TensorFlow2.x 学习笔记(三)基础操作

数据类型pythonData Containerlist ：消耗大np.array ：无GPUtf.tensorTF is a computing libCreattf.constant(1)# inttf.constant(1.)# float32tf.constant(2.2, dtype=tf.int32)# errortf.constant(2., dtyp...

IDrandom

353人浏览 · 2020-03-01 03:49:17

IDrandom · 2020-03-01 03:49:17 发布

数据类型

python

Data Container

list ：消耗大
np.array ：无GPU
tf.tensor

TF is a computing lib

Creat

tf.constant(1)
# int
tf.constant(1.)
# float32
tf.constant(2.2, dtype=tf.int32)
# error
tf.constant(2., dtype=tf.double)
# float64
tf.constant([True, False])
# bool
tf.constant('hello,world.')
# string

Property

with tf.device("cpu"):
	a = tf.constant([1])
with tf.device("gpu"):
	a = tf.range(4)
a.device
b.device
aa = a.gpu()
aa.device

bb = b.cpu()
bb.device

b.numpy()
# return numpy array

b.ndim
tf.rank(b)
tf.rank(tf.ones([3,4,2])) 

b.name
#没啥用了

check Tensor Type

isinstace(a, tf.Tensor)
tf.is_tensor(b)
c.dtype

Convert

a = np.arange(5)
a.dtype
# int64

aa = tf.convert_to_tensor(a) # int64
aa = tf.convert_to_tensor(a, dtype=tf.int32) #int32

tf.cast(aa, dtype=tf.float32)
tf.cast(aa, dtype=tf.double)
tf.cast(aa, dtype=tf.int32)

tf.Variable

对于可优化的参数用Variable

a = tf.range(5)
b = tf.Variable(a)
b.dtype
b.name
b = tf.Variable(a, name='input_data')
b.name
b.trainable

isinstance(b, tf.Tensor)
isinstance(b, tf.Variable)
tf.is_tensor(b)

b.numpy()

a = tf.ones([])
int(a)
float(a)

创建Tensor

from numpy,list
zeros, ones
fill
random
constant
Application

From Numpy,List

tf.convert_to_tensor(np.ones([2,3]))
tf.convert_to_tensor(np.zeros([2,3]))
tf.convert_to_tensor([1, 2])
tf.convert_to_tensor([1, 2.])
tf.convert_to_tensor([[1], [2.]])

zeros,ones

# zeros
a = tf.zeros([2, 3, 3]) # input为shape
tf.zeros_like(a)
tf.zeros_like(a.shape)
# ones
tf.ones()
tf.ones_like()

Fill

tf.fill([2,3],0)
tf.fill([2,3],0)

Random

Normal

tf.random.normal([2,2],mean=1,stddev=1)
tf.random.normal([2,2])
tf.random.truncated_normal([2,2],mean=0,stddev=1)

Uniform

tf.random.uniform([2,2],minval=0, maxval=1)
tf.random.uniform([2,2],minval=0, maxval=100)

Random Permutation

idx = tf.range(10)
idx = tf.random.shuffle(idx)

a = tf.random.normal([10,784])
b = tf.random.uniform([10], maxval=10, dtype=tf.int32)

a = tf.gather(a,idx)
b = tf.gather(b.idx)

Application

Scalar

loss / accuracy

out = tf.random.uniform([4,10])

y = tf.range(4)
y = tf.one_hot(y, depth=10)

loss = tf.keras.losses.mse(y, out)

loss = tf.reduce_mean(loss)

Vector

Bias

net = layers.Dense(10)
net.build((4,8))
net.kernel
net.bias

Matrix

x = tf.random.normal([4,784])
net = layers.Dense(10)
net.build((4,784))

net(x).shape #[4,10]
net.kernel.shape # [784,10]

net.bias.shape [10]

Tensor

dim = 3

nlp : [b, seq_len, word_dim]

(X_train, y_train), (X_test, y_test) = keras.datasets.imdb.load_data(num_words=10000)
x_train = keras.preprocessing.sequence.pad_sequences(X_train, maxlen=80)
x_train.shape

emb = embedding(x_train)
emb.shape
out = rnn(emb[:4])
out.shape

dim = 4

Image :[b,h,w,3]
feature map :[b,h,w,c]

x = tf.random.normal((4,32,32,3))
net = layers.Conv2D(16, kernel_size=3)
net(x)

dim = 5

Single task: [b, h, w, 3]
meta-learning: [task_b, b, h, w, 3]

索引与切片

Indexing

Basic indexing

[idx][idx][idx]

a = tf.ones([1,5,5,3])
a[0][0]
a[0][0][0]
a[0][0][0][2]

Numpy Style

[idx, idx, …]

a = tf.random.normal([4, 28, 28, 3])
a[1].shape
a[1,2].shape
a[1,2,3].shape
a[1,2,3,2].shape

start:end
[A,B)

a = tf.range(10)
a[-1:]
a[-2:]
a[:2]
a[:-1]

Indexing by :

a.shape
a[0].shape
a[0,:,:,:].shape
a[:,:,:,0].shape

Indexing by ::
- $s t a r t : e n d : s t e p$
- $: : s t e p$
```
a.shape
a[0:2,:,:,:].shape
a[:,0:28:2,0:28:2,:].shape
a[:,:14,:14,:].shape
a[:,14:,14:,:].shape
a[:,::2,::2,:].shape
```
- $: : - 1$
```
a = tf.range(4)
a[::-1]
a[::-2]
a[2::-2]
```

…

a = tf.random.normal([2,4,28,28,3])
a[0].shape
a[0,:,:,:,:].shape
a[0,...].shape
a[:,:,:,:,0].shape
a[...,0].shape
a[0,...,2].shape

Selective Indexing

tf.gather

# data: [classes, students, subjects]
# [4,35,8]
tf.gather(a, axis=0, indices=[2,3]).shape
tf.gather(a, axis=0, indices=[2,1,3,0]).shape
tf.gather(a, axis=1, indices=[2,3,7,9,16]).shape

tf.gather_nd

several students and several subjects

aa = tf.gather(a,axis,[several students])
aaa = tf.gather(aa,axis,[several subjects])

several (students and subjects)

a.shape
tf.gather_nd(a,[0]).shape
tf.gather_nd(a, [0,1]).shape
tf.gather_nd(a, [0,1,2]).shape
tf.gather_nd(a, [[0,1,2]]).shape
tf.gather_nd(a, [[0,0],[1,1]]).shape
tf.gather_nd(a, [[0,0],[1,1],[2,2]]).shape
tf.gather_nd(a, [[0,0,0],[1,1,1],[2,2,2]]).shape
tf.gather_nd(a, [[[0,0,0],[1,1,1],[2,2,2]]]).shape

tf.boolean_mask

# [4, 28, 28, 3]
a.shape
tf.boolean_mask(a, mask=[True,True,False,False]).shape
tf.boolean_mask(a, mask=[True,True,False],axis=3).shape
a = tf.ones([2,3,4])
tf.boolean_mask(a, mask=[[True,False,False],[True,True,False]]).shape

维度变换

shape,ndim
- [b, h, w, c]

reshape

a = tf.random.normal([4,28,28,3])
a.shape, a.ndim
tf.reshape(a, [4, 784, 3]).shape
tf.reshape(a, [4, -1, 3]).shape
tf.reshape(a, [4, 784*3]).shape
tf.reshape(a, [4, -1]).shape
aa = tf.reshape(a, [4, -1])
tf.reshape(aa, [4, 28, 28, 3]).shape
tf.reshape(aa, [4, 14, 56, 3]).shape
tf.reshape(aa, [4, 1, 784, 3]).shape

expand_dims

a = tf.random.normal([4,35,8])
tf.expand_dims(a, axis=0).shape
tf.expand_dims(a, axis=3).shape
tf.expand_dims(a, axis=-1).shape
tf.expand_dims(a, axis=-4).shape

Squeeze dim

tf.squeeze(tf.zeros([1,2,1,1,3])).shape
a = tf.zeros([1,2,1,3])
tf.squeeze(a,axis=0).shape
tf.squeeze(a,axis=2).shape
tf.squeeze(a,axis=-2).shape
tf.squeeze(a,axis=-4).shape

transpose

a = tf.random.normal((4,3,2,1))
a.shape
tf.transpose(a).shape
tf.transpose(1, perm=[0,1,3,2]).shape
# transpose to pytorch
# [b,w,h,c] to [b,3,h,w]
tf.transpose(a,[0,3,1,2]).shape

Broadcasting

expand
- insert 1 dim ahead if needed
- expand dims with size 1 to same size
- [4,32,32,3]
- [3] - [1,1,1,3] -[4,32,32,3]
without copying data

tf.broadcast_to

x = tf.random.normal([4,32,32,3])
x.shape
x +tf.random.normal([32,32,1]).shape
x +tf.random.normal([1,4,1,1]).shape
b = tf.broadcast_to(tf.random.normal([4,1,1,1]), [4,32,32,3])
b.shape

Broadcast VS Tile

# 内存占用不一样
a = tf.ones([3,4])
a1 = tf.broadcast_to(a, [2,3,4])

a2 = tf.expand_dims(a, axis=0)
a2 = tf.tile(a2, [2,1,1])

数学运算

element-wise
- +-*/%//
- tf.math.log/tf.exp
- tf.pow/tf.sqrt

matrix-wise

@ matmul

with broadcasting

a = tf.ones([4,2,3])
b = tf.fill([4,3,5],2.)
a@b
tf.matmul(a,b)
b = tf.fill([3,5],2.)
bb = tf.broadcast_to(b, [4,3,5])
a@bb

axis-wise

前向传播(张量)

$out = relu\{relu\{relu[X@W_1+b_1]@W_2 + b_2\}@W_3+b_3\}$
$p r e d = a r g m a x (o u t)$
$l o s s = M S E (o u t, l a b e l)$
$minimize\ loss$

CSDN学习社区

CSDN联合极客时间，共同打造面向开发者的精品内容学习社区，助力成长！

更多推荐

用 OpenAI Assistants 做大模型应用开发

CSDN学习社区

1 小时解读鸿蒙 10 大热点问题

CSDN学习社区

1 小时解读鸿蒙 10 大热点问题

CSDN学习社区

所有评论(0)

查看更多评论

IDrandom

@IDrandom

已为社区贡献1条内容