From 63a53ec313c6a89e4cd079d3749f921efddc9ae7 Mon Sep 17 00:00:00 2001 From: zhangmeng1 Date: Thu, 13 Oct 2022 18:13:43 +0800 Subject: [PATCH] basic_api --- .../preparation_02/tf01_basic_api.ipynb | 662 ++++++++++++++++++ 1 file changed, 662 insertions(+) create mode 100644 Project_preparation/preparation_02/tf01_basic_api.ipynb diff --git a/Project_preparation/preparation_02/tf01_basic_api.ipynb b/Project_preparation/preparation_02/tf01_basic_api.ipynb new file mode 100644 index 0000000..d02246d --- /dev/null +++ b/Project_preparation/preparation_02/tf01_basic_api.ipynb @@ -0,0 +1,662 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "2.2.0\n", + "sys.version_info(major=3, minor=6, micro=9, releaselevel='final', serial=0)\n", + "matplotlib 3.3.4\n", + "numpy 1.19.5\n", + "pandas 1.1.5\n", + "sklearn 0.24.2\n", + "tensorflow 2.2.0\n", + "tensorflow.keras 2.3.0-tf\n" + ] + } + ], + "source": [ + "import matplotlib as mpl\n", + "import matplotlib.pyplot as plt\n", + "%matplotlib inline\n", + "import numpy as np\n", + "import sklearn\n", + "import pandas as pd\n", + "import os\n", + "import sys\n", + "import time\n", + "import tensorflow as tf\n", + "\n", + "from tensorflow import keras\n", + "\n", + "print(tf.__version__)\n", + "print(sys.version_info)\n", + "for module in mpl, np, pd, sklearn, tf, keras:\n", + " print(module.__name__, module.__version__)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "tf.Tensor(\n", + "[[1. 2. 3.]\n", + " [4. 5. 6.]], shape=(2, 3), dtype=float32)\n", + "--------------------------------------------------\n", + "tf.Tensor(\n", + "[[2. 3.]\n", + " [5. 6.]], shape=(2, 2), dtype=float32)\n", + "--------------------------------------------------\n", + "tf.Tensor([2. 5.], shape=(2,), dtype=float32)\n", + "--------------------------------------------------\n" + ] + } + ], + "source": [ + "# constant是常量张量\n", + "t = tf.constant([[1., 2., 3.], [4., 5.,6.]])\n", + "\n", + "# index\n", + "#2.0能够直接获取值时因为execution默认打开的\n", + "print(t)\n", + "print('-'*50)\n", + "print(t[:, 1:])\n", + "print('-'*50)\n", + "print(t[..., 1])\n", + "print('-'*50)\n", + "# t.assign(1)对常量不能进行再次assign设置\n", + "type(t.numpy()) #转为ndarray\n", + "q=t.numpy()" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "t1= tf.constant(q) #把ndarray变为张量\n", + "t1" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "tf.Tensor(\n", + "[[11. 12. 13.]\n", + " [14. 15. 16.]], shape=(2, 3), dtype=float32)\n", + "tf.Tensor(\n", + "[[1. 2. 3.]\n", + " [4. 5. 6.]], shape=(2, 3), dtype=float32)\n", + "tf.Tensor(\n", + "[[ 1. 4. 9.]\n", + " [16. 25. 36.]], shape=(2, 3), dtype=float32)\n", + "tf.Tensor(\n", + "[[1. 2. 3.]\n", + " [4. 5. 6.]], shape=(2, 3), dtype=float32)\n", + "tf.Tensor(\n", + "[[1. 4.]\n", + " [2. 5.]\n", + " [3. 6.]], shape=(3, 2), dtype=float32)\n", + "tf.Tensor(\n", + "[[14. 32.]\n", + " [32. 77.]], shape=(2, 2), dtype=float32)\n" + ] + } + ], + "source": [ + "# ops 使用tf本身的math接口对Tensor进行计算\n", + "print(t+10)\n", + "print(t)\n", + "print(tf.square(t))\n", + "print(t)\n", + "#矩阵乘以自己的转置\n", + "print(tf.transpose(t))\n", + "print(t @ tf.transpose(t)) #@是矩阵乘法，和*不一致" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "tf.Tensor(\n", + "[[1. 1.4142135 1.7320508]\n", + " [2. 2.236068 2.4494898]], shape=(2, 3), dtype=float32)\n", + "--------------------------------------------------\n" + ] + }, + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "print(tf.sqrt(t))\n", + "print('-'*50)\n", + "# tf.math.sqrt(t)\n", + "tf.math.log(t) #必须加math" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[[1. 2. 3.]\n", + " [4. 5. 6.]]\n", + "[[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]]\n", + "\n", + "[[ 1. 4. 9.]\n", + " [16. 25. 36.]]\n", + "tf.Tensor(\n", + "[[1. 2. 3.]\n", + " [4. 5. 6.]], shape=(2, 3), dtype=float64)\n" + ] + } + ], + "source": [ + "# numpy conversion\n", + "print(t.numpy()) #可以直接通过numpy取出来\n", + "print(t.numpy().tolist())\n", + "print(type(t.numpy()))\n", + "print(np.square(t)) #直接求平方\n", + "np_t = np.array([[1., 2., 3.], [4., 5., 6.]])\n", + "print(tf.constant(np_t)) #转换为tensor" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "tf.Tensor(2.718, shape=(), dtype=float32)\n", + "2.718\n", + "()\n" + ] + } + ], + "source": [ + "# Scalars 就是标量，只有一个数值的张量，称为标量\n", + "t = tf.constant(2.718)\n", + "print(t)\n", + "print(t.numpy())\n", + "print(t.shape) #维数" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "tf.Tensor(b'cafe', shape=(), dtype=string)\n", + "tf.Tensor(4, shape=(), dtype=int32)\n", + "tf.Tensor(4, shape=(), dtype=int32)\n", + "tf.Tensor([ 99 97 102 101], shape=(4,), dtype=int32)\n" + ] + } + ], + "source": [ + "# strings\n", + "t = tf.constant(\"cafe\")\n", + "print(t)\n", + "print(tf.strings.length(t))\n", + "print(tf.strings.length(t, unit=\"UTF8_CHAR\"))\n", + "print(tf.strings.unicode_decode(t, \"UTF8\"))" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "tf.Tensor([4 6 2], shape=(3,), dtype=int32)\n", + "tf.Tensor([4 6 6], shape=(3,), dtype=int32)\n", + "\n" + ] + } + ], + "source": [ + "# string array\n", + "t = tf.constant([\"cafe\", \"coffee\", \"咖啡\"])\n", + "#自动求出数组中每一个字符的长度,如果不加unit=\"UTF8_CHAR\"，得到的是实际字节存储的长度\n", + "print(tf.strings.length(t, unit=\"UTF8_CHAR\")) \n", + "print(tf.strings.length(t, unit=\"BYTE\")) \n", + "r = tf.strings.unicode_decode(t, \"UTF8\")\n", + "# https://tool.chinaz.com/tools/unicode.aspx 汉字转的是unicode编码\n", + "print(r)\n", + "# RaggedTensor 是指形状分布不固定的（行元素个数不相等）\n", + "# Tensor，2.0新增" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "(4, None)\n", + "tf.Tensor([21 22 23], shape=(3,), dtype=int32)\n", + "\n" + ] + } + ], + "source": [ + "# ragged tensor\n", + "r = tf.ragged.constant([[11, 12], [21, 22, 23], [], [41]])\n", + "\n", + "# index op\n", + "print(r)\n", + "print(r.shape)\n", + "print(r[1])\n", + "#取一行也是ragged tensor\n", + "print(r[1:3])\n", + "# print(r[:,1])#不能取列索引" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "\n" + ] + } + ], + "source": [ + "# ops on ragged tensor\n", + "r2 = tf.ragged.constant([[51, 52],[], [], [71]])\n", + "print(tf.concat([r, r2], axis = 0))\n", + "print(tf.concat([r, r2], axis = 1)) #行数不相等，不可以拼\n", + "#是否可以把上面的axis改为1" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "#按轴1进行合并时，行数要一致，行数相等，可以拼\n", + "r3 = tf.ragged.constant([[13, 14], [15], [41], [42, 43]])\n", + "print(tf.concat([r, r3], axis = 1))" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "tf.Tensor(\n", + "[[11 12 0]\n", + " [21 22 23]\n", + " [ 0 0 0]\n", + " [41 0 0]], shape=(4, 3), dtype=int32)\n" + ] + } + ], + "source": [ + "print(r.to_tensor()) #各种深度学习模型必须输入一个tensor\n", + "#空闲的补0，只能往后面补" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "SparseTensor(indices=tf.Tensor(\n", + "[[0 1]\n", + " [1 0]\n", + " [2 3]\n", + " [3 2]], shape=(4, 2), dtype=int64), values=tf.Tensor([1. 2. 3. 5.], shape=(4,), dtype=float32), dense_shape=tf.Tensor([4 4], shape=(2,), dtype=int64))\n" + ] + }, + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# sparse tensor 可以往前面补零,sparse tensor从第一行依次往下填位置\n", + "#sparese tensor存储节省内存空间，磁盘空间\n", + "s = tf.SparseTensor(indices = [[0, 1], [1, 0], [2, 3],[3,2]], #位置\n", + " values = [1., 2., 3.,5], #值\n", + " dense_shape = [4, 4]) #维数\n", + "print(s)\n", + "tt=tf.sparse.to_dense(s)\n", + "tt" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "SparseTensor(indices=tf.Tensor(\n", + "[[0 1]\n", + " [1 0]\n", + " [2 3]\n", + " [3 2]], shape=(4, 2), dtype=int64), values=tf.Tensor([ 2. 4. 6. 10.], shape=(4,), dtype=float32), dense_shape=tf.Tensor([4 4], shape=(2,), dtype=int64))\n", + "unsupported operand type(s) for +: 'SparseTensor' and 'int'\n", + "tf.Tensor(\n", + "[[ 30. 40.]\n", + " [ 20. 40.]\n", + " [210. 240.]\n", + " [250. 300.]], shape=(4, 2), dtype=float32)\n" + ] + } + ], + "source": [ + "# ops on sparse tensors\n", + "\n", + "s2 = s * 2.0\n", + "print(s2)\n", + "\n", + "#不支持加法\n", + "try:\n", + " s3 = s + 1\n", + "except TypeError as ex:\n", + " print(ex)\n", + "\n", + "s4 = tf.constant([[10., 20.],\n", + " [30., 40.],\n", + " [50., 60.],\n", + " [70., 80.]])\n", + "# tf.sparse.to_dense(s)@s4\n", + "print(tf.sparse.sparse_dense_matmul(s, s4)) #稀疏Tensor和Tensor想乘" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "SparseTensor(indices=tf.Tensor(\n", + "[[0 2]\n", + " [2 3]\n", + " [0 1]], shape=(3, 2), dtype=int64), values=tf.Tensor([1. 2. 3.], shape=(3,), dtype=float32), dense_shape=tf.Tensor([3 4], shape=(2,), dtype=int64))\n", + "SparseTensor(indices=tf.Tensor(\n", + "[[0 1]\n", + " [0 2]\n", + " [2 3]], shape=(3, 2), dtype=int64), values=tf.Tensor([3. 1. 2.], shape=(3,), dtype=float32), dense_shape=tf.Tensor([3 4], shape=(2,), dtype=int64))\n", + "tf.Tensor(\n", + "[[0. 3. 1. 0.]\n", + " [0. 0. 0. 0.]\n", + " [0. 0. 0. 2.]], shape=(3, 4), dtype=float32)\n" + ] + } + ], + "source": [ + "# sparse tensor\n", + "s5 = tf.SparseTensor(indices = [[0, 2], [2, 3], [0, 1]],\n", + " values = [1., 2., 3.],\n", + " dense_shape = [3, 4])\n", + "# print(tf.sparse.to_dense(s5)) #sparse无顺序时，不能转为tensor，会报错\n", + "print(s5)\n", + "s6 = tf.sparse.reorder(s5)\n", + "print(s6)\n", + "print(tf.sparse.to_dense(s6))" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "tf.Tensor(\n", + "[[1. 2. 3.]\n", + " [4. 5. 6.]], shape=(2, 3), dtype=float32)\n", + "--------------------------------------------------\n", + "[[1. 2. 3.]\n", + " [4. 5. 6.]]\n" + ] + } + ], + "source": [ + "# Variables\n", + "v = tf.Variable([[1., 2., 3.], [4., 5.,6.]])\n", + "print(v)\n", + "print(v.value())\n", + "print('-'*50)\n", + "print(v.numpy())" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "140353908649208\n", + "140353908649208\n", + "[[ 2. 4. 6.]\n", + " [ 8. 10. 12.]]\n", + "--------------------------------------------------\n", + "[[ 2. 42. 6.]\n", + " [ 8. 10. 12.]]\n", + "--------------------------------------------------\n", + "[[ 2. 42. 6.]\n", + " [ 7. 8. 9.]]\n", + "140353908649208\n" + ] + } + ], + "source": [ + "# 修改变量时要用assign，改变tensor内某个值，空间没有发生变化，效率高\n", + "# assign value\n", + "print(id(v))\n", + "v.assign(2*v)\n", + "print(id(v))\n", + "print(v.numpy())\n", + "print('-'*50)\n", + "v[0, 1].assign(42) #取某个元素修改\n", + "print(v.numpy())\n", + "print('-'*50)\n", + "v[1].assign([7., 8., 9.]) #取某一行修改\n", + "print(v.numpy())\n", + "print(id(v))" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "'ResourceVariable' object does not support item assignment\n" + ] + } + ], + "source": [ + "try:\n", + " v[1] = [7., 8., 9.]\n", + "except TypeError as ex:\n", + " print(ex)" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "tf.Tensor(\n", + "[[ 4. 84. 12.]\n", + " [14. 16. 18.]], shape=(2, 3), dtype=float32)\n", + "140353905381784\n", + "\n" + ] + } + ], + "source": [ + "v=2*v\n", + "print(v)\n", + "print(id(v))\n", + "print(type(v))" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "x = tf.constant([[1., 1.], [2., 2.]])\n", + "tf.reduce_mean(x,axis=1)" + ] + } + ], + "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": "3.6.9" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}