MCPcopy Create free account
hub / github.com/DeepRec-AI/DeepRec / shape

Function shape

tensorflow/python/keras/backend.py:1124–1153  ·  view source on GitHub ↗

Returns the symbolic shape of a tensor or variable. Arguments: x: A tensor or variable. Returns: A symbolic shape (which is itself a tensor). Examples: ```python # TensorFlow example >>> from keras import backend as K >>> tf_session = K.get_session() >>> val = np.arra

(x)

Source from the content-addressed store, hash-verified

1122
1123@keras_export('keras.backend.shape')
1124def shape(x):
1125 """Returns the symbolic shape of a tensor or variable.
1126
1127 Arguments:
1128 x: A tensor or variable.
1129
1130 Returns:
1131 A symbolic shape (which is itself a tensor).
1132
1133 Examples:
1134
1135 ```python
1136 # TensorFlow example
1137 >>> from keras import backend as K
1138 >>> tf_session = K.get_session()
1139 >>> val = np.array([[1, 2], [3, 4]])
1140 >>> kvar = K.variable(value=val)
1141 >>> input = keras.backend.placeholder(shape=(2, 4, 5))
1142 >>> K.shape(kvar)
1143 <tf.Tensor 'Shape_8:0' shape=(2,) dtype=int32>
1144 >>> K.shape(input)
1145 <tf.Tensor 'Shape_9:0' shape=(3,) dtype=int32>
1146 # To get integer shape (Instead, you can use K.int_shape(x))
1147 >>> K.shape(kvar).eval(session=tf_session)
1148 array([2, 2], dtype=int32)
1149 >>> K.shape(input).eval(session=tf_session)
1150 array([2, 4, 5], dtype=int32)
1151 ```
1152 """
1153 return array_ops.shape(x)
1154
1155
1156@keras_export('keras.backend.int_shape')

Callers 2

batch_flattenFunction · 0.70
conv2d_transposeFunction · 0.70

Calls 1

shapeMethod · 0.45

Tested by

no test coverage detected