{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# 张量\n", "\n", "[![](https://gitee.com/mindspore/docs/raw/r1.2/resource/_static/logo_source.png)](https://gitee.com/mindspore/docs/blob/r1.2/tutorials/source_zh_cn/tensor.ipynb) [![](https://gitee.com/mindspore/docs/raw/r1.2/resource/_static/logo_notebook.png)](https://obs.dualstack.cn-north-4.myhuaweicloud.com/mindspore-website/notebook/r1.2/quick_start/mindspore_tensor.ipynb) [![](https://gitee.com/mindspore/docs/raw/r1.2/tutorials/training/source_zh_cn/_static/logo_modelarts.png)](https://console.huaweicloud.com/modelarts/?region=cn-north-4#/notebook/loading?share-url-b64=aHR0cHM6Ly9vYnMuZHVhbHN0YWNrLmNuLW5vcnRoLTQubXlodWF3ZWljbG91ZC5jb20vbWluZHNwb3JlLXdlYnNpdGUvbm90ZWJvb2svbW9kZWxhcnRzL3F1aWNrX3N0YXJ0L21pbmRzcG9yZV90ZW5zb3IuaXB5bmI=&image_id=65f636a0-56cf-49df-b941-7d2a07ba8c8c)\n", "\n", "张量（Tensor）是MindSpore网络运算中的基本数据结构。\n", "\n", "首先导入本文档需要的模块和接口，如下所示：" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "from mindspore import Tensor\n", "from mindspore import dtype as mstype" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 初始化张量\n", "\n", "张量的初始化方式有多种，构造张量时，支持传入`Tensor`、`float`、`int`、`bool`、`tuple`、`list`和`NumPy.array`类型。\n", "\n", "- **根据数据直接生成**\n", "\n", "可以根据数据创建张量，数据类型可以设置或者自动推断。" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "x = Tensor(0.1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "- **从NumPy数组生成**\n", "\n", "可以从NumPy数组创建张量。" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "arr = np.array([1, 0, 1, 0])\n", "x_np = Tensor(arr)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "初始值是`NumPy.array`，则生成的`Tensor`数据类型与之对应。\n", "\n", "- **继承另一个张量的属性，形成新的张量**\n" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[1 1]\n", " [1 1]]\n" ] } ], "source": [ "from mindspore import ops\n", "oneslike = ops.OnesLike()\n", "x = Tensor(np.array([[0, 1], [2, 1]]).astype(np.int32))\n", "output = oneslike(x)\n", "print(output)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "- **输出指定大小的恒定值张量**\n", "\n", "`shape`是张量的尺寸元组，确定输出的张量的维度。\n" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[1. 1.]\n", " [1. 1.]]\n", "[[0. 0.]\n", " [0. 0.]]\n" ] } ], "source": [ "from mindspore.ops import operations as ops\n", "\n", "shape = (2, 2)\n", "ones = ops.Ones()\n", "output = ones(shape, mstype.float32)\n", "print(output)\n", "\n", "zeros = ops.Zeros()\n", "output = zeros(shape, mstype.float32)\n", "print(output)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "`Tensor`初始化时，可指定dtype，如`mstype.int32`、`mstype.float32`、`mstype.bool_`等。\n", "\n", "## 张量的属性\n", "\n", "张量的属性包括形状（shape）和数据类型（dtype）。\n", "\n", "- 形状：`Tensor`的shape，是一个tuple。\n", "- 数据类型：`Tensor`的dtype，是MindSpore的一个数据类型。" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Datatype of tensor: Float32\n", "Shape of tensor: (1, 2, 3)\n" ] } ], "source": [ "t1 = Tensor(np.zeros([1,2,3]), mstype.float32)\n", "print(\"Datatype of tensor: {}\".format(t1.dtype))\n", "print(\"Shape of tensor: {}\".format(t1.shape))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "## 张量运算\n", "\n", "张量之间有很多运算，包括算术、线性代数、矩阵处理（转置、标引、切片）、采样等，下面介绍其中几种操作，张量运算和NumPy的使用方式类似。\n", "\n", "类似NumPy的索引和切片操作：\n" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "First row: [0. 1.]\n", "First column: [0. 2.]\n", "Last column: [1. 3.]\n" ] } ], "source": [ "tensor = Tensor(np.array([[0, 1], [2, 3]]).astype(np.float32))\n", "print(\"First row: {}\".format(tensor[0]))\n", "print(\"First column: {}\".format(tensor[:, 0]))\n", "print(\"Last column: {}\".format(tensor[..., -1]))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "`Concat`将给定维度上的一系列张量连接起来。" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[0. 1.]\n", " [2. 3.]\n", " [4. 5.]\n", " [6. 7.]]\n" ] } ], "source": [ "data1 = Tensor(np.array([[0, 1], [2, 3]]).astype(np.float32))\n", "data2 = Tensor(np.array([[4, 5], [6, 7]]).astype(np.float32))\n", "op = ops.Concat()\n", "output = op((data1, data2))\n", "print(output)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "`Stack`则是从另一个维度上将两个张量合并起来。" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[[0. 1.]\n", " [2. 3.]]\n", "\n", " [[4. 5.]\n", " [6. 7.]]]\n" ] } ], "source": [ "data1 = Tensor(np.array([[0, 1], [2, 3]]).astype(np.float32))\n", "data2 = Tensor(np.array([[4, 5], [6, 7]]).astype(np.float32))\n", "op = ops.Stack()\n", "output = op([data1, data2])\n", "print(output)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "普通运算：" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[ 4. 10. 18.]\n" ] } ], "source": [ "input_x = Tensor(np.array([1.0, 2.0, 3.0]), mstype.float32)\n", "input_y = Tensor(np.array([4.0, 5.0, 6.0]), mstype.float32)\n", "mul = ops.Mul()\n", "output = mul(input_x, input_y)\n", "print(output)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "## 与NumPy转换\n", "\n", "张量可以和NumPy进行互相转换。\n", "\n", "### 张量转换为NumPy" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "output: \n", "n_output: \n" ] } ], "source": [ "zeros = ops.Zeros()\n", "output = zeros((2,2), mstype.float32)\n", "print(\"output: {}\".format(type(output)))\n", "n_output = output.asnumpy()\n", "print(\"n_output: {}\".format(type(n_output)))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "### NumPy转换为张量" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "output: \n", "t_output: \n" ] } ], "source": [ "output = np.array([1, 0, 1, 0])\n", "print(\"output: {}\".format(type(output)))\n", "t_output = Tensor(output)\n", "print(\"t_output: {}\".format(type(t_output)))" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.0" } }, "nbformat": 4, "nbformat_minor": 4 }