pytorch快速入门实战篇-FashionMnist案例

最新推荐文章于 2024-09-26 00:15:00 发布
最新推荐文章于 2024-09-26 00:15:00 发布
阅读量1.7k 收藏 3
点赞数 1
分类专栏： 深度学习 文章标签： pytorch
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/weixin_39107270/article/details/124382038
版权

参考：官网

文章目录

1. Working with data

PyTorch has two primitives to work with data: 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.

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, TorchVision, and TorchAudio, 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). 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.

1.1 Download training data from open datasets.

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

1.2 Download test data from open datasets.

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

Out:


Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to 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
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
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to 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
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.

batch_size = 64

1.3 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

Out:

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.

2. Creating Models

To define a neural network in PyTorch, we create a class that inherits from nn.Module. 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 if available.

2.1 Get cpu or gpu device for training.

device = “cuda” if torch.cuda.is_available() else “cpu”
print(f"Using {device} device")

2.2 Define model

class NeuralNetwork(nn.Module):
    def __init__(self):
        super(NeuralNetwork, self).__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)

Out:

Using cuda 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.

2.3 Optimizing the Model Parameters

To train a model, we need a loss function and an optimizer.

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.

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
        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}]")

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

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.

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!")

Out:

Epoch 1
-------------------------------
loss: 2.299968  [    0/60000]
loss: 2.291713  [ 6400/60000]
loss: 2.274773  [12800/60000]
loss: 2.272840  [19200/60000]
loss: 2.265114  [25600/60000]
loss: 2.223690  [32000/60000]
loss: 2.246659  [38400/60000]
loss: 2.205027  [44800/60000]
loss: 2.203506  [51200/60000]
loss: 2.183183  [57600/60000]
Test Error:
 Accuracy: 40.4%, Avg loss: 2.176064

Epoch 2
-------------------------------
loss: 2.179508  [    0/60000]
loss: 2.171398  [ 6400/60000]
loss: 2.122458  [12800/60000]
loss: 2.136343  [19200/60000]
loss: 2.099183  [25600/60000]
loss: 2.031877  [32000/60000]
loss: 2.070053  [38400/60000]
loss: 1.988699  [44800/60000]
loss: 1.989894  [51200/60000]
loss: 1.931872  [57600/60000]
Test Error:
 Accuracy: 58.0%, Avg loss: 1.927841

Epoch 3
-------------------------------
loss: 1.951685  [    0/60000]
loss: 1.920792  [ 6400/60000]
loss: 1.815998  [12800/60000]
loss: 1.850795  [19200/60000]
loss: 1.757668  [25600/60000]
loss: 1.698289  [32000/60000]
loss: 1.727373  [38400/60000]
loss: 1.622224  [44800/60000]
loss: 1.637520  [51200/60000]
loss: 1.541725  [57600/60000]
Test Error:
 Accuracy: 62.5%, Avg loss: 1.558743

Epoch 4
-------------------------------
loss: 1.615998  [    0/60000]
loss: 1.577118  [ 6400/60000]
loss: 1.438216  [12800/60000]
loss: 1.503292  [19200/60000]
loss: 1.393710  [25600/60000]
loss: 1.377801  [32000/60000]
loss: 1.397386  [38400/60000]
loss: 1.316668  [44800/60000]
loss: 1.345000  [51200/60000]
loss: 1.248275  [57600/60000]
Test Error:
 Accuracy: 63.4%, Avg loss: 1.277212

Epoch 5
-------------------------------
loss: 1.348338  [    0/60000]
loss: 1.324071  [ 6400/60000]
loss: 1.170114  [12800/60000]
loss: 1.266121  [19200/60000]
loss: 1.148989  [25600/60000]
loss: 1.163925  [32000/60000]
loss: 1.187885  [38400/60000]
loss: 1.124403  [44800/60000]
loss: 1.159600  [51200/60000]
loss: 1.073207  [57600/60000]
Test Error:
 Accuracy: 64.3%, Avg loss: 1.099506

Done!

Read more about Training your model.

3 Saving Models

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

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

Out:

Saved PyTorch Model State to model.pth

4. Loading Models

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

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

This model can now be used to make predictions.

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():
    pred = model(x)
    predicted, actual = classes[pred[0].argmax(0)], classes[y]
    print(f'Predicted: "{predicted}", Actual: "{actual}"')

Out:

Predicted: "Ankle boot", Actual: "Ankle boot"
Read more about Saving & Loading your model.

Total running time of the script: ( 0 minutes 42.173 seconds)

5 Complete Code in python

5.1 Get Data

如果上面通过命令行的方式下载数据集特别慢，可以直接下载本网盘里的数据集，然后放到对应的文件夹下。

链接：https://pan.baidu.com/s/194eBjl2W98VfcSCNe0x8Ow 
提取码：e11r

解压后放入相应的文件夹下：
在这里插入图片描述

5.2 Train



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


# Download training data from open datasets.
training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=False,  # 数据集已下载，如果未下载，download = True
    transform=ToTensor(), # 数据预处理，格式调整
)

# Download test data from open datasets.
test_data = datasets.FashionMNIST(
    root="data",
    train=False,
    download=True,  # 数据集已下载，如果未下载，download = True
    transform=ToTensor(), # 数据预处理，格式调整
)



# 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



# Define model
class NeuralNetwork(nn.Module):
    def __init__(self):
        super(NeuralNetwork, self).__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


# print(model)



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
        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}]")


if __name__ == '__main__':
    batch_size = 64
    loss_fn = nn.CrossEntropyLoss()
    device = "cuda" if torch.cuda.is_available() else "cpu"
    print(f"Using {device} device")
    model = NeuralNetwork().to(device)  # 实例化模型
    optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)
    # Get cpu or gpu device for training.

    # Create data loaders.
    train_dataloader = DataLoader(training_data, batch_size=batch_size)
    test_dataloader = DataLoader(test_data, batch_size=batch_size)

    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!")

    # Saving models
    torch.save(model.state_dict(), "model.pth")
    print("Saved PyTorch Model State to model.pth")

5.3 Inference

test.py

import torch
from torch import nn

class NeuralNetwork(nn.Module):
    def __init__(self):
        super(NeuralNetwork, self).__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



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

if __name__ == '__main__':
    model = NeuralNetwork()
    model.load_state_dict(torch.load("model.pth"))
    model.eval()
    #x, y = test_data[0][0], test_data[0][1]  # y=9
    x=[[[0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0118, 0.0039, 0.0000, 0.0000, 0.0275,
          0.0000, 0.1451, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0039, 0.0078, 0.0000,
          0.1059, 0.3294, 0.0431, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.4667, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0039, 0.0000, 0.0000,
          0.3451, 0.5608, 0.4314, 0.0000, 0.0000, 0.0000, 0.0000, 0.0863,
          0.3647, 0.4157, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0157, 0.0000, 0.2078,
          0.5059, 0.4706, 0.5765, 0.6863, 0.6157, 0.6510, 0.5294, 0.6039,
          0.6588, 0.5490, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0078, 0.0000, 0.0431, 0.5373,
          0.5098, 0.5020, 0.6275, 0.6902, 0.6235, 0.6549, 0.6980, 0.5843,
          0.5922, 0.5647, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0039, 0.0000,
          0.0078, 0.0039, 0.0000, 0.0118, 0.0000, 0.0000, 0.4510, 0.4471,
          0.4157, 0.5373, 0.6588, 0.6000, 0.6118, 0.6471, 0.6549, 0.5608,
          0.6157, 0.6196, 0.0431, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0039, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0118, 0.0000, 0.0000, 0.3490, 0.5451, 0.3529,
          0.3686, 0.6000, 0.5843, 0.5137, 0.5922, 0.6627, 0.6745, 0.5608,
          0.6235, 0.6627, 0.1882, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0078, 0.0157,
          0.0039, 0.0000, 0.0000, 0.0000, 0.3843, 0.5333, 0.4314, 0.4275,
          0.4314, 0.6353, 0.5294, 0.5647, 0.5843, 0.6235, 0.6549, 0.5647,
          0.6196, 0.6627, 0.4667, 0.0000],
         [0.0000, 0.0000, 0.0078, 0.0078, 0.0039, 0.0078, 0.0000, 0.0000,
          0.0000, 0.0000, 0.1020, 0.4235, 0.4588, 0.3882, 0.4353, 0.4588,
          0.5333, 0.6118, 0.5255, 0.6039, 0.6039, 0.6118, 0.6275, 0.5529,
          0.5765, 0.6118, 0.6980, 0.0000],
         [0.0118, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0824,
          0.2078, 0.3608, 0.4588, 0.4353, 0.4039, 0.4510, 0.5059, 0.5255,
          0.5608, 0.6039, 0.6471, 0.6667, 0.6039, 0.5922, 0.6039, 0.5608,
          0.5412, 0.5882, 0.6471, 0.1686],
         [0.0000, 0.0000, 0.0902, 0.2118, 0.2549, 0.2980, 0.3333, 0.4627,
          0.5020, 0.4824, 0.4353, 0.4431, 0.4627, 0.4980, 0.4902, 0.5451,
          0.5216, 0.5333, 0.6275, 0.5490, 0.6078, 0.6314, 0.5647, 0.6078,
          0.6745, 0.6314, 0.7412, 0.2431],
         [0.0000, 0.2667, 0.3686, 0.3529, 0.4353, 0.4471, 0.4353, 0.4471,
          0.4510, 0.4980, 0.5294, 0.5333, 0.5608, 0.4941, 0.4980, 0.5922,
          0.6039, 0.5608, 0.5804, 0.4902, 0.6353, 0.6353, 0.5647, 0.5412,
          0.6000, 0.6353, 0.7686, 0.2275],
         [0.2745, 0.6627, 0.5059, 0.4078, 0.3843, 0.3922, 0.3686, 0.3804,
          0.3843, 0.4000, 0.4235, 0.4157, 0.4667, 0.4706, 0.5059, 0.5843,
          0.6118, 0.6549, 0.7451, 0.7451, 0.7686, 0.7765, 0.7765, 0.7333,
          0.7725, 0.7412, 0.7216, 0.1412],
         [0.0627, 0.4941, 0.6706, 0.7373, 0.7373, 0.7216, 0.6706, 0.6000,
          0.5294, 0.4706, 0.4941, 0.4980, 0.5725, 0.7255, 0.7647, 0.8196,
          0.8157, 1.0000, 0.8196, 0.6941, 0.9608, 0.9882, 0.9843, 0.9843,
          0.9686, 0.8627, 0.8078, 0.1922],
         [0.0000, 0.0000, 0.0000, 0.0471, 0.2627, 0.4157, 0.6431, 0.7255,
          0.7804, 0.8235, 0.8275, 0.8235, 0.8157, 0.7451, 0.5882, 0.3216,
          0.0314, 0.0000, 0.0000, 0.0000, 0.6980, 0.8157, 0.7373, 0.6863,
          0.6353, 0.6196, 0.5922, 0.0431],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000],
         [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
          0.0000, 0.0000, 0.0000, 0.0000]]]
    x=torch.tensor(x)
    #y=9
    with torch.no_grad():
        pred = model(x)
        #predicted, actual = classes[pred[0].argmax(0)], classes[y]
        predicted= classes[pred[0].argmax(0)]
        print(f'Predicted: "{predicted}"')

out:

Predicted: "Ankle boot"

6. Reference

  1. 官网：https://pytorch.org/tutorials/beginner/basics/quickstart_tutorial.html

7. others

完整的数据集和代码可从该处下载：https://download.csdn.net/download/weixin_39107270/85213879

闪闪发亮的小星星
关注
专栏目录
Pytorch GAN入门实战---生成MNIST手写数据集代码实现
l love CV
03-30 3392
大话超级火爆的GAN，对新手超级友好的实战入门小例子---利用GAN 生成MNIST手写数据集代码实现pytorch版，分享心得​。基础GAN的原理还不懂的，先看：生成式对抗神经网络（GAN）原理给你讲的明明白白。 ​
Pytorch 快速入门实战之 Fashionmnist
04-24
内涵数据集、Train.py Test.py 以及相应的说明文档。适合新手快速入门ptrorch。
PyTorch项目实战—FashionMNIST时装分类
Alexa_的博客
07-16 1146
PyTorch项目实战1
0基础学习PyTorch——时尚分类（Fashion MNIST）训练和推理
最新发布
方亮的专栏
09-26 1129
将下面内容保存为garmentclassifier.py。该文件会被训练和推理两个环节使用。# 定义一个用于服装分类的卷积神经网络# 定义第一个卷积层，输入通道数为1，输出通道数为6，卷积核大小为5x5# 定义最大池化层，池化窗口大小为2x2# 定义第二个卷积层，输入通道数为6，输出通道数为16，卷积核大小为5x5# 定义第一个全连接层，输入大小为16*4*4，输出大小为120# 定义第二个全连接层，输入大小为120，输出大小为84。
pytorch学习21：Fashion MNIST实例
HMT的博客
10-13 308
介绍 Fashion MNIST数据集 是kaggle上提供的一个图像分类入门级的数据集，其中包含10个类别的70000个灰度图像。如图所示，这些图片显示的是每件衣服的低分辨率(28×28像素) 数据集的下载和介绍：地址 步骤 载入数据 使用pandas载入文件中的数据 预处理数据 将数据划分为X、Y 并创建相应的DataLoader方便使用 创建网络 使用三层CNN网络 定义超参、损失函数和优化器 损失函数选择交叉熵 优化器选择Adam 开始训练 测试结果 全部代码 impor
PyTorch 04： 用PyTorch实现Fashion-MNIST
科学边界
05-15 2064
好了，我们来实战演练。你将使用 Fashion-MNIST 数据集。对于神经网络来说，MNIST 的规模很小，可以轻松地达到 97% 的准确率。Fashion-MNIST 包括很多 28x28 灰色服饰图像。它比 MNIST 更复杂，也更贴近实际现实需求。 你要在这个 notebook 里构建神经网络。其实你可以用 Part 3 notebook 里的代码，但是这样就学不到任何知识了。只有自己编写代码并确保代码能运行，才能实现最佳学习效果。当然，你可以参考 Part 3 notebook。 首先，通过 t
基于Pytorch的Fashion mnist实战
pylittlebrat的博客
04-26 4788
import torch from torchvision import datasets, transforms import time import numpy as np import matplotlib.pyplot as plt from PIL import Image # Define a transform to normalize the data transform = transforms.Compose([transforms.ToTensor(),
Pytorch-GAN-MNIST-FashionMNIST-USPS:用于MNIST，FashionMNIST和USPS数据集的GAN的Pytorch实现
03-31
Pytorch-GAN-MNIST-FashionMNIST-USPS 针对MNIST，FashionMNIST和USPS数据集的GAN的Pytorch实现。 生成的样本 MNIST #### FashionMNIST！[FashionMNIST]（/ results / FashionMNIST.png）#### USPS！[USPS]（/ ...
pytorch基础实战--FashionMNIST时装分类.ipynb
11-16
pytorch基础实战--FashionMNIST时装分类.ipynb
pytorch-FashionMNIST实战项目
09-16
本资源是基于FashionMNIS数据集进行多分类的实战项目 项目中的数据集使用的是pytorch自带数据集，第一次使用需要下载
Pytorch：卷积神经网络-LeNet
Jingmin Wei's Blog
02-04 1261
LeNet网络结构讲解，在GPU上训练模型，识别Fashion-MNIST
FashionMNIST数据集（pytorch）免费下载
02-13
train_set = torchvision.datasets.FashionMNIST( root='D:\\python\\dataset', train=True, download=True, transform=transforms.Compose([transforms.ToTensor()])) 使用上述代码下载的内容，包含raw和processed，解压既用。
PyTorch示例——CNN图像分类-FashionMNIST
蒋含竹的博客
04-05 1723
PyTorch示例-CNN多分类-FashionMNIST数据
『跟着雨哥学AI』系列之五：快速上手趣味案例FashionMNIST
PaddlePaddle
01-25 460
点击左上方蓝字关注我们课程简介：“跟着雨哥学AI”是百度飞桨开源框架近期针对高层API推出的系列课。本课程由多位资深飞桨工程师精心打造，不仅提供了从数据处理、到模型组网、模型训练、模型评估...
PyTorch 深度学习实战 | Fashion MNIST 图片重建实战
不断学习，不断进步，提高自己
03-23 975
Fashion MNIST 图片重建实战
PyTorch深度学习（三）：Fashion-MNIST 数据集介绍
~宪宪的博客
11-07 1万+
PyTorch深度学习（三）：Fashion-MNIST 数据集介绍
(保姆级)Pytorch构建神经网络的简单实例——对FashionMNIST数据集图像进行分类（源代码来源于Pytorch计算机视觉实战第三章）
Zssss12的博客
02-05 750
FashionMNIST（时尚MNIST）是一个经典的计算机视觉数据集，用于图像分类任务。它是由 Zalando Research 创建的，旨在替代传统的MNIST数据集，以更贴近实际场景中的图像分类问题。FashionMNIST数据集包含了60,000个用于训练的图像样本和10,000个用于测试的图像样本，总共包括10个类别。每个样本都是灰度图像，分辨率为28x28像素。每个像素的值介于0到255之间，表示像素的灰度强度。数据集中的图像样本代表了不同种类的时尚商品，包括衣服、鞋子、手袋等。
pytorch进行fashion mnist数据集分类
热门推荐
lemonHe的博客
05-19 2万+
标题1.数据集介绍 （1）MNIST MNIST是深度学习最基本的数据集之一，由CNN鼻祖yann lecun建立的一个手写字符数据集，包含60000张训练图像和10000张测试图像，包含数字0-9共10个类别. （2）FASHION MNIST 由于MNIST数据集太简单，简单的网络就可以达到99.7%的top one准确率，也就是说在这个数据集上表现较好的网络，在别的任务上表现不一定好。因此...
GDB调试 —— 史上最完整 GDB 指令大全_gdb调试命令大全
2401_85012088的博客
05-17 827
i/info display (查看设置的自动变量操作)display 变量名 (自动打印指定变量的值)undisplay 编号 (删除设置的自动变量)p/print 变量名
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

闪闪发亮的小星星

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付：¥1
获取中
扫码支付

您的余额不足，请更换扫码支付或充值

打赏作者

实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值