tensorflow常量与变量基本操作

tensorflow 基础api

1. t = tf.constant() 常量

对数字进行操作

t = tf.constant([[1., 2., 3.], [4., 5., 6.]])
# index
print(t)
print(t[:, 1:]) # 输出第二列以后
print(t[..., 1]) # 只输出第二列

# output
tf.Tensor(
[[1. 2. 3.]
 [4. 5. 6.]], shape=(2, 3), dtype=float32)
tf.Tensor(
[[2. 3.]
 [5. 6.]], shape=(2, 2), dtype=float32)
tf.Tensor([2. 5.], shape=(2,), dtype=float32)

# ops 算子运算
print(t+10)
print(tf.square(t))  # 平方
print(t @ tf.transpose(t))  # 乘以转置

# output
tf.Tensor(
[[11. 12. 13.]
 [14. 15. 16.]], shape=(2, 3), dtype=float32)
tf.Tensor(
[[ 1.  4.  9.]
 [16. 25. 36.]], shape=(2, 3), dtype=float32)
tf.Tensor(
[[14. 32.]
 [32. 77.]], shape=(2, 2), dtype=float32)

tensorflow2.0不用session.run()

# numpy conversion 和numpyd的转换
print(t.numpy())
print(np.square(t))
np_t = np.array([[1., 2., 3.], [4., 5., 6.]])
print(tf.constant(np_t))

# output
[[1. 2. 3.]
 [4. 5. 6.]]
[[ 1.  4.  9.]
 [16. 25. 36.]]
tf.Tensor(
[[1. 2. 3.]
 [4. 5. 6.]], shape=(2, 3), dtype=float64)

# Scalars 0维数字
t = tf.constant(2.718)
print(t.numpy())
print(t.shape)

2.718
()

对字符串进行操作

# strings
t = tf.constant("cafe")
print(t)
print(tf.strings.length(t))
print(tf.strings.length(t, unit="UTF8_CHAR"))
print(tf.strings.unicode_decode(t, "UTF8"))

# output
tf.Tensor(b'cafe', shape=(), dtype=string)  
tf.Tensor(4, shape=(), dtype=int32)
tf.Tensor(4, shape=(), dtype=int32)
tf.Tensor([ 99  97 102 101], shape=(4,), dtype=int32)

对数组进行操作

# string array
t = tf.constant(["cafe", "coffee", "咖啡"])
print(tf.strings.length(t, unit="UTF8_CHAR"))
r = tf.strings.unicode_decode(t, "UTF8")
print(r)

# output
tf.Tensor([4 6 2], shape=(3,), dtype=int32)
<tf.RaggedTensor [[99, 97, 102, 101], [99, 111, 102, 102, 101, 101], [21654, 21857]]>
# RaggedTensor 不完整的n维矩阵 ，每行不等长（不规整）

ragged tensor

# ragged tensor
r = tf.ragged.constant([[11, 12], [21, 22, 23], [], [41]])
# index op
print(r)
print(r[1])
print(r[1:2])

# output
<tf.RaggedTensor [[11, 12], [21, 22, 23], [], [41]]>
tf.Tensor([21 22 23], shape=(3,), dtype=int32)
<tf.RaggedTensor [[21, 22, 23]]>

ragged tensor 进行拼接操作

# ops on ragged tensor 进行拼接操作
r2 = tf.ragged.constant([[51, 52], [], [71]])
print(tf.concat([r, r2], axis = 0)) # 按0维拼接

# output 
<tf.RaggedTensor [[11, 12], [21, 22, 23], [], [41], [51, 52], [], [71]]> # 4+3

r3 = tf.ragged.constant([[13, 14], [15], [], [42, 43]]) # 横向拼接
print(tf.concat([r, r3], axis = 1))

<tf.RaggedTensor [[11, 12, 13, 14], [21, 22, 23, 15], [], [41, 42, 43]]>

ragged tensor 变为普通tensor

print(r.to_tensor())

# output
tf.Tensor(
[[11 12  0]
 [21 22 23]
 [ 0  0  0]
 [41  0  0]], shape=(4, 3), dtype=int32)

sparse tensor 只将有值的都记录下来

# sparse tensor
s = tf.SparseTensor(indices = [[0, 1], [1, 0], [2, 3]],
                    values = [1., 2., 3.],
                    dense_shape = [3, 4])
print(s)
print(tf.sparse.to_dense(s))

sparse tensor 的形式与转换为密集矩阵

# sparse tensor
s = tf.SparseTensor(indices = [[0, 1], [1, 0], [2, 3]],
                    values = [1., 2., 3.],
                    dense_shape = [3, 4])
print(s)
print(tf.sparse.to_dense(s))

# output
SparseTensor(indices=tf.Tensor(
[[0 1]
 [1 0]
 [2 3]], shape=(3, 2), dtype=int64), values=tf.Tensor([1. 2. 3.], shape=(3,), dtype=float32), dense_shape=tf.Tensor([3 4], shape=(2,), dtype=int64))
tf.Tensor(
[[0. 1. 0. 0.]
 [2. 0. 0. 0.]
 [0. 0. 0. 3.]], shape=(3, 4), dtype=float32)

sparse tensor 的操作类型

# ops on sparse tensors

s2 = s * 2.0
print(s2)

try:
    s3 = s + 1
except TypeError as ex:
    print(ex)

s4 = tf.constant([[10., 20.],
                  [30., 40.],
                  [50., 60.],
                  [70., 80.]])
print(tf.sparse.sparse_dense_matmul(s, s4))

# output
SparseTensor(indices=tf.Tensor(
[[0 1]
 [1 0]
 [2 3]], shape=(3, 2), dtype=int64), values=tf.Tensor([2. 4. 6.], shape=(3,), dtype=float32), dense_shape=tf.Tensor([3 4], shape=(2,), dtype=int64))
unsupported operand type(s) for +: 'SparseTensor' and 'int'
tf.Tensor(
[[ 30.  40.]
 [ 20.  40.]
 [210. 240.]], shape=(3, 2), dtype=float32)

sparse tensor常见坑:indices必须是先拍好序

2. v = tf.Variable() 变量

# Variables
v = tf.Variable([[1., 2., 3.], [4., 5., 6.]])
print(v)
print(v.value())
print(v.numpy())

# output
<tf.Variable 'Variable:0' shape=(2, 3) dtype=float32, numpy=
array([[1., 2., 3.],
       [4., 5., 6.]], dtype=float32)>
tf.Tensor(
[[1. 2. 3.]
 [4. 5. 6.]], shape=(2, 3), dtype=float32)
[[1. 2. 3.]
 [4. 5. 6.]]

variable重新赋值

# assign value
v.assign(2*v)
print(v.numpy())
v[0, 1].assign(42)
print(v.numpy())
v[1].assign([7., 8., 9.])
print(v.numpy())

# ouput
[[ 2.  4.  6.]
 [ 8. 10. 12.]]
[[ 2. 42.  6.]
 [ 8. 10. 12.]]
[[ 2. 42.  6.]
 [ 7.  8.  9.]]

变量赋值只能用assiagn函数

try:
    v[1] = [7., 8., 9.]
except TypeError as ex:
    print(ex)

# output
'ResourceVariable' object does not support item assignment