pytorch实现CNN卷积神经网络

本文为大家讲解了pytorch实现CNN卷积神经网络，供大家参考，具体内容如下

我对卷积神经网络的一些认识

卷积神经网络是时下最为流行的一种深度学习网络，由于其具有局部感受野等特性，让其与人眼识别图像具有相似性，因此被广泛应用于图像识别中，本人是研究机械故障诊断方面的，一般利用旋转机械的振动信号作为数据。

对一维信号，通常采取的方法有两种，第一，直接对其做一维卷积，第二，反映到时频图像上，这就变成了图像识别，此前一直都在利用keras搭建网络，最近学了pytroch搭建cnn的方法，进行一下代码的尝试。所用数据为经典的minist手写字体数据集

import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt
`EPOCH = 1
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = True

从网上下载数据集：

```python
train_data = torchvision.datasets.MNIST(
root="./mnist/",
train = True,
transform=torchvision.transforms.ToTensor(),
download = DOWNLOAD_MNIST,
)

print(train_data.train_data.size())
print(train_data.train_labels.size())

```plt.imshow(train_data.train_data[0].numpy(), cmap='autumn')
plt.title("％i" ％ train_data.train_labels[0])
plt.show()

train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

test_data = torchvision.datasets.MNIST(root="./mnist/", train=False)
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000]/255.

test_y = test_data.test_labels[:2000]

class CNN(nn.Module):
def __init__(self):
 super(CNN, self).__init__()
 self.conv1 = nn.Sequential(
  nn.Conv2d(
   in_channels=1,
   out_channels=16,
   kernel_size=5,
   stride=1,
   padding=2,
  ),

nn.ReLU(),
  nn.MaxPool2d(kernel_size=2),
 )

self.conv2 = nn.Sequential(
  nn.Conv2d(16, 32, 5, 1, 2),
  nn.ReLU(),
  nn.MaxPool2d(2),
 )

self.out = nn.Linear(32*7*7, 10) # fully connected layer, output 10 classes

def forward(self, x):
 x = self.conv1(x)
 x = self.conv2(x)
 x = x.view(x.size(0), -1) # flatten the output of conv2 to (batch_size, 32*7*7)
 output = self.out(x)
 return output

optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)
loss_func = nn.CrossEntropyLoss()

from matplotlib import cm
try: from sklearn.manifold import TSNE; HAS_SK = True
except: HAS_SK = False; print('Please install sklearn for layer visualization')
def plot_with_labels(lowDWeights, labels):
plt.cla()
X, Y = lowDWeights[:, 0], lowDWeights[:, 1]
for x, y, s in zip(X, Y, labels):
 c = cm.rainbow(int(255 * s / 9)); plt.text(x, y, s, backgroundcolor=c, fontsize=9)
plt.xlim(X.min(), X.max()); plt.ylim(Y.min(), Y.max()); plt.title('Visualize last layer'); plt.show(); plt.pause(0.01)

plt.ion()

for epoch in range(EPOCH):
for step, (b_x, b_y) in enumerate(train_loader):
 output = cnn(b_x)
 loss = loss_func(output, b_y)
 optimizer.zero_grad()
 loss.backward()
 optimizer.step()

if step ％ 50 == 0:
  test_output = cnn(test_x)
  pred_y = torch.max(test_output, 1)[1].data.numpy()
  accuracy = float((pred_y == test_y.data.numpy()).astype(int).sum()) / float(test_y.size(0))
  print("Epoch: ", epoch, "| train loss: ％.4f" ％ loss.data.numpy(),
    "| test accuracy: ％.2f" ％ accuracy)

plt.ioff()

来源：https://blog.csdn.net/xiaoshan0609/article/details/104382920