Exceptions for package
keras
github stars 52268

5
views 659
`tape` is required when a `Tensor` loss is passed. / keras
5
views 97
The number of input channels must be evenly divisible by the number of groups. Received groups=(param1), but the input has (param1) channels (full input shape is (param1)). / keras
5
views 91
Received non-atomic and non-sequence element: (param1) / keras
5
views 60
Invalid merge mode. Merge mode should be one of ("sum", "mul", "ave", "concat", None) / keras
5
views 60
num_oov_indices must be greater than or equal to 0. You passed %s / keras
5
views 47
The length of boundaries should be 1 less than the length of values / keras
5
views 43
The global policy can only be set in TensorFlow 2 or if V2 dtype behavior has been set. To enable V2 dtype behavior, call "tf.compat.v1.keras.layers.enable_v2_dtype_behavior()" / keras
5
views 27
`momentum` must be between [0, 1]. / keras
5
views 17
`inputs` should be a list. / keras
5
views 17
end_index must be lower than the length of the data. Got: end_index=%s / keras
4
views 714
When providing an infinite dataset, you must specify the number of steps to run (if you did not intend to create an infinite dataset, make sure to not call `repeat()` on the dataset). / keras
4
views 479
It looks like you are subclassing `Model` and you forgot to call `super(YourClass, self).__init__()`. Always start with this line. / keras
First Prev Page 2 of 68 Next Last