 View source on GitHub |
Symbolic tensor -- encapsulates a shape and a dtype.
tf.keras.KerasTensor( shape, dtype='float32', sparse=False, record_history=True, name=None ) You can use KerasTensor instances to build computation graphs of Keras operations, such as keras.Function objects or Functional keras.models.Model objects.
Example:
x = keras.KerasTensor(shape=(3, 4), dtype="float32")x.shape(3, 4)x.dtypefloat32
Calling a Keras operation (including a layer or a model) on a KerasTensor instance will return another KerasTensor instance with the appropriate shape and dtype. This is called a "symbolic call" (since there is no actual data involved). The computation of the correct output shape and dtype is called "static shape inference".
Attributes | |
|---|---|
ndim | |
Methods
reshape
reshape( newshape ) squeeze
squeeze( axis=None ) __abs__
__abs__() __add__
__add__( other ) __and__
__and__( other ) __array__
__array__() __bool__
__bool__() __div__
__div__( other ) __floordiv__
__floordiv__( other ) __ge__
__ge__( other ) Return self>=value.
__getitem__
__getitem__( key ) __gt__
__gt__( other ) Return self>value.
__invert__
__invert__() __iter__
__iter__() __le__
__le__( other ) Return self<=value.
__lt__
__lt__( other ) Return self<value.
__matmul__
__matmul__( other ) __mod__
__mod__( other ) __mul__
__mul__( other ) __ne__
__ne__( other ) Return self!=value.
__neg__
__neg__() __or__
__or__( other ) __pow__
__pow__( other ) __radd__
__radd__( other ) __rand__
__rand__( other ) __rdiv__
__rdiv__( other ) __rfloordiv__
__rfloordiv__( other ) __rmatmul__
__rmatmul__( other ) __rmod__
__rmod__( other ) __rmul__
__rmul__( other ) __ror__
__ror__( other ) __rpow__
__rpow__( other ) __rsub__
__rsub__( other ) __rtruediv__
__rtruediv__( other ) __rxor__
__rxor__( other ) __sub__
__sub__( other ) __truediv__
__truediv__( other ) __xor__
__xor__( other )