使用 pytorch 构建一维卷积神经网络与数据集

• 以一维卷积神经网络为例

1 直接使用 numpy 与 tensor 来构建数据集

1.1一维卷积神经网络结构

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv1d(in_channels=1, out_channels=10, kernel_size=3, stride=2)
        self.max_pool1 = nn.MaxPool1d(kernel_size=3, stride=2)
        self.conv2 = nn.Conv1d(10, 20, 3, 2)
        self.max_pool2 = nn.MaxPool1d(3, 2)
        self.conv3 = nn.Conv1d(20, 40, 3, 2)
        
        self.liner1 = nn.Linear(40 * 14, 120)
        self.liner2 = nn.Linear(120, 84)
        self.liner3 = nn.Linear(84, 4) 
        
    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = self.max_pool1(x)
        x = F.relu(self.conv2(x))
        x = self.max_pool2(x)
        x = F.relu(self.conv3(x))
        
        x = x.view(-1, 40 * 14)
        x = F.relu(self.liner1(x))
        x = F.relu(self.liner2(x))
        x = self.liner3(x)
        
        return x

1.2 数据的结构

x_train, x_test, y_train, y_test = train_test_split(dataSet, labels, test_size=0.3, random_state=42)
print( x_train.shape, y_train.shape, x_test.shape, y_test.shape)

out:

((51527, 500), (51527,), (22084, 500), (22084,))

1.3 数据的结构

1.3.1 将 numpy 数据集转化为 tensor

x_train = torch.from_numpy(x_train)
y_train = torch.from_numpy(y_train)
x_test = torch.from_numpy(x_test)
y_test = torch.from_numpy(y_test)

1.3.2 训练集数据类型转化为：tensor.float32

x_train = torch.tensor(x_train, dtype=torch.float32)
x_test = torch.tensor(x_test, dtype=torch.float32)

1.3.3 改变 x_train.shape , x_test.shape 的形状

送入训练的数据格式为：（1， 1， 500）

x_train = x_train.reshape(x_train.shape[0], 1, 1, x_train.shape[1])
x_test = x_test.reshape(x_test.shape[0], 1, x_train.shape[1])
print(x_train.shape, x_test.shape)

out:

(torch.Size([51527, 1, 1, 500]), torch.Size([22084, 1, 500]))

1.3.4 标签的数据格式 与 数据类型

• 在1.2 节中给出标签的形状：x_train.shape = (51527,) , y_train.shape = (22084,)，，类型是：float， 但是训练器需要的是：（51527, 1）, (22084, 1) ,dtype=tensor.long

y_train = y_train.reshape(y_train.shape[0], 1)
y_test = y_test.reshape(y_test.shape[0], 1)

y_train = torch.tensor(y_train, dtype=torch.long)
y_test = torch.tensor(y_test, dtype=torch.long)

1.4 开始训练

# 定义损失函数 与 优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
start = time.time()
for epoch in tqdm(range(10)):
    running_loss = 0
    for i, input_data in enumerate(x_train, 0):
        # print(input_data.shape)
        label = y_train[i]
        optimizer.zero_grad()
        
        outputs = net(input_data)
        loss = criterion(outputs, label)
        loss.backward()
        optimizer.step()
        
        running_loss += loss.item()
        if i % 2000 == 1999:
            print('[%d, %5d] loss: %0.3f' % (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0
print('time = %2dm:%2ds' % ((time.time() - start)//60, (time.time()-start)%60))

2 通过继承 torch.utils.data.Dataset类构建一个数据集

class NuclearDataset(Dataset):
    """ Nuclear Dataset."""

    def __init__(self, data_file, root_dir=None, transform=None):
        """
        Args:
            data_file (string): Path to the data file with annotations.
            root_dir (string): Directory with all the images.
            transform (callable, optional): Optional transform to be applied
                on a sample.
        """
        # self.landmarks_frame = pd.read_csv(csv_file)
        # 加载数据
        self.landmarks_frame = np.load(data_file)
        self.root_dir = root_dir
        self.transform = transform

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

    def __getitem__(self, idx):
        if torch.is_tensor(idx):
            idx = idx.tolist()

        # img_name = os.path.join(self.root_dir,self.landmarks_frame.iloc[idx, 0])
        # image = io.imread(img_name)
        # landmarks = self.landmarks_frame.iloc[idx, 1:]
        landmarks = self.landmarks_frame[:, -1]
        landmarks = np.array([landmarks])
        # landmarks = landmarks.astype('float').reshape(-1, 2)
        landmarks = landmarks.astype('float').reshape(-1, 1)
        sample = {'landmarks': landmarks}

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

        return sample

dataSet实例
标签

同样可以直接定义函数 划分训练集与训练集，比较方便，代码可移植性较好。这其中数据的形状是怎样的，可以按照代码运行的错误提示进行修改。