在 MxNet 中添加损失函数 - "Operator _copyto is non-differentiable because it didn't register FGradient attribute"

Question

我有一个生成训练数据的系统，我想将损失函数加在一起以获得批量大小。我正在尝试做 (full code at commit in question),

for epoch in range(100):
    with mx.autograd.record():
        loss = 0.0
        for k in range(40):
            (i, x), (j, y) = random.choice(data), random.choice(data)
            # Just compute loss on last output
            if i == j:
                loss = loss - l2loss(net(mx.nd.array(x)), net(mx.nd.array(y)))
            else:
                loss = loss + l2loss(net(mx.nd.array(x)), net(mx.nd.array(y)))
        loss.backward()
    trainer.step(BATCH_SIZE)

但是我得到了这样的错误，

---------------------------------------------------------------------------
MXNetError                                Traceback (most recent call last)
<ipython-input-39-14981406278a> in <module>()
     21             else:
     22                 loss = loss + l2loss(net(mx.nd.array(x)), net(mx.nd.array(y)))
---> 23         loss.backward()
     24     trainer.step(BATCH_SIZE)
     25     avg_loss += mx.nd.mean(loss).asscalar()

... More trace ...

MXNetError: [16:52:49] src/pass/gradient.cc:187: Operator _copyto is non-differentiable because it didn't register FGradient attribute.

如何像我尝试的那样逐步添加损失函数？

Answer 1

您使用的是哪个版本的 MXNet？我无法使用最新的代码库重现这一点。您可以尝试 GitHub master 分支或版本 0.12.

在 MxNet 中添加损失函数 - "Operator _copyto is non-differentiable because it didn't register FGradient attribute"

Adding loss functions in MxNet - "Operator _copyto is non-differentiable because it didn't register FGradient attribute"

mxnet