模型的搭建
import torch
import torch.nn as nn
class RNN(nn.Module):
def __init__(self):
super(RNN, self).__init__()
self.rnn = nn.LSTM(
input_size=28,
hidden_size=64,
num_layers=1,
batch_first=True,
)
self.out = nn.Linear(64, 10)
self.relu=nn.Sigmoid()
def forward(self, x):
# x shape (batch, time_step, input_size)
# r_out shape (batch, time_step, output_size)
# h_n shape (n_layers, batch, hidden_size)
# h_c shape (n_layers, batch, hidden_size)
r_out, (h_n, h_c) = self.rnn(x, None) # None represents zero initial hidden state
# choose r_out at the last time step
out = self.out(r_out[:, -1, :])
out=self.relu(out)
return out
if __name__=='__main__':
model=RNN()
input=torch.randn(1,28,28)
output=model(input)
print(output.shape)
模型的训练
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
from models import RNN
# Hyper Parameters
EPOCH = 1 # train the training data n times, to save time, we just train 1 epoch
BATCH_SIZE = 64
TIME_STEP = 28 # rnn time step / image height
INPUT_SIZE = 28 # rnn input size / image width
LR = 0.01 # learning rate
# Mnist digital dataset
train_data = torchvision.datasets.MNIST(
root='./mnist/',
train=True, # this is training data
transform=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=True, # download it if you don't have it
)
print(train_data.train_data.size()) # (60000, 28, 28)
print(train_data.train_labels.size()) # (60000)
# 加载训练数据集
train_loader = torch.utils.data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
# 加载测试数据集,选取2000个样本以加快测试速度
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False, transform=transforms.ToTensor())
test_x = test_data.test_data.type(torch.FloatTensor)[:2000]/255. # shape (2000, 28, 28) value in range(0,1)
test_y = test_data.test_labels.numpy()[:2000] # covert to numpy array
rnn = RNN()
print(rnn)
optimizer = torch.optim.Adam(rnn.parameters(), lr=LR)
loss_func = nn.CrossEntropyLoss()
# 训练
for epoch in range(EPOCH):
for step, (b_x, b_y) in enumerate(train_loader): # gives batch data
b_x = b_x.view(-1, 28, 28) # reshape x to (batch, time_step, input_size)
output = rnn(b_x) # rnn 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 = rnn(test_x) # (samples, time_step, input_size)
pred_y = torch.max(test_output, 1)[1].data.numpy()
accuracy = float((pred_y == test_y).astype(int).sum()) / float(test_y.size)
print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy(), '| test accuracy: %.2f' % accuracy)
# print 10 predictions from test data
test_output = rnn(test_x[:10].view(-1, 28, 28))
pred_y = torch.max(test_output, 1)[1].data.numpy()
print(pred_y, 'prediction number')
print(test_y[:10], 'real number')
