dropout¶
- dragon.vm.tensorflow.nn.- dropout(
 x,
 rate,
 name=None,
 **kwargs
 )[source]¶
- Set the elements of input to zero randomly. [Srivastava et.al, 2014]. - The Dropout function is defined as: \[\text{Dropout}(x) = x * \text{Bernoulli}(p=1 - prob) \]- Examples: - x = tf.ones((2, 3), 'float32') print(tf.nn.dropout(x, 0.5)) - Parameters:
- x (dragon.Tensor) – The tensor \(x\).
- rate (Union[float, dragon.Tensor]) – The probability to zero an element.
- name (str, optional) – The operation name.
 
 - Returns:
- dragon.Tensor – The output tensor. 
 
