PyTorch学习笔记 2. 运行官网训练、推理的入门示例
作者：互联网
PyTorch学习笔记 2. 运行官网训练、推理的入门示例
一、加载数据
首先引用必要的库：
import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor, Lambda, Compose
import matplotlib.pyplot as plt
与其它机器深度学习类似，Pytorch运行时需要数据集和标签。
Pytorch提供了文本、语音、视频等多个领域的数据库，本文使用的是FashionMNIST视频库数据集。
每个Torch视频库包含两个重要的参数：样本和标签。
# 从开放库下载训练集
training_data = datasets.FashionMNIST(
root="data",
train=True,
download=True,
transform=ToTensor(),
)
# 从开放库下载测试数据集
test_data = datasets.FashionMNIST(
root="data",
train=False,
download=True,
transform=ToTensor(),
)
下面在数据集上进行迭代，可以打印一些数据信息：
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("Shape of X [N, C, H, W]: ", X.shape)
print("Shape of y: ", y.shape, y.dtype)
break
输出结果如下，我们定义的批大小64，迭代器每批返回64个特征和标签。
Shape of X [N, C, H, W]: torch.Size([64, 1, 28, 28])
Shape of y: torch.Size([64]) torch.int64
二、创建模型
使用nn.Module 用来在PyTorch里创建神经网络。这里定义的是顺序网络，
下面定义了神经网络层，可以使用GPU来加速运算。
# Get cpu or gpu device for training.
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
# 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)
torch.nn.Linear(input_data,hidden_layer)完成从输入层到隐藏层的线性变换；torch.nn.ReLU()为激活函数；torch.nn.Linear(hidden_layer, output_data)完成从隐藏层到输出层的线性变换；
torch.nn.Sequential介绍：
torch.nn.Sequential 类是 torch.nn 中的一种序列容器，可以在其中嵌套各种实现神经网络中来完成对神经网络模型的搭建，而参数会按照我们定义好的序列自动传递下去。
另一种参数传递的方式是orderdict，
torch.nn.Linear
torch.nn.Linear 类用于定义模型的线性层，即完成前面提到的不同的层之间的线性变换。
3. torch.nn.ReLU
torch.nn.ReLU 类属于非线性激活分类，在定义时默认不需要传入参数。
这一步打印网络结构如下：
三、调整模型参数
为了训练模型，这里要定义损失函数和优化器。
loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)
在每一轮的训练中，模型要在训练集上执行预测，并且根据反射传播来调整模型参数。
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}]")
另外需要测试集来优化、检查模型。
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")
训练过程包含多个周期，每一轮模型都要通过参数来学习，以获得更好的推理模型。迭代过程的精度和损失函数在下面代码中打印出来：
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!")
四、保存模型
通常会把内部的状态词典序列化后作为模型保存下来。
torch.save(model.state_dict(), "model.pth")
print("Saved PyTorch Model State to model.pth")
五、加载模型
model = NeuralNetwork()
model.load_state_dict(torch.load("model.pth"))
下面使用模型执行推理：
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}"')
推理结果：
完整源代码：
import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor, Lambda, Compose
import matplotlib.pyplot as plt
# 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(),
)
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("Shape of X [N, C, H, W]: ", X.shape)
print("Shape of y: ", y.shape, y.dtype)
break
# Get cpu or gpu device for training.
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
# 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)
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):
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)
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")
print("Saved PyTorch Model State to model.pth")
model = NeuralNetwork()
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():
pred = model(x)
predicted, actual = classes[pred[0].argmax(0)], classes[y]
print(f'Predicted: "{predicted}", Actual: "{actual}"')
运行结果：
(pytorch) appledeMacBook-Pro:pytorch apple$ python3 learn1.py
/opt/miniconda3/envs/pytorch/lib/python3.7/site-packages/torchvision/datasets/mnist.py:498: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at ../torch/csrc/utils/tensor_numpy.cpp:180.)
return torch.from_numpy(parsed.astype(m[2], copy=False)).view(*s)
Shape of X [N, C, H, W]: torch.Size([64, 1, 28, 28])
Shape of y: torch.Size([64]) torch.int64
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)
)
)
Epoch 1
-------------------------------
loss: 2.314974 [ 0/60000]
loss: 2.301318 [ 6400/60000]
loss: 2.279395 [12800/60000]
loss: 2.260673 [19200/60000]
loss: 2.256194 [25600/60000]
loss: 2.230177 [32000/60000]
loss: 2.232735 [38400/60000]
loss: 2.197281 [44800/60000]
loss: 2.199913 [51200/60000]
loss: 2.165345 [57600/60000]
Test Error:
Accuracy: 46.0%, Avg loss: 2.161378
Epoch 2
-------------------------------
loss: 2.181149 [ 0/60000]
loss: 2.164842 [ 6400/60000]
loss: 2.110326 [12800/60000]
loss: 2.114110 [19200/60000]
loss: 2.074363 [25600/60000]
loss: 2.027263 [32000/60000]
loss: 2.043373 [38400/60000]
loss: 1.965748 [44800/60000]
loss: 1.974563 [51200/60000]
loss: 1.901750 [57600/60000]
Test Error:
Accuracy: 58.3%, Avg loss: 1.897587
Epoch 3
-------------------------------
loss: 1.938917 [ 0/60000]
loss: 1.899398 [ 6400/60000]
loss: 1.785908 [12800/60000]
loss: 1.814409 [19200/60000]
loss: 1.720331 [25600/60000]
loss: 1.681701 [32000/60000]
loss: 1.687258 [38400/60000]
loss: 1.586764 [44800/60000]
loss: 1.616351 [51200/60000]
loss: 1.508570 [57600/60000]
Test Error:
Accuracy: 60.8%, Avg loss: 1.523732
Epoch 4
-------------------------------
loss: 1.598114 [ 0/60000]
loss: 1.553433 [ 6400/60000]
loss: 1.402492 [12800/60000]
loss: 1.467502 [19200/60000]
loss: 1.366623 [25600/60000]
loss: 1.368079 [32000/60000]
loss: 1.371022 [38400/60000]
loss: 1.290068 [44800/60000]
loss: 1.333592 [51200/60000]
loss: 1.231188 [57600/60000]
Test Error:
Accuracy: 62.9%, Avg loss: 1.253851
Epoch 5
-------------------------------
loss: 1.339722 [ 0/60000]
loss: 1.310711 [ 6400/60000]
loss: 1.143826 [12800/60000]
loss: 1.242881 [19200/60000]
loss: 1.134900 [25600/60000]
loss: 1.168011 [32000/60000]
loss: 1.180709 [38400/60000]
loss: 1.111995 [44800/60000]
loss: 1.158805 [51200/60000]
loss: 1.070515 [57600/60000]
Test Error:
Accuracy: 64.0%, Avg loss: 1.088987
Done!
Saved PyTorch Model State to model.pth
Predicted: "Ankle boot", Actual: "Ankle boot"
标签：loss,nn,示例,torch,PyTorch,60000,test,model,官网 来源： https://blog.csdn.net/xundh/article/details/120498324