115 lines
4.2 KiB
Python
115 lines
4.2 KiB
Python
from pathlib import Path
|
||
import numpy
|
||
import torch
|
||
from torch.utils.data import DataLoader, Dataset
|
||
from torchvision.transforms import v2 as tvtrans
|
||
from torchvision import datasets
|
||
import torch.nn.functional as F
|
||
|
||
|
||
class CNN(torch.nn.Module):
|
||
"""卷积神经网络模型"""
|
||
|
||
def __init__(self):
|
||
super(CNN, self).__init__()
|
||
|
||
self.conv1 = torch.nn.Conv2d(1, 32, kernel_size=(3, 3))
|
||
self.pool1 = torch.nn.MaxPool2d(kernel_size=(2, 2))
|
||
self.conv2 = torch.nn.Conv2d(32, 64, kernel_size=(3, 3))
|
||
self.pool2 = torch.nn.MaxPool2d(kernel_size=(2, 2))
|
||
self.conv3 = torch.nn.Conv2d(64, 64, kernel_size=(3, 3))
|
||
self.flatten = torch.nn.Flatten()
|
||
# 28x28过第一轮卷积后变为26x26，过第一轮池化后变为13x13
|
||
# 过第二轮卷积后变为11x11，过第二轮池化后变为5x5
|
||
# 过第三轮卷积后变为3x3。
|
||
# 最后一轮卷积核个数为64。
|
||
self.fc1 = torch.nn.Linear(64 * 3 * 3, 64)
|
||
torch.nn.init.xavier_normal_(self.fc1.weight)
|
||
torch.nn.init.zeros_(self.fc1.bias)
|
||
self.fc2 = torch.nn.Linear(64, 10)
|
||
torch.nn.init.xavier_normal_(self.fc2.weight)
|
||
torch.nn.init.zeros_(self.fc2.bias)
|
||
|
||
def forward(self, x):
|
||
x = F.relu(self.conv1(x))
|
||
x = self.pool1(x)
|
||
x = F.relu(self.conv2(x))
|
||
x = self.pool2(x)
|
||
x = F.relu(self.conv3(x))
|
||
x = self.flatten(x)
|
||
x = F.relu(self.fc1(x))
|
||
x = self.fc2(x)
|
||
return F.softmax(x, dim=1)
|
||
|
||
|
||
class MnistDataset(Dataset):
|
||
"""用于加载Mnist的自定义数据集"""
|
||
|
||
shape: int
|
||
transform: tvtrans.Transform
|
||
images_data: numpy.ndarray
|
||
labels_data: torch.Tensor
|
||
|
||
def __init__(self, images: numpy.ndarray, labels: numpy.ndarray, transform: tvtrans.Transform):
|
||
images_len: int = images.shape[0]
|
||
labels_len: int = labels.shape[0]
|
||
assert (images_len == labels_len)
|
||
self.shape = images_len
|
||
|
||
self.images_data = images
|
||
self.labels_data = torch.from_numpy(labels)
|
||
self.transform = transform
|
||
|
||
def __getitem__(self, index):
|
||
return self.transform(self.images_data[index]), self.labels_data[index]
|
||
|
||
def __len__(self):
|
||
return self.shape
|
||
|
||
|
||
class MnistDataSource:
|
||
"""用于读取MNIST数据的数据读取器"""
|
||
|
||
train_loader: DataLoader
|
||
test_loader: DataLoader
|
||
|
||
def __init__(self, batch_size: int):
|
||
dataset_path = Path(__file__).resolve().parent.parent / 'datasets' / 'mnist.npz'
|
||
dataset = numpy.load(dataset_path)
|
||
|
||
# 所有图片均为黑底白字
|
||
# 6万张训练图片：60000x28x28。标签只有第一维。
|
||
train_images: numpy.ndarray = dataset['x_train']
|
||
train_labels: numpy.ndarray = dataset['y_train']
|
||
# 1万张测试图片：10000x28x28。标签只有第一维。
|
||
test_images: numpy.ndarray = dataset['x_test']
|
||
test_labels: numpy.ndarray = dataset['y_test']
|
||
|
||
# 定义数据转换器
|
||
trans = tvtrans.Compose([
|
||
# 从uint8转换为float32并自动归一化到0-1区间
|
||
# tvtrans.ToTensor(),
|
||
tvtrans.ToImage(),
|
||
tvtrans.ToDtype(torch.float32, scale=True),
|
||
|
||
# 为了符合后面图像的输入颜色通道条件，要在最后挤出一个新的维度
|
||
#tvtrans.Lambda(lambda x: x.unsqueeze(-1))
|
||
|
||
# 这个特定的标准化参数 (0.1307, 0.3081) 是 MNIST 数据集的标准化参数，这些数值是MNIST训练集的全局均值和标准差。
|
||
# 这种标准化有助于模型训练时的数值稳定性和收敛速度。
|
||
#tvtrans.Normalize((0.1307,), (0.3081,)),
|
||
])
|
||
|
||
# 创建数据集
|
||
train_dataset = MnistDataset(train_images, train_labels, transform=trans)
|
||
test_dataset = MnistDataset(test_images, test_labels, transform=trans)
|
||
|
||
|
||
# 赋值到自身
|
||
self.train_loader = DataLoader(dataset=train_dataset,
|
||
batch_size=batch_size,
|
||
shuffle=False)
|
||
self.test_loader = DataLoader(dataset=test_dataset,
|
||
batch_size=batch_size,
|
||
shuffle=False)
|