tf.reshape(inputs, [-1,dim])的理解

示例：

import tensorflow as tf
lenth = tf.reshape(30,shape=[-1])  #变成一维张量
lenth2 = tf.reshape(30,shape=[])  #变成标量了
lenth3 = tf.reshape([30],shape=[])  #变成标量了
with tf.Session() as sess:sess.run(tf.global_variables_initializer())a = sess.run(lenth)b = sess.run(lenth2)c = sess.run(lenth3)
print(a,b,c)[30] 30 30

变成一维的，但一维与标量确理解错了；标量可以理解为0维；

标量可以用shape=[]参数定义

If one component of `shape` is the special value -1, the size of that dimensionis computed so that the total size remains constant.  In particular, a `shape`of `[-1]` flattens into 1-D.  At most one component of `shape` can be -1.If `shape` is 1-D or higher, then the operation returns a tensor with shape`shape` filled with the values of `tensor`. In this case, the number of elementsimplied by `shape` must be the same as the number of elements in `tensor`.For example:```# tensor 't' is [1, 2, 3, 4, 5, 6, 7, 8, 9]# tensor 't' has shape [9]reshape(t, [3, 3]) ==> [[1, 2, 3],[4, 5, 6],[7, 8, 9]]# tensor 't' is [[[1, 1], [2, 2]],#                [[3, 3], [4, 4]]]# tensor 't' has shape [2, 2, 2]reshape(t, [2, 4]) ==> [[1, 1, 2, 2],[3, 3, 4, 4]]# tensor 't' is [[[1, 1, 1],#                 [2, 2, 2]],#                [[3, 3, 3],#                 [4, 4, 4]],#                [[5, 5, 5],#                 [6, 6, 6]]]# tensor 't' has shape [3, 2, 3]# pass '[-1]' to flatten 't'reshape(t, [-1]) ==> [1, 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 4, 5, 5, 5, 6, 6, 6]# -1 can also be used to infer the shape# -1 is inferred to be 9:reshape(t, [2, -1]) ==> [[1, 1, 1, 2, 2, 2, 3, 3, 3],[4, 4, 4, 5, 5, 5, 6, 6, 6]]# -1 is inferred to be 2:reshape(t, [-1, 9]) ==> [[1, 1, 1, 2, 2, 2, 3, 3, 3],[4, 4, 4, 5, 5, 5, 6, 6, 6]]# -1 is inferred to be 3:reshape(t, [ 2, -1, 3]) ==> [[[1, 1, 1],[2, 2, 2],[3, 3, 3]],[[4, 4, 4],[5, 5, 5],[6, 6, 6]]]# tensor 't' is [7]# shape `[]` reshapes to a scalarreshape(t, []) ==> 7```

tf.reshape(inputs, [-1,dim])的理解相关推荐

tf.reshape的-1的错误理解
一直以为reshape(-1,)会变成一维的,然后变成一个标量: import tensorflow as tf lenth = tf.reshape(30,shape=[-1]) lenth2 = ...
tensorflow 之 tf.reshape 之 -1
最近压力好大,写点东西可能对心情有好处. reshape即把矩阵的形状变一下,这跟matlab一样的,但如果参数是-1的话是什么意思呢? 看一下例子哈: . . . In [21]: tensor = ...
tf.reshape 和 tf.transpose 用法
import tensorflow as tf x= tf.constant([[2,3],[4,5],[6,7]],tf.int32) print(x.numpy()) [[2 3][4 5][6 ...
【tensorflow】tf.reshape函数说明：重塑张量
转载 [471]tf.reshape函数说明_周小董-CSDN博客 https://blog.csdn.net/xc_zhou/article/details/85342542 函数原型: tf.re ...
tensorflow 之最近用到的几个小操作tf.reshape，tf.convert_to_tensor，tf.where
1.tf.reshape() #调整tensor的形状 img = .... img_res = tf.reshape(img, [-1]) 着重记录是shape=[-1]时,相当于flatten操作 ...
TensorFlow学习笔记（十八）tf.reshape矩阵变形
tf.reshape(tensor, shape, name=None) 矩阵变形是常用的操作,在Tensorflow中调用方式有多种,例如: 1. tf.reshape tf.reshape(L3, ...
tf.reshape()
_image = tf.reshape(x, [-1,28, 28, 1]) # -1表示任意数量的样本数,大小为28x28深度为一的张量 # 可以忽略(其实是用深度为28的,28x1的张量,来表示2 ...
tf.shape()和tf.reshape()
一.tf.shape() tf.shape(input,name=None,out_type=tf.int32) 参数 (1)input:输入张量或稀疏张量: (2)name:命名: (3)out_t ...
Pytorch中dim的理解
dim的定义 dim 表示维度 x = torch.randn(2, 3, 3)print(x) print(x.size()) print(x.dim()) 输出: tensor([[[-1.694 ...

tf.reshape(inputs, [-1,dim])的理解

tf.reshape(inputs, [-1,dim])的理解相关推荐

最新文章

热门文章