tf.one_hot(indices, depth, on_value=None, off_value=None, axis=None)
2017-03-15 21:20
459 查看
Tensor Transformations > Slicing and Joining
See the guide: Tensor Transformations > Slicing and Joining
Returns a one-hot tensor.
The locations represented by indices in
while all other locations take value
have matching data types. If
type as specified by
If
type
If
type
If the input
the output will have rank
the new axis is appended at the end).
If
If
the output shape will be:
If
If
if one or both are passed in. If none of
or
default to the value
Note: If a non-numeric data type output is desired (
etc.), both
provided to
Suppose that
Then output is
Suppose that
Then output is
Using default values for
The output will be
indices.
defining the depth of the one hot dimension.
defining the value to fill in output when
defining the value to fill in output when
to fill (default: -1, a new inner-most axis).
type of the output tensor.
tensor.
of either
match
of
match one another
Defined in
tf.one_hot(indices, depth, on_value=None, off_value=None, axis=None, dtype=None, name=None)
tf.one_hot(indices, depth, on_value=None, off_value=None, axis=None, dtype=None, name=None)
See the guide: Tensor Transformations > Slicing and JoiningReturns a one-hot tensor.
The locations represented by indices in
indicestake value
on_value,
while all other locations take value
off_value.
on_valueand
off_valuemust
have matching data types. If
dtypeis also provided, they must be the same data
type as specified by
dtype.
If
on_valueis not provided, it will default to the value
1with
type
dtype
If
off_valueis not provided, it will default to the value
0with
type
dtype
If the input
indicesis rank
N,
the output will have rank
N+1. The new axis is created at dimension
axis(default:
the new axis is appended at the end).
If
indicesis a scalar the output shape will be a vector of length
depth
If
indicesis a vector of length
features,
the output shape will be:
features x depth if axis == -1 depth x features if axis == 0
If
indicesis a matrix (batch) with shape
[batch, features], the output shape will be:
batch x features x depth if axis == -1 batch x depth x features if axis == 1 depth x batch x features if axis == 0
If
dtypeis not provided, it will attempt to assume the data type of
on_valueor
off_value,
if one or both are passed in. If none of
on_value,
off_value,
or
dtypeare provided,
dtypewill
default to the value
tf.float32.
Note: If a non-numeric data type output is desired (
tf.string,
tf.bool,
etc.), both
on_valueand
off_valuemust be
provided to
one_hot.
Examples
Suppose thatindices = [0, 2, -1, 1] depth = 3 on_value = 5.0 off_value = 0.0 axis = -1
Then output is
[4 x 3]:
output = [5.0 0.0 0.0] // one_hot(0) [0.0 0.0 5.0] // one_hot(2) [0.0 0.0 0.0] // one_hot(-1) [0.0 5.0 0.0] // one_hot(1)
Suppose that
indices = [[0, 2], [1, -1]] depth = 3 on_value = 1.0 off_value = 0.0 axis = -1
Then output is
[2 x 2 x 3]:
output = [ [1.0, 0.0, 0.0] // one_hot(0) [0.0, 0.0, 1.0] // one_hot(2) ][ [0.0, 1.0, 0.0] // one_hot(1) [0.0, 0.0, 0.0] // one_hot(-1) ]
Using default values for
on_valueand
off_value:
indices = [0, 1, 2] depth = 3
The output will be
output = [[1., 0., 0.], [0., 1., 0.], [0., 0., 1.]]
Args:
indices: A
Tensorof
indices.
depth: A scalar
defining the depth of the one hot dimension.
on_value: A scalar
defining the value to fill in output when
indices[j] = i. (default: 1)
off_value: A scalar
defining the value to fill in output when
indices[j] != i. (default: 0)
axis: The axis
to fill (default: -1, a new inner-most axis).
dtype: The data
type of the output tensor.
Returns:
output: The one-hot
tensor.
Raises:
TypeError: If dtype
of either
on_valueor
off_valuedon't
match
dtype
TypeError: If dtype
of
on_valueand
off_valuedon't
match one another
Defined in
tensorflow/python/ops/array_ops.py.
相关文章推荐
- tf.reduce_mean(input,axis=None,keep_dims=False,name=None,reduction_indices=None)
- jQuery高级事件---on、off、one和事件委托
- [DOM Event Learning] Section 3 jQuery事件处理基础 on(), off()和one()方法使用
- 问题:jquery中的.on() .one() .off()函数
- tf.one_hot 实例
- 第一百七十一节,jQuery,高级事件,模拟操作,命名空间,事件委托,on、off 和 one
- Refreshing One Column based on the value of Another Column in ADFdi Table
- 浅谈jQuery代码优化之事件委托(事件绑定)——bind()|live()|delegate()|on()|off()|one()方法
- jquery 委托 on() | off()删除委托 | one()只执行一次的委托
- javascript事件委托和jQuery事件绑定on、off 和one以及on绑定多个事件(重要)
- One-hot 编码/TF-IDF 值来提取特征,LAD/梯度下降法(Gradient Descent),Sigmoid
- tf.nn.conv2d(input, filter, strides, padding, use_cudnn_on_gpu=None, name=None) 除去name参数用以指定该操作的nam
- tf.argmax(input, axis=None, name=None, dimension=None)
- one artical on pci hotplug framework
- tf.gather_nd(params, indices, name=None)
- jQuery事件绑定on、off 和one,取代bind, live, delegate
- tensorflow--tf.one_hot()函数示例
- [DOM Event Learning] Section 3 jQuery事件处理基础 on(), off()和one()方法使用
- 【tensorflow】tf.one_hot,tf.reduce_mean,tf.argmax,tf.equal,tf.cast学习
- js事件委托和jQuery事件绑定on , off , one , bind , unbind , die