Try run PyTorch Quickstart demo

博主： YiYu
发布时间：2024 年 05 月 05 日
600 次浏览
2 条评论
11663字数
分类： AI

Learn AI 系列文章：
[1. Setup ubuntu server 20.04 for machine learning](https://www.helloyiyu.com/index.php/ai/28.html)
[2. Try run PyTorch Quickstart demo](https://www.helloyiyu.com/index.php/ai/32.html)
[3. 使用Ollama和OpenWebUI本地运行llama3大语言模型](https://www.helloyiyu.com/index.php/ai/39.html)

---

关于PyTorch的资料：

[datawhalechina/thorough-pytorch: PyTorch入门教程，在线阅读地址：https://datawhalechina.github.io/thorough-pytorch/](https://github.com/datawhalechina/thorough-pytorch)

---

参考官网文档：[Quickstart — PyTorch Tutorials 2.3.0+cu121 documentation](https://pytorch.org/tutorials/beginner/basics/quickstart_tutorial.html)
在本地Ubuntu Server 20.04 环境中跑一下pytorch quickstart demo code。

### Working with data

PyTorch has two [primitives to work with data](https://pytorch.org/docs/stable/data.html): `torch.utils.data.DataLoader` and `torch.utils.data.Dataset`. `Dataset` stores the samples and their corresponding labels, and `DataLoader` wraps an iterable around the `Dataset`.

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

PyTorch offers domain-specific libraries such as [TorchText](https://pytorch.org/text/stable/index.html), [TorchVision](https://pytorch.org/vision/stable/index.html), and [TorchAudio](https://pytorch.org/audio/stable/index.html), all of which include datasets. For this tutorial, we will be using a TorchVision dataset.

The `torchvision.datasets` module contains `Dataset` objects for many real-world vision data like CIFAR, COCO ([full list here](https://pytorch.org/vision/stable/datasets.html)). In this tutorial, we use the FashionMNIST dataset. Every TorchVision `Dataset` includes two arguments: `transform` and `target_transform` to modify the samples and labels respectively.

**Note**: 这一步下载速度可能很慢，可以直接通过浏览器从[fashion-mnist · GitHub](https://github.com/zalandoresearch/fashion-mnist/tree/master/data/fashion)将`train-images-idx3-ubyte.gz`和`t10k-images-idx3-ubyte.gz`下载到本地，然后上传到{jupyter_root_dir}/data/FashionMNIST/raw/，然后再执行下面这段code。

```python
# Download training data from open datasets.
training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor(),
)

# Download test data from open datasets.
test_data = datasets.FashionMNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor(),
)
```

```
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz
Using downloaded and verified file: data/FashionMNIST/raw/train-images-idx3-ubyte.gz
Extracting data/FashionMNIST/raw/train-images-idx3-ubyte.gz to data/FashionMNIST/raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to data/FashionMNIST/raw/train-labels-idx1-ubyte.gz

100.0%

Extracting data/FashionMNIST/raw/train-labels-idx1-ubyte.gz to data/FashionMNIST/raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz
Using downloaded and verified file: data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz
Extracting data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz to data/FashionMNIST/raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz

100.0%

Extracting data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw
```

We pass the `Dataset` as an argument to `DataLoader`. This wraps an iterable over our dataset, and supports automatic batching, sampling, shuffling and multiprocess data loading. Here we define a batch size of 64, i.e. each element in the dataloader iterable will return a batch of 64 features and labels.

```python
batch_size = 64

# Create data loaders.
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
```

```
Shape of X [N, C, H, W]: torch.Size([64, 1, 28, 28])
Shape of y: torch.Size([64]) torch.int64
```

Read more about [loading data in PyTorch](data_tutorial.html).

---

### Creating Models

To define a neural network in PyTorch, we create a class that inherits from [nn.Module](https://pytorch.org/docs/stable/generated/torch.nn.Module.html). We define the layers of the network in the `__init__` function and specify how data will pass through the network in the `forward` function. To accelerate operations in the neural network, we move it to the GPU or MPS if available.

```python
# Get cpu, gpu or mps device for training.
device = (
    "cuda"
    if torch.cuda.is_available()
    else "mps"
    if torch.backends.mps.is_available()
    else "cpu"
)
print(f"Using {device} device")

# Define model
class NeuralNetwork(nn.Module):
    def __init__(self):
        super().__init__()
        self.flatten = nn.Flatten()
        self.linear_relu_stack = nn.Sequential(
            nn.Linear(28*28, 512),
            nn.ReLU(),
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, 10)
        )

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

model = NeuralNetwork().to(device)
print(model)
```

```
Using cpu device
NeuralNetwork(
  (flatten): Flatten(start_dim=1, end_dim=-1)
  (linear_relu_stack): Sequential(
    (0): Linear(in_features=784, out_features=512, bias=True)
    (1): ReLU()
    (2): Linear(in_features=512, out_features=512, bias=True)
    (3): ReLU()
    (4): Linear(in_features=512, out_features=10, bias=True)
  )
)
```

Read more about [building neural networks in PyTorch](buildmodel_tutorial.html).

---

### Optimizing the Model Parameters

To train a model, we need a [loss function](https://pytorch.org/docs/stable/nn.html#loss-functions) and an [optimizer](https://pytorch.org/docs/stable/optim.html).

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

In a single training loop, the model makes predictions on the training dataset (fed to it in batches), and backpropagates the prediction error to adjust the model's parameters.

```python
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    model.train()
    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
        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}]")
```

We also check the model's performance against the test dataset to ensure it is learning.

```python
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")
```

The training process is conducted over several iterations (*epochs*). During each epoch, the model learns parameters to make better predictions. We print the model's accuracy and loss at each epoch; we'd like to see the accuracy increase and the loss decrease with every epoch.

```python
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!")
```

```
Epoch 1
-------------------------------
loss: 2.289245  [   64/60000]
loss: 2.280316  [ 6464/60000]
loss: 2.262248  [12864/60000]
loss: 2.266677  [19264/60000]
loss: 2.236694  [25664/60000]
loss: 2.220209  [32064/60000]
loss: 2.223473  [38464/60000]
loss: 2.185845  [44864/60000]
loss: 2.181429  [51264/60000]
loss: 2.156792  [57664/60000]
Test Error: 
 Accuracy: 41.9%, Avg loss: 2.140304

Epoch 2
-------------------------------
loss: 2.141585  [   64/60000]
loss: 2.131078  [ 6464/60000]
loss: 2.075279  [12864/60000]
loss: 2.101078  [19264/60000]
loss: 2.023978  [25664/60000]
loss: 1.982755  [32064/60000]
loss: 2.003413  [38464/60000]
loss: 1.913837  [44864/60000]
loss: 1.920139  [51264/60000]
loss: 1.854348  [57664/60000]
Test Error: 
 Accuracy: 57.2%, Avg loss: 1.844530

Epoch 3
-------------------------------
loss: 1.865049  [   64/60000]
loss: 1.838099  [ 6464/60000]
loss: 1.725792  [12864/60000]
loss: 1.779518  [19264/60000]
loss: 1.646965  [25664/60000]
loss: 1.620810  [32064/60000]
loss: 1.635814  [38464/60000]
loss: 1.534571  [44864/60000]
loss: 1.559003  [51264/60000]
loss: 1.463222  [57664/60000]
Test Error: 
 Accuracy: 61.6%, Avg loss: 1.481398

Epoch 4
-------------------------------
loss: 1.534660  [   64/60000]
loss: 1.510708  [ 6464/60000]
loss: 1.369240  [12864/60000]
loss: 1.450706  [19264/60000]
loss: 1.320927  [25664/60000]
loss: 1.332666  [32064/60000]
loss: 1.338850  [38464/60000]
loss: 1.266171  [44864/60000]
loss: 1.298449  [51264/60000]
loss: 1.206169  [57664/60000]
Test Error: 
 Accuracy: 63.3%, Avg loss: 1.232588

Epoch 5
-------------------------------
loss: 1.298163  [   64/60000]
loss: 1.289273  [ 6464/60000]
loss: 1.130808  [12864/60000]
loss: 1.241744  [19264/60000]
loss: 1.112488  [25664/60000]
loss: 1.146212  [32064/60000]
loss: 1.159560  [38464/60000]
loss: 1.099317  [44864/60000]
loss: 1.136193  [51264/60000]
loss: 1.057784  [57664/60000]
Test Error: 
 Accuracy: 64.8%, Avg loss: 1.077425

Done!
```

Read more about [Training your model](optimization_tutorial.html).

---

### Saving Models

A common way to save a model is to serialize the internal state dictionary (containing the model parameters).

```python
torch.save(model.state_dict(), "model.pth")
print("Saved PyTorch Model State to model.pth")
```

```
Saved PyTorch Model State to model.pth
```

---

### Loading Models

The process for loading a model includes re-creating the model structure and loading the state dictionary into it.

```python
model = NeuralNetwork().to(device)
model.load_state_dict(torch.load("model.pth"))
```

```
<All keys matched successfully>
```

This model can now be used to make predictions.

```python
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}"')
```

```
Predicted: "Ankle boot", Actual: "Ankle boot"
```

最后修改：2024 年 05 月 08 日

如果觉得我的文章对你有用，请随意赞赏

发表评论
使用cookie技术保留您的个人信息以便您下次快速评论，继续评论表示您已同意该条款

评论 *

私密评论

名称 *

🎲

邮箱

地址

Try run PyTorch Quickstart demo

YiYu • 2024 年 05 月 05 日

---

关于PyTorch的资料：

[datawhalechina/thorough-pytorch: PyTorch入门教程，在线阅读地址：https://datawhalechina.github.io/thorough-pytorch/](https://github.com/datawhalechina/thorough-pytorch)

---

### Working with data

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

```python
# Download training data from open datasets.
training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor(),
)

# Download test data from open datasets.
test_data = datasets.FashionMNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor(),
)
```

100.0%

Extracting data/FashionMNIST/raw/train-labels-idx1-ubyte.gz to data/FashionMNIST/raw

100.0%

Extracting data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw
```

```python
batch_size = 64

# Create data loaders.
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
```

```
Shape of X [N, C, H, W]: torch.Size([64, 1, 28, 28])
Shape of y: torch.Size([64]) torch.int64
```

Read more about [loading data in PyTorch](data_tutorial.html).

---

### Creating Models

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

model = NeuralNetwork().to(device)
print(model)
```

Read more about [building neural networks in PyTorch](buildmodel_tutorial.html).

---

### Optimizing the Model Parameters

To train a model, we need a [loss function](https://pytorch.org/docs/stable/nn.html#loss-functions) and an [optimizer](https://pytorch.org/docs/stable/optim.html).

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

In a single training loop, the model makes predictions on the training dataset (fed to it in batches), and backpropagates the prediction error to adjust the model's parameters.

# Compute prediction error
        pred = model(X)
        loss = loss_fn(pred, y)

# Backpropagation
        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}]")
```

We also check the model's performance against the test dataset to ensure it is learning.

Done!
```

Read more about [Training your model](optimization_tutorial.html).

---

### Saving Models

A common way to save a model is to serialize the internal state dictionary (containing the model parameters).

```python
torch.save(model.state_dict(), "model.pth")
print("Saved PyTorch Model State to model.pth")
```

```
Saved PyTorch Model State to model.pth
```

---

### Loading Models

The process for loading a model includes re-creating the model structure and loading the state dictionary into it.

```python
model = NeuralNetwork().to(device)
model.load_state_dict(torch.load("model.pth"))
```

```
<All keys matched successfully>
```

This model can now be used to make predictions.

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

```
Predicted: "Ankle boot", Actual: "Ankle boot"
```

Try run PyTorch Quickstart demo

发表评论
使用cookie技术保留您的个人信息以便您下次快速评论，继续评论表示您已同意该条款

Setup ubuntu server 20.04 for machine learning

Try run PyTorch Quickstart demo

使用Ollama和OpenWebUI本地运行llama3大语言模型

STM32ADC+DMA周期采样数据滤波

HDLBits Note

【转】How I Won Singapore’s GPT-4 Prompt Engineering Competition

使用Ollama和OpenWebUI本地运行llama3大语言模型

机器学习的一些基本概念

Setup ubuntu server 20.04 for machine learning

STM32ADC+DMA周期采样数据滤波

Try run PyTorch Quickstart demo

发表评论 使用cookie技术保留您的个人信息以便您下次快速评论，继续评论表示您已同意该条款

Try run PyTorch Quickstart demo

发表评论
使用cookie技术保留您的个人信息以便您下次快速评论，继续评论表示您已同意该条款