tf.squeeze_python tf.squeeze-CSDN博客

tf.squeeze

https://github.com/tensorflow/docs/tree/r1.4/site/en/api_docs/api_docs/python/tf
site/en/api_docs/api_docs/python/tf/squeeze.md

squeeze(
    input,
    axis=None,
    name=None,
    squeeze_dims=None
)

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

Removes dimensions of size 1 from the shape of a tensor.
从张量形状中移除大小为 1 的维度。

Given a tensor input, this operation returns a tensor of the same type with all dimensions of size 1 removed. If you don’t want to remove all size 1 dimensions, you can remove specific size 1 dimensions by specifying axis.
给定一个张量 input，该操作返回一个与已经移除的所有大小为 1 的维度具有相同类型的张量。如果您不想删除所有大小为 1 的维度，则可以通过指定 axis 来删除特定的大小为 1 的维度。

For example:

注意是 shape。

# 't' is a tensor of shape [1, 2, 1, 3, 1, 1]
tf.shape(tf.squeeze(t))  # [2, 3]

Or, to remove specific size 1 dimensions:
或者，要删除特定的大小为 1 的维度：

注意是 shape。

# 't' is a tensor of shape [1, 2, 1, 3, 1, 1]
tf.shape(tf.squeeze(t, [2, 4]))  # [1, 2, 3, 1]

1. Args

input: A Tensor. The input to squeeze.
axis: An optional list of ints. Defaults to []. If specified, only squeezes the dimensions listed. The dimension index starts at 0. It is an error to squeeze a dimension that is not 1. Must be in the range [-rank(input), rank(input)). (如果指定，只能挤压列出的维度。维度索引从 0 开始。压缩非 1 的维度是错误的。必须在范围内 [-rank(input), rank(input))。)
name: A name for the operation (optional). (操作的名称 (可选))
squeeze_dims: Deprecated keyword argument that is now axis.

2. Returns

A Tensor. Has the same type as input.
Contains the same data as input, but has one or more dimensions of size 1 removed.
包含与 input 相同的数据，但删除一个或多个尺寸为 1。

##3. Raises

ValueError: When both squeeze_dims and axis are specified.

squeeze [skwiːz]：v. 挤，紧握，勒索，压榨，使挤进，(非正式) 向...施加压力，(尤于金融或商业) 破坏 n. 挤压，榨出的液体，压榨，紧握，拥挤，佣金，(可获得的钱、工作岗位等的) 减少，(非正式) 女朋友，男朋友，拥挤的社交集会，压模，(非正式) 勒索的钱，(桥牌) 紧逼打法，(棒球) 抢分战术

4. 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 * "++--")

matrix_data = tf.Variable(tf.random_normal(shape=(1, 3, 2)))
squeezed_data = tf.squeeze(matrix_data)

matrix_data_shape = tf.shape(matrix_data)
squeezed_data_shape = tf.shape(squeezed_data)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    squeezed_data_shape_, matrix_data_shape_, squeezed_data_, matrix_data_ = sess.run(
        [squeezed_data_shape, matrix_data_shape, squeezed_data, matrix_data])

    print("matrix_data:\n", matrix_data_)
    print("squeezed_data:\n", squeezed_data_)
    print("matrix_data_shape:\n", matrix_data_shape_)
    print("squeezed_data_shape:\n", squeezed_data_shape_)

/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 17:47:22.155174: 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 17:47:22.237386: 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 17:47:22.237628: 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 17:47:22.237639: 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)
matrix_data:
 [[[ 0.52290684 -0.39370742]
  [-1.131437   -0.29959333]
  [-0.52568823  0.317227  ]]]
squeezed_data:
 [[ 0.52290684 -0.39370742]
 [-1.131437   -0.29959333]
 [-0.52568823  0.317227  ]]
matrix_data_shape:
 [1 3 2]
squeezed_data_shape:
 [3 2]

Process finished with exit code 0