tf.reshape (API r1.3)

tf.reshape (API r1.3)

https://github.com/tensorflow/docs/tree/r1.3/site/en/api_docs/api_docs/python/tf
site/en/api_docs/api_docs/python/tf/reshape.md

reshape(
    tensor,
    shape,
    name=None
)

Defined in tensorflow/python/ops/gen_array_ops.py.
See the guide: Tensor Transformations > Shapes and Shaping

Reshapes a tensor.
重塑張量。

Given tensor, this operation returns a tensor that has the same values as tensor with shape shape.
給定 tensor，這個操作返回一個張量，它與帶有形狀 shape 的 tensor 具有相同的值。

If one component of shape is the special value -1, the size of that dimension is 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.
如果 shape 的一個分量是特殊值 -1，則計算該維度的大小，以使總大小保持不變。特別地情況爲，一個 [-1] 維的 shape 整個矩陣平鋪成 1 維。至多能有一個 shape 的分量可以是 -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 elements implied by shape must be the same as the number of elements in tensor.
如果 shape 是 1-D 或更高，則操作返回形狀爲 shape 的張量，其填充爲 tensor 的值。在這種情況下，隱含的 shape 元素數量必須與 tensor 元素數量相同。

1. Args

tensor: A Tensor.
shape: A Tensor. Must be one of the following types: int32, int64. Defines the shape of the output tensor. (用於定義輸出張量的形狀。)
name: A name for the operation (optional). (操作的名稱 (可選)。)

2. Returns

A Tensor. Has the same type as tensor.
該操作返回一個 Tensor。與 tensor 具有相同的類型。

shape 是一個張量，其中的一個元素可以是 -1。-1 表示不指定這一維度的大小，函數自動計算，但列表中只能存在一個 -1。

reshape 變換矩陣按照最簡單的理解就是：
reshape(M, shape) == reshape(M, [-1]) => reshape(M, shape)
先將矩陣 M 變爲一維矩陣，然後再對一維矩陣的形式根據 shape 進行構造。

3. Example

#!/usr/bin/env python
# -*- coding: utf-8 -*-

from __future__ import absolute_import
from __future__ import print_function
from __future__ import division

import os
import sys
import numpy as np
import tensorflow as tf

sys.path.append(os.path.dirname(os.path.abspath(__file__)))
current_directory = os.path.dirname(os.path.abspath(__file__))

print(16 * "++--")
print("current_directory:", current_directory)
print(16 * "++--")

x = tf.constant([[[0, 1],
                  [2, 3],
                  [4, 5],
                  [6, 7],
                  [8, 9],
                  [10, 11]]], dtype=np.float32)

y_reshape = tf.reshape(x, [12])
y_reshape_slice = tf.reshape(x, [12])[0:3]

with tf.Session() as sess:
    input_x = sess.run(x)
    print("input_x.shape:", input_x.shape)
    print('\n')

    output_reshape = sess.run(y_reshape)
    print("output_reshape.shape:", output_reshape.shape)
    print("output_reshape:", output_reshape)
    print('\n')

    output_reshape_slice = sess.run(y_reshape_slice)
    print("output_reshape_slice.shape:", output_reshape_slice.shape)
    print("output_reshape_slice:", output_reshape_slice)

/usr/bin/python2.7 /home/strong/tensorflow_work/R2CNN_Faster-RCNN_Tensorflow/yongqiang.py
++--++--++--++--++--++--++--++--++--++--++--++--++--++--++--++--
current_directory: /home/strong/tensorflow_work/R2CNN_Faster-RCNN_Tensorflow
++--++--++--++--++--++--++--++--++--++--++--++--++--++--++--++--
2019-08-15 19:09:35.722959: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-08-15 19:09:35.804714: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-08-15 19:09:35.804993: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties: 
name: GeForce GTX 1080 major: 6 minor: 1 memoryClockRate(GHz): 1.7335
pciBusID: 0000:01:00.0
totalMemory: 7.92GiB freeMemory: 7.43GiB
2019-08-15 19:09:35.805004: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0, compute capability: 6.1)
input_x.shape: (1, 6, 2)


output_reshape.shape: (12,)
output_reshape: [ 0.  1.  2.  3.  4.  5.  6.  7.  8.  9. 10. 11.]


output_reshape_slice.shape: (3,)
output_reshape_slice: [0. 1. 2.]

Process finished with exit code 0