以PyTorch實作卷積神經網路模型
- MNIS手寫數據
import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt
torch.manual_seed(1)
EPOCH = 10 #訓練數據10次
BATCH_SIZE = 50
LR = 0.001 #學習率
DOWNLOAD_MNIST = True
train_data = torchvision.datasets.MNIST(
root='./mnist/',
train=True,
transform=torchvision.transforms.ToTensor(),
download=DOWNLOAD_MNIST
)
#對(50,1,28,28)進行批次訓練
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)
#測試前1000個樣本
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:1000]/255.
test_y = test_data.test_labels[:1000]
- CNN模型
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)
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x)
x = x.view(x.size(0), -1)
output = self.out(x)
return output, x
cnn = CNN()
print(cnn)
- 訓練
optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)
loss_func = nn.CrossEntropyLoss()
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)[0]
loss = loss_func(output, b_y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if step % 50 == 0:
test_output, last_layer = 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)
- 可視化訓練
if HAS_SK:
tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)
plot_only = 500
low_dim_embs = tsne.fit_transform(last_layer.data.numpy()[:plot_only, :])
labels = test_y.numpy()[:plot_only]
plot_with_labels(low_dim_embs, labels)
plt.ioff()
- 取十個數據來驗證預測的值是否正確
test_output, _ = cnn(test_x[:10])
pred_y = torch.max(test_output, 1)[1].data.numpy()
print(pred_y, 'prediction number')
print(test_y[:10].numpy(), 'real number')
參考資料: