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

最新推荐文章于 2024-04-17 17:32:46 发布

火星种萝卜

最新推荐文章于 2024-04-17 17:32:46 发布

阅读量4.8k

点赞数

分类专栏： keras 文章标签： keras

本文链接：https://blog.csdn.net/studyvcmfc/article/details/121019788

版权

keras 专栏收录该内容

29 篇文章

订阅专栏

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。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

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/tensorflow/python/training/tracking/util.py", line 162, in __del__
File "/root/anaconda3/envs/nlp/lib/python3.6/site-packages/tensorflow/python/training/tracking/util.py", line 107, in node_names
TypeError: 'NoneType' object is not callable

原因：

调用模型应该用scores = model.predict(x)而不是用上面的model(x),这两个方法使用的类型不同，前者要求的是list(或ndarray 未再确认)后者要求是Tensor出现了上面的问题。