Pembelajaran Mesin |. Tutorial Ringkas PyTorch Bahagian 2-AI-php.cn

Menyusul artikel sebelum ini"Tutorial Ringkas PyTorch Bahagian 1", teruskan mempelajari perceptron berbilang lapisan, rangkaian neural konvolusi dan LSTMNet.

1. Multi-layer perceptron

Multi-layer perceptron ialah rangkaian neural yang ringkas dan asas penting untuk pembelajaran mendalam. Ia mengatasi batasan model linear dengan menambahkan satu atau lebih lapisan tersembunyi pada rangkaian. Gambar rajah khusus adalah seperti berikut:

Pembelajaran Mesin |. Tutorial Ringkas PyTorch Bahagian 2

import numpy as npimport torchfrom torch.autograd import Variablefrom torch import optimfrom data_util import load_mnistdef build_model(input_dim, output_dim):return torch.nn.Sequential(torch.nn.Linear(input_dim, 512, bias=False),torch.nn.ReLU(),torch.nn.Dropout(0.2),torch.nn.Linear(512, 512, bias=False),torch.nn.ReLU(),torch.nn.Dropout(0.2),torch.nn.Linear(512, output_dim, bias=False),)def train(model, loss, optimizer, x_val, y_val):model.train()optimizer.zero_grad()fx = model.forward(x_val)output = loss.forward(fx, y_val)output.backward()optimizer.step()return output.item()def predict(model, x_val):model.eval()output = model.forward(x_val)return output.data.numpy().argmax(axis=1)def main():torch.manual_seed(42)trX, teX, trY, teY = load_mnist(notallow=False)trX = torch.from_numpy(trX).float()teX = torch.from_numpy(teX).float()trY = torch.tensor(trY)n_examples, n_features = trX.size()n_classes = 10model = build_model(n_features, n_classes)loss = torch.nn.CrossEntropyLoss(reductinotallow='mean')optimizer = optim.Adam(model.parameters())batch_size = 100for i in range(100):cost = 0.num_batches = n_examples // batch_sizefor k in range(num_batches):start, end = k * batch_size, (k + 1) * batch_sizecost += train(model, loss, optimizer,trX[start:end], trY[start:end])predY = predict(model, teX)print("Epoch %d, cost = %f, acc = %.2f%%"% (i + 1, cost / num_batches, 100. * np.mean(predY == teY)))if __name__ == "__main__":main()

Salin selepas log masuk

(1) Kod di atas adalah serupa dengan kod rangkaian neural satu lapisan Perbezaannya ialah build_model membina model rangkaian saraf yang mengandungi tiga lapisan linear dan dua pengaktifan ReLU fungsi:

Tambahkan lapisan linear pertama pada model Bilangan ciri input lapisan ini adalah input_dim dan bilangan ciri output ialah 512
Kemudian tambahkan fungsi pengaktifan ReLU dan lapisan Dropout untuk meningkatkan keupayaan bukan linear; daripada model dan elakkan overfitting; Lapisan tercicir;
Tambah lapisan linear ketiga pada model A lapisan linear, bilangan ciri input lapisan ini ialah 512, dan bilangan ciri output ialah output_dim, iaitu bilangan kategori keluaran model;
(4)print("Epoch %d, cost = %f, acc = %.2f%%" % (i + 1, cost / num_batches, 100. * np.mean(predY == teY))) Akhirnya , pusingan latihan semasa, nilai kerugian dan acc dicetak Output kod di atas adalah seperti berikut:

...Epoch 91, cost = 0.011129, acc = 98.45%Epoch 92, cost = 0.007644, acc = 98.58%Epoch 93, cost = 0.011872, acc = 98.61%Epoch 94, cost = 0.010658, acc = 98.58%Epoch 95, cost = 0.007274, acc = 98.54%Epoch 96, cost = 0.008183, acc = 98.43%Epoch 97, cost = 0.009999, acc = 98.33%Epoch 98, cost = 0.011613, acc = 98.36%Epoch 99, cost = 0.007391, acc = 98.51%Epoch 100, cost = 0.011122, acc = 98.59%

Salin selepas log masuk

2. Rangkaian Neural Convolutional

Convolutional Neural Network (CNN) ialah algoritma pembelajaran mendalam. Apabila matriks adalah input, CNN boleh membezakan antara bahagian penting dan tidak penting (menetapkan pemberat). Berbanding dengan tugas pengelasan lain, CNN tidak memerlukan prapemprosesan data yang tinggi Selagi ia terlatih sepenuhnya, ia boleh mempelajari ciri-ciri matriks. Rajah berikut menunjukkan proses:

import numpy as npimport torchfrom torch.autograd import Variablefrom torch import optimfrom data_util import load_mnistclass ConvNet(torch.nn.Module):def __init__(self, output_dim):super(ConvNet, self).__init__()self.conv = torch.nn.Sequential()self.conv.add_module("conv_1", torch.nn.Conv2d(1, 10, kernel_size=5))self.conv.add_module("maxpool_1", torch.nn.MaxPool2d(kernel_size=2))self.conv.add_module("relu_1", torch.nn.ReLU())self.conv.add_module("conv_2", torch.nn.Conv2d(10, 20, kernel_size=5))self.conv.add_module("dropout_2", torch.nn.Dropout())self.conv.add_module("maxpool_2", torch.nn.MaxPool2d(kernel_size=2))self.conv.add_module("relu_2", torch.nn.ReLU())self.fc = torch.nn.Sequential()self.fc.add_module("fc1", torch.nn.Linear(320, 50))self.fc.add_module("relu_3", torch.nn.ReLU())self.fc.add_module("dropout_3", torch.nn.Dropout())self.fc.add_module("fc2", torch.nn.Linear(50, output_dim))def forward(self, x):x = self.conv.forward(x)x = x.view(-1, 320)return self.fc.forward(x)def train(model, loss, optimizer, x_val, y_val):model.train()optimizer.zero_grad()fx = model.forward(x_val)output = loss.forward(fx, y_val)output.backward()optimizer.step()return output.item()def predict(model, x_val):model.eval()output = model.forward(x_val)return output.data.numpy().argmax(axis=1)def main():torch.manual_seed(42)trX, teX, trY, teY = load_mnist(notallow=False)trX = trX.reshape(-1, 1, 28, 28)teX = teX.reshape(-1, 1, 28, 28)trX = torch.from_numpy(trX).float()teX = torch.from_numpy(teX).float()trY = torch.tensor(trY)n_examples = len(trX)n_classes = 10model = ConvNet(output_dim=n_classes)loss = torch.nn.CrossEntropyLoss(reductinotallow='mean')optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9)batch_size = 100for i in range(100):cost = 0.num_batches = n_examples // batch_sizefor k in range(num_batches):start, end = k * batch_size, (k + 1) * batch_sizecost += train(model, loss, optimizer,trX[start:end], trY[start:end])predY = predict(model, teX)print("Epoch %d, cost = %f, acc = %.2f%%"% (i + 1, cost / num_batches, 100. * np.mean(predY == teY)))if __name__ == "__main__":main()

Salin selepas log masuk

(1) Kod di atas mentakrifkan kelas bernama ConvNet, yang mewarisi daripada kelas torch.nn.Module dan mewakili rangkaian neural convolutional dalam kaedah __init__ Dua sub-modul conv dan fc ditakrifkan, masing-masing mewakili lapisan konvolusi dan lapisan bersambung sepenuhnya. Dalam submodul penukaran, kami mentakrifkan dua lapisan konvolusi (torch.nn.Conv2d), dua lapisan pengumpulan maksimum (torch.nn.MaxPool2d), dua fungsi pengaktifan ReLU (torch.nn.ReLU) dan lapisan Dropout (torch.nn. Keciciran). Dalam sub-modul fc, dua lapisan linear (torch.nn.Linear), fungsi pengaktifan ReLU dan lapisan Dropout ditakrifkan

Lapisan pengumpulan memainkan peranan penting dalam CNN, dan tujuan utamanya adalah seperti berikut Point; :

降低维度：池化层通过对输入特征图（Feature maps）进行局部区域的下采样操作，降低了特征图的尺寸。这样可以减少后续层中的参数数量，降低计算复杂度，加速训练过程；
平移不变性：池化层可以提高网络对输入图像的平移不变性。当图像中的某个特征发生小幅度平移时，池化层的输出仍然具有相似的特征表示。这有助于提高模型的泛化能力，使其能够在不同位置和尺度下识别相同的特征；
防止过拟合：通过减少特征图的尺寸，池化层可以降低模型的参数数量，从而降低过拟合的风险；
增强特征表达：池化操作可以聚合局部区域内的特征，从而强化和突出更重要的特征信息。常见的池化操作有最大池化（Max Pooling）和平均池化（Average Pooling），分别表示在局部区域内取最大值或平均值作为输出；

（3）print("Epoch %d, cost = %f, acc = %.2f%%" % (i + 1, cost / num_batches, 100. * np.mean(predY == teY)))最后打印当前训练的轮次，损失值和acc，上述的代码输出如下：

...Epoch 91, cost = 0.047302, acc = 99.22%Epoch 92, cost = 0.049026, acc = 99.22%Epoch 93, cost = 0.048953, acc = 99.13%Epoch 94, cost = 0.045235, acc = 99.12%Epoch 95, cost = 0.045136, acc = 99.14%Epoch 96, cost = 0.048240, acc = 99.02%Epoch 97, cost = 0.049063, acc = 99.21%Epoch 98, cost = 0.045373, acc = 99.23%Epoch 99, cost = 0.046127, acc = 99.12%Epoch 100, cost = 0.046864, acc = 99.10%

Salin selepas log masuk

可以看出最后相同的数据分类，准确率比多层感知机要高（99.10% > 98.59%）。

3、LSTMNet

LSTMNet是使用长短时记忆网络（Long Short-Term Memory, LSTM）构建的神经网络，核心思想是引入了一个名为"记忆单元"的结构，该结构可以在一定程度上保留长期依赖信息，LSTM中的每个单元包括一个输入门（input gate）、一个遗忘门（forget gate）和一个输出门（output gate），这些门的作用是控制信息在记忆单元中的流动，以便网络可以学习何时存储、更新或输出有用的信息。

import numpy as npimport torchfrom torch import optim, nnfrom data_util import load_mnistclass LSTMNet(torch.nn.Module):def __init__(self, input_dim, hidden_dim, output_dim):super(LSTMNet, self).__init__()self.hidden_dim = hidden_dimself.lstm = nn.LSTM(input_dim, hidden_dim)self.linear = nn.Linear(hidden_dim, output_dim, bias=False)def forward(self, x):batch_size = x.size()[1]h0 = torch.zeros([1, batch_size, self.hidden_dim])c0 = torch.zeros([1, batch_size, self.hidden_dim])fx, _ = self.lstm.forward(x, (h0, c0))return self.linear.forward(fx[-1])def train(model, loss, optimizer, x_val, y_val):model.train()optimizer.zero_grad()fx = model.forward(x_val)output = loss.forward(fx, y_val)output.backward()optimizer.step()return output.item()def predict(model, x_val):model.eval()output = model.forward(x_val)return output.data.numpy().argmax(axis=1)def main():torch.manual_seed(42)trX, teX, trY, teY = load_mnist(notallow=False)train_size = len(trY)n_classes = 10seq_length = 28input_dim = 28hidden_dim = 128batch_size = 100epochs = 100trX = trX.reshape(-1, seq_length, input_dim)teX = teX.reshape(-1, seq_length, input_dim)trX = np.swapaxes(trX, 0, 1)teX = np.swapaxes(teX, 0, 1)trX = torch.from_numpy(trX).float()teX = torch.from_numpy(teX).float()trY = torch.tensor(trY)model = LSTMNet(input_dim, hidden_dim, n_classes)loss = torch.nn.CrossEntropyLoss(reductinotallow='mean')optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9)for i in range(epochs):cost = 0.num_batches = train_size // batch_sizefor k in range(num_batches):start, end = k * batch_size, (k + 1) * batch_sizecost += train(model, loss, optimizer,trX[:, start:end, :], trY[start:end])predY = predict(model, teX)print("Epoch %d, cost = %f, acc = %.2f%%" %(i + 1, cost / num_batches, 100. * np.mean(predY == teY)))if __name__ == "__main__":main()

Salin selepas log masuk

（1）以上这段代码通用的部分就不解释了，具体说LSTMNet类：

self.lstm = nn.LSTM(input_dim, hidden_dim)创建一个LSTM层，输入维度为input_dim，隐藏层维度为hidden_dim；
self.linear = nn.Linear(hidden_dim, output_dim, bias=False)创建一个线性层（全连接层），输入维度为hidden_dim，输出维度为output_dim，并设置不使用偏置项（bias）；
h0 = torch.zeros([1, batch_size, self.hidden_dim])初始化LSTM层的隐藏状态h0，全零张量，形状为[1, batch_size, hidden_dim]；
c0 = torch.zeros([1, batch_size, self.hidden_dim])初始化LSTM层的细胞状态c0，全零张量，形状为[1, batch_size, hidden_dim]；
fx, _ = self.lstm.forward(x, (h0, c0))将输入数据x以及初始隐藏状态h0和细胞状态c0传入LSTM层，得到LSTM层的输出fx；
return self.linear.forward(fx[-1])将LSTM层的输出传入线性层进行计算，得到最终输出。这里fx[-1]表示取LSTM层输出的最后一个时间步的数据；

（2）print("第%d轮，损失值=%f，准确率=%.2f%%" % (i + 1, cost / num_batches, 100. * np.mean(predY == teY)))。打印出当前训练轮次的信息，其中包括损失值和准确率，以上代码的输出结果如下：

Epoch 91, cost = 0.000468, acc = 98.57%Epoch 92, cost = 0.000452, acc = 98.57%Epoch 93, cost = 0.000437, acc = 98.58%Epoch 94, cost = 0.000422, acc = 98.57%Epoch 95, cost = 0.000409, acc = 98.58%Epoch 96, cost = 0.000396, acc = 98.58%Epoch 97, cost = 0.000384, acc = 98.57%Epoch 98, cost = 0.000372, acc = 98.56%Epoch 99, cost = 0.000360, acc = 98.55%Epoch 100, cost = 0.000349, acc = 98.55%

Salin selepas log masuk

4、辅助代码

两篇文章的from data_util import load_mnist的data_util.py代码如下：

import gzip
import os
import urllib.request as request
from os import path
import numpy as np

DATASET_DIR = 'datasets/'
MNIST_FILES = ["train-images-idx3-ubyte.gz", "train-labels-idx1-ubyte.gz", "t10k-images-idx3-ubyte.gz", "t10k-labels-idx1-ubyte.gz"]

def download_file(url, local_path):
    dir_path = path.dirname(local_path)
    if not path.exists(dir_path):
        print("创建目录'%s' ..." % dir_path)
        os.makedirs(dir_path)
    print("从'%s'下载中 ..." % url)
    request.urlretrieve(url, local_path)

def download_mnist(local_path):
    url_root = "http://yann.lecun.com/exdb/mnist/"
    for f_name in MNIST_FILES:
        f_path = os.path.join(local_path, f_name)
        if not path.exists(f_path):
            download_file(url_root + f_name, f_path)

def one_hot(x, n):
    if type(x) == list:
        x = np.array(x)
    x = x.flatten()
    o_h = np.zeros((len(x), n))
    o_h[np.arange(len(x)), x] = 1
    return o_h

def load_mnist(ntrain=60000, ntest=10000, notallow=True):
    data_dir = os.path.join(DATASET_DIR, 'mnist/')
    if not path.exists(data_dir):
        download_mnist(data_dir)
    else:
        # 检查所有文件
        checks = [path.exists(os.path.join(data_dir, f)) for f in MNIST_FILES]
        if not np.all(checks):
            download_mnist(data_dir)
    
    with gzip.open(os.path.join(data_dir, 'train-images-idx3-ubyte.gz')) as fd:
        buf = fd.read()
        loaded = np.frombuffer(buf, dtype=np.uint8)
        trX = loaded[16:].reshape((60000, 28 * 28)).astype(float)
    
    with gzip.open(os.path.join(data_dir, 'train-labels-idx1-ubyte.gz')) as fd:
        buf = fd.read()
        loaded = np.frombuffer(buf, dtype=np.uint8)
        trY = loaded[8:].reshape((60000))
    
    with gzip.open(os.path.join(data_dir, 't10k-images-idx3-ubyte.gz')) as fd:
        buf = fd.read()
        loaded = np.frombuffer(buf, dtype=np.uint8)
        teX = loaded[16:].reshape((10000, 28 * 28)).astype(float)
    
    with gzip.open(os.path.join(data_dir, 't10k-labels-idx1-ubyte.gz')) as fd:
        buf = fd.read()
        loaded = np.frombuffer(buf, dtype=np.uint8)
        teY = loaded[8:].reshape((10000))
    
    trX /= 255.
    teX /= 255.
    trX = trX[:ntrain]
    trY = trY[:ntrain]
    teX = teX[:ntest]
    teY = teY[:ntest]
    
    if onehot:
        trY = one_hot(trY, 10)
        teY = one_hot(teY, 10)
    else:
        trY = np.asarray(trY)
        teY = np.asarray(teY)
    
    return trX, teX, trY, teY

Salin selepas log masuk

Atas ialah kandungan terperinci Pembelajaran Mesin |. Tutorial Ringkas PyTorch Bahagian 2. Untuk maklumat lanjut, sila ikut artikel berkaitan lain di laman web China PHP!