raise TypeError(‘Inputs to a layer should be tensors. Got: %s‘ % (x,))

最新推荐文章于 2023-05-14 20:00:00 发布

原创

最新推荐文章于 2023-05-14 20:00:00 发布 · 4.8k 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#keras

在使用Nezha Recognizer时，遇到TypeError，因为将非Tensor类型（财经新闻类别）误输入到模型。代码中model.predict()与model(x)的区别导致了输入规格不匹配。解决办法在于确保输入数据符合模型期望的Tensor格式。

File "/home/server-train/data/nezha_recognizer.py", line 50, in predict_nezha
scores = model(x)
File "/root/anaconda3/envs/nlp/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 1013, in __call__
input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
File "/root/anaconda3/envs/nlp/lib/python3.6/site-packages/tensorflow/python/keras/engine/input_spec.py", line 197, in assert_input_compatibility
raise TypeError('Inputs to a layer should be tensors. Got: %s' % (x,))
TypeError: Inputs to a layer should be tensors. Got: 财经,金融,快讯,财经网,科技,汽车,资本,互联网,腾讯,杂志
Exception ignored in: <bound method _CheckpointRestoreCoordinatorDeleter.__del__ of <tensorflow.python.training.tracking.util._CheckpointRestoreCoordinatorDeleter object at 0x7f3a42786a20>>
Traceback (most recent call last):
File "/root/anaconda3/envs/nlp/lib/python3.6/site-packages/t