Returns a reference to this variable. You usually do not need to call this method as all ops that need a reference to the variable call it automatically. Returns is a `Tensor` which holds a reference to the variable. You can assign a new value to the variable by passing the tensor
(self)
| 2164 | return array_ops.identity(self._variable, name="read") |
| 2165 | |
| 2166 | def _ref(self): |
| 2167 | """Returns a reference to this variable. |
| 2168 | |
| 2169 | You usually do not need to call this method as all ops that need a reference |
| 2170 | to the variable call it automatically. |
| 2171 | |
| 2172 | Returns is a `Tensor` which holds a reference to the variable. You can |
| 2173 | assign a new value to the variable by passing the tensor to an assign op. |
| 2174 | See `tf.Variable.value` if you want to get the value of the |
| 2175 | variable. |
| 2176 | |
| 2177 | Returns: |
| 2178 | A `Tensor` that is a reference to the variable. |
| 2179 | """ |
| 2180 | return self._variable |
| 2181 | |
| 2182 | def set_shape(self, shape): |
| 2183 | """Overrides the shape for this variable. |
no outgoing calls