import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt
# torch.manual_seed(1) # reproducible
# Hyper Parameters
EPOCH = 1 # train the training data n times, to save time, we just train 1 epoch
BATCH_SIZE = 50
LR = 0.001 # learning rate
DOWNLOAD_MNIST = False
train_data = torchvision.datasets.MNIST(
root='./mnist/',
train=True, # this is training data
transform=torchvision.transforms.ToTensor(), # Converts a PIL.Image or numpy.ndarray to
# torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
download=DOWNLOAD_MNIST,
)
# plot one example
print(train_data.train_data.size()) # (60000, 28, 28)
print(train_data.train_labels.size()) # (60000)
plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[0])
plt.show()
# Data Loader for easy mini-batch return in training, the image batch shape will be (50, 1, 28, 28)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
# pick 2000 samples to speed up testing
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000]/255. # shape from (2000, 28, 28) to (2000, 1, 28, 28), value in range(0,1)
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, #s=1,padding=(k-1)/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.conv3 = nn.Sequential(
nn.Conv2d(32, 32, 5, 1, 2),
nn.ReLU(),
nn.MaxPool2d(2),
)
self.out=nn.Linear(32*7*7,10) # 展平
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
cnn = CNN()
print(cnn)
optimizer = torch.optim.Adam(cnn.parameters(), lr=LR) # optimize all cnn parameters
loss_func = nn.CrossEntropyLoss() # the target label is not one-hotted
# training and testing
for epoch in range(EPOCH):
for step, (b_x, b_y) in enumerate(train_loader): # gives batch data, normalize x when iterate train_loader
output = cnn(b_x) # cnn output
loss = loss_func(output, b_y) # cross entropy loss
optimizer.zero_grad() # clear gradients for this training step
loss.backward() # backpropagation, compute gradients
optimizer.step() # apply gradients
if step % 50 == 0:
test_output = cnn(test_x)
pred_y = torch.max(test_output, 1)[1].data.squeeze()
accuracy = sum(pred_y == test_y)/test_y.size(0)
print('Epoch: ', epoch, '| train loss: %.4f' % loss.item(), '| test accuracy: %.2f' % accuracy)
# print 10 predictions from test data
test_output = cnn(test_x[:10])
pred_y = torch.max(test_output, 1)[1].data.numpy().squeeze()
print(pred_y, 'prediction number')
print(test_y[:10].numpy(), 'real number')