Unfold function？ MNIST use a 5-step LSTM model to preprocess the input data

vision
1

I split one image of MNIST into 5 segments, for example, 28*28 --> 28x5x5 (delete the left three columns). In this step, I used “fold” function to do this.


import torch
from torch import nn
from torch.autograd import Variable
import torchvision.datasets as dsets
import torch.utils.data as Data
import torchvision

torch.manual_seed(1)

EPOCH = 1
BATCH_SIZE = 64
TIME_STEP = 28
INPUT_SIZE = 28
LR = 0.01
DOWNLOAD_MNIST = True

train_data = dsets.MNIST(root='./mnist',
                         train=True,
                         transform=torchvision.transforms.ToTensor(),
                         download=DOWNLOAD_MNIST)

test_data = torchvision.datasets.MNIST(root='./mnist', train=False)

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

test_x = Variable(torch.unsqueeze(test_data.test_data, dim=1), volatile=True).type(torch.FloatTensor) / 255
test_y = test_data.test_labels


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

        self.rnn = nn.LSTM(
            input_size=100,
            hidden_size=64,
            num_layers=1,
            batch_first=True,
        )
        self.lstm_skb = LSTMTCN(100, 1, 10, 10, 100, 3, 100)
        self.out = nn.Linear(64, 10)

    def forward(self, x):
        x = self.lstm_skb(x)
        r_out, (h_n, h_c) = self.rnn(x, None)

        out = self.out(r_out[:, -1, :])
        return out


rnn = RNN()
print(rnn)

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

for epoch in range(EPOCH):
    for step, (x, y) in enumerate(train_loader):
        b_x = Variable(x.view(-1, 28, 28))
        b_y = Variable(y)

        output = rnn(b_x)
        loss = loss_func(output, b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        print('Epoch: ', epoch, '| train loss:%.4f' % loss.item())