max_pool¶

dragon.vm.tensorflow.nn.max_pool(
  input,
  ksize,
  strides,
  padding='VALID',
  data_format='NHWC',
  name=None
)[source]¶

Apply the n-dimension max pooling.

• If data_format is 'NCHW', excepts input shape \((N, C, D1, D2, ...)\), and output shape is \((N, C, D1_{\text{out}}, D2_{\text{out}}, ...)\).
• If data_format is 'NHWC', excepts input shape \((N, D1, D2, ..., C)\), and output shape is \((N, D1_{\text{out}}, D2_{\text{out}}, ..., C)\).
• padding could be 'VALID', 'SAME' or explicit padding size.

Examples:

for i in range(3):
    ndim = i + 1
    x = tf.ones((1,) + (2,) * ndim + (2,))
    y = tf.nn.max_pool(x, ksize=(2,) * ndim, strides=2)
    assert y.shape == (1,) + (1,) * ndim + (2,)

Parameters:

• input (dragon.Tensor) – The input tensor.
• ksize (Union[int, Sequence[int]]) – The size of pooling window.
• strides (Union[int, Sequence[int]]) – The stride of pooling window.
• padding (Union[int, Sequence[int], str], optional, default='VALID') – The padding algorithm or size.
• data_format (str, optional, default='NHWC') – 'NCHW' or 'NHWC'.
• name (str, optional) – The operation name.

Returns:

dragon.Tensor – The output tensor.