huang
Reputation: 1167
WARNING:tensorflow:Model was constructed with shape (None, 188) for input, but it was called on an input with incompatible shape (188,)
Can someone help me to fix this? tensorflow is really annoying.
WARNING:tensorflow:Model was constructed with shape (None, 188) for input KerasTensor(type_spec=TensorSpec(shape=(None, 188), dtype=tf.float32, name='input_9'), name='input_9', description="created by layer 'input_9'"), but it was called on an input with incompatible shape (188,).
Upvotes: 1
Views: 753
Answers (1)
AloneTogether
Reputation: 26698
You seem to be missing a dimension. Try batching your data:
train_set = train_set.batch(32)
Upvotes: 3
Related Questions
- Tensorflow / Keras ValueError: Input 0 of layer "model" is incompatible with the layer: expected shape=(None, 224, 224, 3), found shape=(32, 224, 3)
- WARNING : tensorflow:Model was constructed with shape
- ValueError: Shapes (None,) and (None, 150, 150, 6) are incompatible
- Model was constructed with shape (None, 65536) but it was called on an input with incompatible shape (None, 65536, None)
- Tensorflow:Model was constructed with shape (None, 28, 28) , but it was called on an input with incompatible shape (None, 28)
- WARNING:tensorflow:Model was constructed with shape (4, 112, 112, 3) for input ..., but it was called on an input with incompatible shape ((None, 112)
- ValueError: Shapes (None, 1) and (None, 64) are incompatible Keras
- tensorflow:Model was constructed with shape (None, None, 6), but it was called on an input with incompatible shape
- WARNING:tensorflow:Model was constructed with shape for input Tensor(). but it was called on an input with incompatible shape
- WARNING:tensorflow:Model was constructed with shape (None, ....)