn.Sequential(
nn.Linear(16*(5**2), 120),
nn.ReLU(),
nn.Linear(120, 84),
nn.ReLU(),
nn.Linear(84, 10),
nn.ReLU(),
)
def forward(self, x):
x = self.conv_relu_stack(x)
x = x.view(-1, 16 * 5 * 5)
return self.linear_relu_stack(x)
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset)
for batch, (X, y) in enumerate(dataloader):
X, y = X.to(device), y.to(device)
# Compute prediction error
pred = model(X)
loss = loss_fn(pred, y)
# Backpropagation
optimizer.zero_grad()
loss.backward()
optimizer.step()
if batch % 100 == 0:
loss, current = loss.item(), batch * len(X)
print(f"loss: {loss:>7f} [{current:>5d}/{size:>5d}]")
def test(dataloader, model, loss_fn):
size = len(dataloader.dataset)
model.eval()
test_loss, correct = 0, 0
with torch.no_grad():
for X, y in dataloader:
X, y = X.to(device), y.to(device)
pred = model(X)
test_loss += loss_fn(pred, y).item()
correct += (pred.argmax(1) == y).type(torch.float).sum().item()
test_loss /= size
correct /= size
print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")
return correct
def training():
train_data, test_data = get_data()
model = NeuralNetwork().to(device)
if isfile("model.pth"):
print("Loading model from save")
model.load_state_dict(torch.load("model.pth"))
print(model)
loss_fn = nn.CrossEntropyLoss()
# lr = sur/sous appretisage
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3, momentum=.9)
e = 0
c = 0
while c < 0.90:
print(f"Epoch {e+1}\n-------------------------------")
train(train_data, model, loss_fn, optimizer)
c = test(test_data, model, loss_fn)
torch.save(model.state_dict(), "model.pth")
e += 1
print("Done!")
if __name__ == '__main__':
training()