tf.reduce_Meanとtf.reduce_min

# 'x' is [[1., 1.]
#         [2., 2.]]
tf.reduce_mean(x) ==> 1.5
tf.reduce_mean(x, 0) ==> [1.5, 1.5]
tf.reduce_mean(x, 1) ==> [1.,  2.]

Args:

input_tensor : The tensor to reduce. Should have numeric type.

axis : The dimensions to reduce. If  None  (the default), reduces all dimensions.

keep_dims : If true, retains reduced dimensions with length 1.

name : A name for the operation (optional).

reduction_indices : The old (deprecated) name for axis.

Returns:
The reduced tensor.
numpy compatibility
Equivalent to np.mean
しないで、これはベクトルの を するので、 のパラメータをプラスして の で を して、 に を しません
tf.reduce_min reduce_min(
    input_tensor,
    axis=None,
    keep_dims=False,
    name=None,
    reduction_indices=None
)

Defined in  tensorflow/python/ops/math_ops.py .
See the guide: Math > Reduction
Computes the minimum of elements across dimensions of a tensor.
Reduces  input_tensor  along the dimensions given in  axis . Unless  keep_dims  is true, the rank of the tensor is reduced by 1 for each entry in  axis . If  keep_dims  is true, the reduced dimensions are retained with length 1.
If  axis  has no entries, all dimensions are reduced, and a tensor with a single element is returned.
Args:

input_tensor : The tensor to reduce. Should have numeric type.

axis : The dimensions to reduce. If  None  (the default), reduces all dimensions.

keep_dims : If true, retains reduced dimensions with length 1.

name : A name for the operation (optional).

reduction_indices : The old (deprecated) name for axis.

Returns:
The reduced tensor.
numpy compatibility
Equivalent to np.min
これが ベクトルの で、 のパラメータをプラスして の で を して、 に することを りません