Pytorch

 

✅ Pytorch

 

✅ Pytorch를 활용해야 하는 이유

import torch

from torch import nn
fromtorch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor

# 공개 데이터 셋에서 학습 데이터를 내려 받습니다.

training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor(),
)

# 공개 데이터 셋에서 테스트 데이터를 내려 받습니다.

test_data = datasets.FashionMNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor(),
)

batch_size = 64

# 데이터 로더를 생성합니다.
train_dataloader = DataLoader(training_data, batch_size=batch_size)
test_dataloader = DataLoader(test_data, batch_size=batch_size)

for X, y in test_dataloader:
    print(f"Shape of X [N, C, H, W] : {X.shape}")
    print(f"Shape of y : {y.shape} {y.dtype}")
    break

# 학습에 사용할 CPU나 GPU, MPS 장치를 얻습니다.
device = (
    "cuda"
    if torch.cuda.is_available()
    else "mps"
    if torch.backends.mps.is_available()
    else "cpu"
)
print(f"Using {device} device")

# 모델을 정의합니다.
class NeuralNetwork(nn.Module):
    def __init__(self):
        super().__init__()
        self.flatten = nn.Flatten() # 1차원 형태로 변경
        self.linear_relu_stack = nn.Sequential(
            nn.Linear(28*28, 512),
            nn.ReLU(),
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, 10),
            nn.ReLU()
        )

    def forward(self, x):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

model = NeuralNetwork().to(device)

print(model)

loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    model.train()
    for batch, (X, y) in enumerate(dataloader): # enumerate -> 인덱스가 같이 사용
        X, y = X.to(device), y.to(device)

        # 예측 오류 계산
        pred = model(X)
        loss = loss_fn(pred, y)

        # 역전파
        loss.backward()
        optimizer.step()
        optimizer.zero_grad()

        if batch % 100 == 0:
            loss, current = loss.item(), (batch + 1) * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")

def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)

    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 /= num_batches
    correct /= size

    print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")

epochs = 5

for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")

    train(train_dataloader, model, loss_fn, optimizer)
    test(test_dataloader, model, loss_fn)

print("Done!")

torch.save(model.state_dict(), "model.pth") # 확장자 -> pth, model -> 파일 이름

print("Saved PyTorch Model State to model.pth")

model = NeuralNetwork().to(device)

model.load_state_dict(torch.load("model.pth"))

classes = [
    "T-shirt/top",
    "Trouser",
    "Pullover",
    "Dress",
    "Coat",
    "Sandal",
    "Shirt",
    "Sneaker",
    "Bag",
    "Ankle boot",
]

model.eval()

x, y = test_data[0][0], test_data[0][1]

with torch.no_grad():
    x = x.to(device)
    pred = model(x)

    predicted, actual = classes[pred[0].argmax(0)], classes[y]

    print(f'Predicted: "{predicted}", Actual: "{actual}"')

 

 

import torch
import numpy as np

 

data = [[1, 2], [3, 4]]
x_data = torch.tensor(data)

print(data)

np_array = np.array(data) # type이 ndarray
x_np = torch.from_numpy(np_array) # type이 tensor

print(type(x_np))

x_ones = torch.ones_like(x_data) # x_data의 속성을 유지합니다.

print(f"Ones Tensor: \n {x_ones} \n")

x_rand = torch.rand_like(x_data, dtype=torch.float) # x_data의 속성을 덮어씁니다.

print(f"Random Tensor: \n {x_rand} \n")

shape = (2, 3,)

rand_tensor = torch.rand(shape)
ones_tensor = torch.ones(shape)
zeros_tensor = torch.zeros(shape)

print(f"Random Tensor: \n {rand_tensor} \n")
print(f"Ones Tensor: \n {ones_tensor} \n")
print(f"Zeros Tensor: \n {zeros_tensor}")

tensor = torch.rand(3, 4)

print(f"Shape of tensor: {tensor.shape}")
print(f"Datatype of tensor: {tensor.dtype}")
print(f"Device tensor is stored on: {tensor.device}")

# GPU가 존재하면 텐서를 이동합니다

if torch.cuda.is_available():
    tensor = tensor.to("cuda")
print(tensor.dtype)

tensor = torch.ones(4, 4)

print(f"First row: {tensor[0]}")
print(f"First column: {tensor[:, 0]}")
print(f"Last column: {tensor[..., -1]}")

tensor[:,1] = 0

print(tensor)

t1 = torch.cat([tensor, tensor, tensor], dim=0) # dim = 1 -> 가로, 0 -> 세로

print(t1.shape)

 

# 두 텐서 간의 행렬 곱(matrix multiplication)을 계산합니다. y1, y2, y3은 모두 같은 값을 갖습니다.
# ``tesnsor.T``는 텐서의 전치(transpose)를 반환합니다.

y1 = tensor @ tensor.T # M*N N*M => M * M(정사각형)
y2 = tensor.matmul(tensor.T)
y3 = torch.rand_like(y1)

torch.matmul(tensor, tensor.T, out=y3)

# 요소별 곱(element-wise product)을 계산합니다. z1, z2, z3는 모두 같은 값을 갖습니다.

z1 = tensor * tensor
z2 = tensor.mul(tensor)
z3 = torch.rand_like(tensor)

torch.mul(tensor, tensor, out=z3)

agg = tensor.sum()

# print(agg)

agg_item = agg.item()

print(agg_item, type(agg_item))

print(f"{tensor} \n")

tensor.add_(5)

print(tensor)

t = torch.ones(5)

print(f"t: {t}")

n = t.numpy()

print(f"n: {n}")

t.add_(1)

print(f"t: {t}")
print(f"n: {n}")

n = np.ones(5)

t = torch.from_numpy(n)

import torch
import matplotlib.pyplot as plt

from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor

training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor(),
)

test_data = datasets.FashionMNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor(),
)

labels_map = {
    0: "T-Shirt",
    1: "Trouser",
    2: "Pullover",
    3: "Dress",
    4: "Coat",
    5: "Sandal",
    6: "Shirt",
    7: "Sneaker",
    8: "Bag",
    9: "Ankle Boot",
}

figure = plt.figure(figsize=(8, 8))
cols, rows = 3, 3

for i in range(1, cols * rows + 1):
    sample_idx = torch.randint(len(training_data), size=(1,)).item()
    img, label = training_data[sample_idx]

    figure.add_subplot(rows, cols, i)

    plt.title(labels_map[label])
    plt.axis("off")
    plt.imshow(img.squeeze(), cmap="gray")

plt.show()

import os
import pandas as pd

from torchvision.io import read_image

class CustomImageDataset(Dataset):
    def __init__(self, annotations_file, img_dir, transform=None, target_transform=None):
        self.img_labels = pd.read_csv(annotations_file, names=['file_name', 'label'])
        self.img_dir = img_dir

        self.transform = transform

        self.target_transform = target_transform

    def __len__(self):
        return len(self.img_labels)

    def __getitem__(self, idx):
        img_path = os.path.join(self.img_dir, self.img_labels.iloc[idx, 0])

        image = read_image(img_path)

        label = self.img_labels.iloc[idx, 1]

        if self.transform:
            image = self.transform(image)

        if self.target_transform:
            label = self.target_transform(label)
            
        return image, label

def __init__(self, annotations_file, img_dir, transform=None, target_transform=None):
    self.img_labels = pd.read_csv(annotations_file)
    self.img_dir = img_dir
    self.transform = transform
    self.target_transform = target_transform

def __len__(self):
    return len(self.img_labels)

def __getitem__(self, idx):
    img_path = os.path.join(self.img_dir, self.img_labels.iloc[idx, 0])
    image = read_image(img_path)
    label = self.img_labels.iloc[idx, 1]
    if self.transform:
        image = self.transform(image)
    if self.target_transform:
        label = self.target_transform(label)
    sample = {"image": image, "label": label}
    return sample

from torch.utils.data import DataLoader

train_dataloader = DataLoader(training_data, batch_size=64, shuffle=True)
test_dataloader = DataLoader(test_data, batch_size=64, shuffle=False)

# 이미지와 정답(label)을 표시합니다.

train_features, train_labels = next(iter(train_dataloader))

print(f"Feature batch shape: {train_features.size()}")
print(f"Labels batch shape: {train_labels.size()}")

img = train_features[0].squeeze()

label = train_labels[0]

plt.imshow(img, cmap="gray")
plt.show()

print(f"Label: {label}")