error in copy-task-plots.ipynb

[bw-xu]

when run the code piece

seq_len = 60
_, x, y = next(iter(dataloader(1, 1, 8, seq_len, seq_len)))
result = evaluate(model.net, model.criterion, x, y)
y_out = result['y_out']

there comes the error information:

IndexError                                Traceback (most recent call last)
<ipython-input-41-127bd44fb490> in <module>()
      1 seq_len = 60
      2 _, x, y = next(iter(dataloader(1, 1, 8, seq_len, seq_len)))
----> 3 result = evaluate(model.net, model.criterion, x, y)
      4 y_out = result['y_out']

D:\GithubProjs\pytorch-ntm-master\train.py in evaluate(net, criterion, X, Y)
    151 
    152     result = {
--> 153         'loss': loss.data[0],
    154         'cost': cost / batch_size,
    155         'y_out': y_out,

IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number

how to solve it?

[muyi95]

Did you solve this problem?

[hankyul2]

You should change data[0] to item(). It is described in your error log. And you should also change it in draw_sequence. I tried it and success without that error.

 def evaluate(net, criterion, X, Y):
    """Evaluate a single batch (without training)."""
    inp_seq_len = X.size(0)
    outp_seq_len, batch_size, _ = Y.size()

    # New sequence
    net.init_sequence(batch_size)

    # Feed the sequence + delimiter
    states = []
    for i in range(inp_seq_len):
        o, state = net(X[i])
        states += [state]

    # Read the output (no input given)
    y_out = torch.zeros(Y.size())
    for i in range(outp_seq_len):
        y_out[i], state = net()
        states += [state]

    loss = criterion(y_out, Y)

    y_out_binarized = y_out.clone().data
    y_out_binarized.apply_(lambda x: 0 if x < 0.5 else 1)

    # The cost is the number of error bits per sequence
    cost = torch.sum(torch.abs(y_out_binarized - Y.data))

    result = {
        'loss': loss.item(),
        'cost': cost / batch_size,
        'y_out': y_out,
        'y_out_binarized': y_out_binarized,
        'states': states
    }

    return result

def draw_sequence(y, u=12):
    seq_len = y.size(0)
    seq_width = y.size(2)
    inset = u // 8
    pad = u // 2
    width = seq_len * u + 2 * pad
    height = seq_width * u + 2 * pad
    im = Image.new('L', (width, height))
    draw = ImageDraw.ImageDraw(im)
    draw.rectangle([0, 0, width, height], fill=250)
    for i in range(seq_len):
        for j in range(seq_width):
            val = 1 - y[i, 0, j].item()
            draw.rectangle([pad + i*u + inset,
                            pad + j*u + inset,
                            pad + (i+1)*u - inset,
                            pad + (j+1)*u - inset], fill=cmap(val))

    return im