mindspore.ops.BatchNorm

class mindspore.ops.BatchNorm(*args, **kwargs)[source]

Batch Normalization for input data and updated parameters.

Batch Normalization is widely used in convolutional neural networks. This operation applies Batch Normalization over input to avoid internal covariate shift as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. It rescales and recenters the features using a mini-batch of data and the learned parameters which can be described in the following formula,

\[y = \frac{x - mean}{\sqrt{variance + \epsilon}} * \gamma + \beta\]

where \(\gamma\) is scale, \(\beta\) is bias, \(\epsilon\) is epsilon.

Parameters
  • is_training (bool) – If is_training is True, mean and variance are computed during training. If is_training is False, they’re loaded from checkpoint during inference. Default: False.

  • epsilon (float) – A small value added for numerical stability. Default: 1e-5.

  • momentum (float) – The hyper parameter to compute moving average for running_mean and running_var (e.g. \(new\_running\_mean = (1 - momentum) * running\_mean + momentum * current\_mean\)). Momentum value must be [0, 1]. Default: 0.1.

  • data_format (str) – The optional value for data format, is ‘NHWC’ or ‘NCHW’. Default: “NCHW”.

Inputs:

If is_training is False, inputs are Tensors.

  • input_x (Tensor) - Tensor of shape \((N, C)\), with float16 or float32 data type.

  • scale (Tensor) - Tensor of shape \((C,)\), with float16 or float32 data type.

  • bias (Tensor) - Tensor of shape \((C,)\), has the same data type with scale.

  • mean (Tensor) - Tensor of shape \((C,)\), with float16 or float32 data type.

  • variance (Tensor) - Tensor of shape \((C,)\), has the same data type with mean.

If is_training is True, scale, bias, mean and variance are Parameters.

  • input_x (Tensor) - Tensor of shape \((N, C)\), with float16 or float32 data type.

  • scale (Parameter) - Parameter of shape \((C,)\), with float16 or float32 data type.

  • bias (Parameter) - Parameter of shape \((C,)\), has the same data type with scale.

  • mean (Parameter) - Parameter of shape \((C,)\), with float16 or float32 data type.

  • variance (Parameter) - Parameter of shape \((C,)\), has the same data type with mean.

Outputs:

Tuple of 5 Tensor, the normalized inputs and the updated parameters.

  • output_x (Tensor) - The same type and shape as the input_x. The shape is \((N, C)\).

  • updated_scale (Tensor) - Tensor of shape \((C,)\).

  • updated_bias (Tensor) - Tensor of shape \((C,)\).

  • reserve_space_1 (Tensor) - Tensor of shape \((C,)\).

  • reserve_space_2 (Tensor) - Tensor of shape \((C,)\).

Raises
  • TypeError – If is_training is not a bool.

  • TypeError – If dtype of epsilon or momentum is not float.

  • TypeError – If data_format is not a str.

  • TypeError – If input_x, scale, bias, mean or variance is not a Tensor.

  • TypeError – If dtype of input_x, scale or mean is neither float16 nor float32.

Supported Platforms:

Ascend CPU

Examples

>>> input_x = Tensor(np.ones([2, 2]), mindspore.float32)
>>> scale = Tensor(np.ones([2]), mindspore.float32)
>>> bias = Tensor(np.ones([2]), mindspore.float32)
>>> mean = Tensor(np.ones([2]), mindspore.float32)
>>> variance = Tensor(np.ones([2]), mindspore.float32)
>>> batch_norm = ops.BatchNorm()
>>> output = batch_norm(input_x, scale, bias, mean, variance)
>>> print(output)
(Tensor(shape=[2, 2], dtype=Float32, value=
[[ 1.00000000e+00, 1.00000000e+00],
 [ 1.00000000e+00, 1.00000000e+00]]), Tensor(shape=[2], dtype=Float32, value=
 [ 1.00000000e+00, 1.00000000e+00]), Tensor(shape=[2], dtype=Float32, value=
 [ 1.00000000e+00, 1.00000000e+00]), Tensor(shape=[2], dtype=Float32, value=
 [ 1.00000000e+00, 1.00000000e+00]), Tensor(shape=[2], dtype=Float32, value=
 [ 1.00000000e+00, 1.00000000e+00]))