MNIST handwritten data recognition by RNN

---

RNN Realization MNIST Handwritten data recognition

One 、 Code

import torch
import torchvision.datasets
from torch import nn
import torch.utils.data as Data
EPOCH=1 # How many times to train 
BATCH_SIZE =64 # Batch training quantity 
TIME_STEP=28 #nn Time steps / Picture height 
INPUT_SIZE=28 #nn Input value per step / Pixels per line of the picture 
LR=0.01 # Learning rate 

DOWNLOAD_MNIST=False #mnist data 

# Batch training 
train_data = torchvision.datasets.MNIST(root='./mnist',train=True,transform=torchvision.transforms.ToTensor(),download=DOWNLOAD_MNIST)
train_loader = Data.DataLoader(dataset=train_data,batch_size=BATCH_SIZE,shuffle=True)
# test 
test_data = torchvision.datasets.MNIST(root='./mnist',train=False,transform=torchvision.transforms.ToTensor())
test_x = test_data.test_data.type(torch.FloatTensor)[:2000]/255 #shape(2000,28,28)
test_y = test_data.test_labels.numpy()[:2000]

class RNN(nn.Module):
    def __init__(self):
        super(RNN, self).__init__()

        self.rnn =nn.LSTM(
            input_size=INPUT_SIZE,
            hidden_size=64,
            num_layers=1,
            batch_first=True, #(bach_size,time_step)
        )
        self.out = nn.Linear(64,10)
    def forward(self,x):
        r_out,(h_n,h_c) = self.rnn(x,None)
        out = self.out(r_out[:,-1,:])
        return out

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

for epoch in range(EPOCH):
    for step,(b_x,b_y) in enumerate(train_loader):
        b_x = b_x.view(-1,28,28)
        output=rnn(b_x)
        loss = loss_func(output,b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        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')

Two 、 Realization effect