https://aistudio.baidu.com/aistudio/projectdetail/2390780

尝试上面的代码，在它训练完成后，我希望放入1条新数据进行预测，已经照着前面数据的清洗和特征化做好了。

最后再预测的时候，就报错了

predict_dataset = BuildDataSet(df_data_test_copy, dense_features, is_test=True)

predict_loader = DataLoader(predict_dataset,
batch_size=1,
shuffle=False)

for (userid, docid, network, device_t, os, province, city, age, gender, category1st, category2nd, dense_features, keywords, click) in predict_loader():
     predict, loss = model(userid, docid, network, device_t, os,
                           province, city, age, gender, category1st,
                           category2nd, dense_features, keywords, click)

错误如下：

---------------------------------------------------------------------------ValueError Traceback (most recent call last) in
17 predict, loss = model(userid, docid, network, device_t, os,
18 province, city, age, gender, category1st,
---> 19 category2nd, dense_features, keywords, click)
20
21
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py in __call__(self, *inputs, **kwargs)
900 self._built = True
901
--> 902 outputs = self.forward(*inputs, **kwargs)
903
904 for forward_post_hook in self._forward_post_hooks.values():
in forward(self, userid, docid, network, device_t, os, province, city, age, gender, category1st, category2nd, dense_features, keywords, click)
211 pred = paddle.cast(pred, 'float32')
212 click = paddle.cast(click, 'float32')
--> 213 loss = F.binary_cross_entropy(pred, click)
214
215 return pred, loss
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/nn/functional/loss.py in binary_cross_entropy(input, label, weight, reduction, name)
116
117 if in_dygraph_mode():
--> 118 out = core.ops.bce_loss(input, label)
119 if weight is not None:
120 out = core.ops.elementwise_mul(out, weight, 'axis', -1)
ValueError: (InvalidArgument) Input(X) and Input(Label) shall have the same rank.But received: the rank of Input(X) is [0], the rank of Input(Label) is [1].
[Hint: Expected rank == labels_dims.size(), but received rank:0 != labels_dims.size():1.] (at /paddle/paddle/fluid/operators/bce_loss_op.cc:43)
[operator < bce_loss > error]

我对比我传入的特征数据和 现有代码验证模型时传入的特征数据，shape 都一样，现在有点不知道是什么问题了; 请大佬帮助指点一下，应该去哪里找问题