3.6_softmax-regression-scratch.ipynb 运行错误

[davidwang9527]

bug描述 3.6_softmax-regression-scratch.ipynb "3.6.8 预测"下的cell运行错误: RuntimeError Traceback (most recent call last)

in 2 3 true_labels = d2l.get_fashion_mnist_labels(y.numpy()) ----> 4 pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(dim=1).numpy()) 5 titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)] 6 RuntimeError: Can't call numpy() on Variable that requires grad. Use var.detach().numpy() instead. 原版本： pytorch:0.4.1 torchvision:0.2.1 **版本信息** pytorch:1.5.0 torchvision:0.6.0 torchtext: ...

[davidwang9527]

该cell的代码改为如下代码可避免报错： X, y = iter(test_iter).next()

true_labels = d2l.get_fashion_mnist_labels(y.detach().numpy()) pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(dim=1).detach().numpy()) titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]

d2l.show_fashion_mnist(X[0:9], titles[0:9])

[ShusenTang]

该cell的代码改为如下代码可避免报错： X, y = iter(test_iter).next()

true_labels = d2l.get_fashion_mnist_labels(y.detach().numpy()) pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(dim=1).detach().numpy()) titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]

d2l.show_fashion_mnist(X[0:9], titles[0:9])

嗯，应该是新版本的PyTorch不支持call numpy() on Variable that requires grad了，后续会修正，感谢指出。

[wang321123]

是的，我今天也遇到了这样的问题。