From d6a229547b2a73d4bc28365f3474ae4a6f936e88 Mon Sep 17 00:00:00 2001
From: Arun Koundinya Parasa <127001683+ArunKoundinya@users.noreply.github.com>
Date: Tue, 19 Mar 2024 22:18:45 -0700
Subject: [PATCH] Tensor Flow Basics ; Creating Tensors Using Google Colab
---
.../Basics-1/TensorFlowBasics.ipynb | 1268 +++++++++++++++++
1 file changed, 1268 insertions(+)
create mode 100644 TensorFlow_Practice/Basics-1/TensorFlowBasics.ipynb
diff --git a/TensorFlow_Practice/Basics-1/TensorFlowBasics.ipynb b/TensorFlow_Practice/Basics-1/TensorFlowBasics.ipynb
new file mode 100644
index 0000000..635305d
--- /dev/null
+++ b/TensorFlow_Practice/Basics-1/TensorFlowBasics.ipynb
@@ -0,0 +1,1268 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+ "colab": {
+ "provenance": [],
+ "gpuType": "T4",
+ "authorship_tag": "ABX9TyNi89N3ynQwVGssDOrY2Viv",
+ "include_colab_link": true
+ },
+ "kernelspec": {
+ "name": "python3",
+ "display_name": "Python 3"
+ },
+ "language_info": {
+ "name": "python"
+ },
+ "accelerator": "GPU"
+ },
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "view-in-github",
+ "colab_type": "text"
+ },
+ "source": [
+ "![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\")
"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "#TensorFlow Basics"
+ ],
+ "metadata": {
+ "id": "EzXWUXfRzY6K"
+ }
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "id": "UXsD3c9TzBw-"
+ },
+ "outputs": [],
+ "source": [
+ "import tensorflow as tf"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### What is tensor Flow?\n",
+ "\n",
+ "Tensor flow is deep learning framework developed by Google in 2011 and made it publicly available in the year 2015.\n",
+ "\n",
+ "It is flexible, scalable solutio that enable us to build models with the existing frameworks.\n",
+ "\n",
+ "It is like sci-kit learn library but more advanced and flexible as we can custom build our own neural network."
+ ],
+ "metadata": {
+ "id": "nM8Clf3Oz8TX"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "print(tf.__version__)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "q3xy-QNhzXU7",
+ "outputId": "e398e880-429d-48c7-d18f-4a55488b7ec5"
+ },
+ "execution_count": 3,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "2.15.0\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Basics Unit in TensorFlow Framework - Tensor\n",
+ "\n",
+ "Tensors are multi-dimensional arrays designed for numerical data representation; although they share some similarities with NumPy arrays, they possess certain unique features that give them an advantage in deep learning tasks. One of these key advantages is their ability to utilize hardware acceleration from GPUs and TPUs to significantly speed up computational operations, which is especially useful when working with input data such as images, text, and videos.\n",
+ "\n",
+ "\n",
+ "In simple words \"ML\" needs numbers; In case of large dimensions we need matrices. These matrices are called tensors. As these are specially designed to use hardware capabilities to accelerate learnings."
+ ],
+ "metadata": {
+ "id": "qKYY91xe4_Mm"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Creating Tensors"
+ ],
+ "metadata": {
+ "id": "ga1uilJk7fnN"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "tf.constant(1, shape=(2,2))"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "A1kfJ-5V49UK",
+ "outputId": "6555b23c-5835-4701-86c5-5ba89b4e8f0a"
+ },
+ "execution_count": 13,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 13
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Here we have created a basic tensor with constant number `1` with a shape 2,2 i.e.; two rows and two columns.\n",
+ "\n",
+ "And its datatype is `integer`.\n",
+ "\n",
+ "It is a numpy array."
+ ],
+ "metadata": {
+ "id": "GnOf_KKl78I9"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "## Manually providing the shape\n",
+ "y = tf.constant([[1, 2, 3], [4, 5, 6]])\n",
+ "print(y)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "LqZaxLIr8x_p",
+ "outputId": "05e1c9aa-9322-43d1-bf44-75f6fcc39fba"
+ },
+ "execution_count": 9,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "tf.Tensor(\n",
+ "[[1 2 3]\n",
+ " [4 5 6]], shape=(2, 3), dtype=int32)\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Instead of giving the shape here we have manually given the values"
+ ],
+ "metadata": {
+ "id": "pzXkcmmyDDu1"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "tf.rank(y)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "4qIGakwZDCIq",
+ "outputId": "0d2ec1f9-7452-46da-d740-d71cab3818aa"
+ },
+ "execution_count": 11,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 11
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Here we are checking what is the rank of the tensor.\n",
+ "\n",
+ ""
+ ],
+ "metadata": {
+ "id": "KlBg-eqBEz_g"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "print(\"The rank of scalar is \" , tf.rank(tf.constant(1)))\n",
+ "print(\"The rank of vector is \" , tf.rank(tf.constant(1,shape=(5))))\n",
+ "print(\"The rank of matrix is \" , tf.rank(tf.constant(1,shape=(5,4))))\n",
+ "print(\"The rank of rank3tensor is \" , tf.rank(tf.constant(1,shape=(4,2,3))))"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "7lF6LBhVEwt1",
+ "outputId": "71a60419-7637-4743-cac9-2abc0d419aef"
+ },
+ "execution_count": 19,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "The rank of scalar is tf.Tensor(0, shape=(), dtype=int32)\n",
+ "The rank of vector is tf.Tensor(1, shape=(), dtype=int32)\n",
+ "The rank of matrix is tf.Tensor(2, shape=(), dtype=int32)\n",
+ "The rank of rank3tensor is tf.Tensor(3, shape=(), dtype=int32)\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Can there me more than 3 dimensional; of course, but we cannot represent them pictographically."
+ ],
+ "metadata": {
+ "id": "Iyuj60rvGl1W"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "print(\"The rank of rank5tensor is \" , tf.rank(tf.constant(1,shape=(4,2,3,3,3))))\n",
+ "print(\"The rank of rank9tensor is \" , tf.rank(tf.constant(1,shape=(4,2,3,3,3,1,1,3,3))))"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "BGRPAjkYFYVu",
+ "outputId": "783382cb-8b10-48e9-c32d-0666206dc463"
+ },
+ "execution_count": 24,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "The rank of rank5tensor is tf.Tensor(5, shape=(), dtype=int32)\n",
+ "The rank of rank9tensor is tf.Tensor(9, shape=(), dtype=int32)\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Basic Tensor Operations"
+ ],
+ "metadata": {
+ "id": "ZETisG8MHdhT"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "tf.constant(1.1, shape=(2,2))"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "2ZLyOAwlHhOS",
+ "outputId": "4f190f70-98b8-4a53-f87a-141cf202116c"
+ },
+ "execution_count": 26,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 26
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "#### TypeCasting\n",
+ "\n",
+ "The moment we kept 1.1 the data-type has changed to float; Lets check how to typecast integer to float and vice versa"
+ ],
+ "metadata": {
+ "id": "prkoIZ9UIe-R"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "x_int = tf.constant(1, shape=(2,2))\n",
+ "print(x_int)\n",
+ "x_float = tf.cast(x_int, dtype = tf.float32)\n",
+ "print(x_float)\n",
+ "x_float_int = tf.cast(x_float, tf.int32)\n",
+ "print(x_float_int)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "1Js_IirAIeFM",
+ "outputId": "0f542a28-fc2a-4046-cdd0-8e6fb927d0f5"
+ },
+ "execution_count": 29,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "tf.Tensor(\n",
+ "[[1 1]\n",
+ " [1 1]], shape=(2, 2), dtype=int32)\n",
+ "tf.Tensor(\n",
+ "[[1. 1.]\n",
+ " [1. 1.]], shape=(2, 2), dtype=float32)\n",
+ "tf.Tensor(\n",
+ "[[1 1]\n",
+ " [1 1]], shape=(2, 2), dtype=int32)\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "#### Indexing\n",
+ "\n",
+ "Similar to numpy array we can do indexing for the tensors"
+ ],
+ "metadata": {
+ "id": "D3Z-O9g7KAL2"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "y = tf.constant([[1,2,3],[4,5,6]])"
+ ],
+ "metadata": {
+ "id": "KxH47yQ1I62q"
+ },
+ "execution_count": 33,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "y"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "srpkft9gKICm",
+ "outputId": "d7716a5c-0dd9-4cd7-876e-b8f6b4c1a9b9"
+ },
+ "execution_count": 34,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 34
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "y[0]"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "7bObDKD2KKK3",
+ "outputId": "3d55d4ee-6ee4-45bf-ec51-c2d890c1d70a"
+ },
+ "execution_count": 35,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 35
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "y[0][0]"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "a5J2OJIfKMQ_",
+ "outputId": "7fc1a3f7-8501-422f-9a8d-8461788ffd6c"
+ },
+ "execution_count": 36,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 36
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "#### Expanding a matrix"
+ ],
+ "metadata": {
+ "id": "mYKeWLVaMA9a"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "y = tf.constant([[1,2,3],[4,5,6]])"
+ ],
+ "metadata": {
+ "id": "P3Ygk0bOLHSJ"
+ },
+ "execution_count": 42,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "y"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "a7cKMQEhMONJ",
+ "outputId": "aca81235-33a8-4784-9068-078a6fd85076"
+ },
+ "execution_count": 43,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 43
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "print(tf.expand_dims(y,axis=0)) ## Expanding at the beginning of the tensor\n",
+ "print(tf.expand_dims(y,axis=1)) ## Expanding at the Middle of the tensor { for this example}\n",
+ "print(tf.expand_dims(y,axis=-1)) ## Expanding at the End of the tensor"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "WmO6aRvMMPFL",
+ "outputId": "91a411d5-5842-4290-b897-4ff548c2519f"
+ },
+ "execution_count": 48,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "tf.Tensor(\n",
+ "[[[1 2 3]\n",
+ " [4 5 6]]], shape=(1, 2, 3), dtype=int32)\n",
+ "tf.Tensor(\n",
+ "[[[1 2 3]]\n",
+ "\n",
+ " [[4 5 6]]], shape=(2, 1, 3), dtype=int32)\n",
+ "tf.Tensor(\n",
+ "[[[1]\n",
+ " [2]\n",
+ " [3]]\n",
+ "\n",
+ " [[4]\n",
+ " [5]\n",
+ " [6]]], shape=(2, 3, 1), dtype=int32)\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Tensor Aggregation"
+ ],
+ "metadata": {
+ "id": "MTHmDiXXM05R"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "y"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "uNEWASocMVJK",
+ "outputId": "211e574d-238c-4998-cea1-81230cda7187"
+ },
+ "execution_count": 52,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 52
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "print(\"Smallest of the number is \",tf.reduce_min(y).numpy())\n",
+ "print(\"Largest of the number is \",tf.reduce_max(y).numpy())"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "bGcKg6beM-u7",
+ "outputId": "03909be6-3908-4ee4-d0ad-b73bcd32bcab"
+ },
+ "execution_count": 53,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Smallest of the number is 1\n",
+ "Largest of the number is 6\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "print(\"Sum of the numbers are \",tf.reduce_sum(y).numpy())\n",
+ "print(\"Average of the numbers are \",tf.reduce_mean(y).numpy())"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "2Zh9yc53NPOa",
+ "outputId": "9d1a7958-5927-44f3-a775-a7662883be67"
+ },
+ "execution_count": 54,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Sum of the numbers are 21\n",
+ "Average of the numbers are 3\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "#### Matrix with all ones,zeroes and identity"
+ ],
+ "metadata": {
+ "id": "QOYB77IeN4Jh"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "z = tf.ones([2,3])\n",
+ "print(z)\n",
+ "print(\" \")\n",
+ "\n",
+ "x = tf.constant(1,shape=(2,3),dtype=tf.float32)\n",
+ "print(x)\n",
+ "print(\" \")\n",
+ "\n",
+ "z = tf.zeros([2,3])\n",
+ "print(z)\n",
+ "print(\" \")\n",
+ "\n",
+ "z = tf.eye(3)\n",
+ "print(z)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "TKGTYNQeNoQ4",
+ "outputId": "e52a6223-30d0-4b18-b18f-a041dbd0272b"
+ },
+ "execution_count": 58,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "tf.Tensor(\n",
+ "[[1. 1. 1.]\n",
+ " [1. 1. 1.]], shape=(2, 3), dtype=float32)\n",
+ " \n",
+ "tf.Tensor(\n",
+ "[[1. 1. 1.]\n",
+ " [1. 1. 1.]], shape=(2, 3), dtype=float32)\n",
+ " \n",
+ "tf.Tensor(\n",
+ "[[0. 0. 0.]\n",
+ " [0. 0. 0.]], shape=(2, 3), dtype=float32)\n",
+ " \n",
+ "tf.Tensor(\n",
+ "[[1. 0. 0.]\n",
+ " [0. 1. 0.]\n",
+ " [0. 0. 1.]], shape=(3, 3), dtype=float32)\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "#### Reshaping and Transposing Tensors"
+ ],
+ "metadata": {
+ "id": "DEIvWGR5OSJN"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "x_initial = tf.constant(1, shape=(4,3))\n",
+ "print(x_initial)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "G9S-hKxyN68-",
+ "outputId": "4376bc4e-1d84-4bfa-c5e5-64506dbf9664"
+ },
+ "execution_count": 61,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "tf.Tensor(\n",
+ "[[1 1 1]\n",
+ " [1 1 1]\n",
+ " [1 1 1]\n",
+ " [1 1 1]], shape=(4, 3), dtype=int32)\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "tf.reshape(x_initial,shape=(2,2,3))"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "5gUJGsKIOq6A",
+ "outputId": "e62ec1e2-d079-4ef2-bab7-af16d109a2fa"
+ },
+ "execution_count": 62,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 62
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "tf.reshape(x_initial,shape=(2,6))"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "PDpd_dm8Osjr",
+ "outputId": "ca2d9a22-b98d-44fa-88a9-2f4d4d3a3c8a"
+ },
+ "execution_count": 63,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 63
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "tf.reshape(x_initial,shape=(12,1))"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "D9HiXTMXO3ko",
+ "outputId": "85f133db-6270-4326-d063-c45c0a59c6fc"
+ },
+ "execution_count": 64,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 64
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Here we can reshape to any other shape; However, the multiplication of shapes should remain the same."
+ ],
+ "metadata": {
+ "id": "Gn3AFfQ3O9ZZ"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "tf.reshape(x_initial,shape=-1) #Flatten the array"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "hkZIKfhMO6re",
+ "outputId": "83f86c50-610c-42af-96cd-1d9fcd3fd8d3"
+ },
+ "execution_count": 66,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 66
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "tf.transpose(x_initial)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "chW9pLsNPOcZ",
+ "outputId": "907c7fe3-d78c-4453-d836-499e2b015ce7"
+ },
+ "execution_count": 68,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 68
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "The initial shape of `(4,3)` got changed to `(3,4)`"
+ ],
+ "metadata": {
+ "id": "auLTk3TOPeD3"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "#### Distrbutions"
+ ],
+ "metadata": {
+ "id": "SravOXaTPzrF"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "x1 = tf.random.normal((3,3))\n",
+ "print(x1)\n",
+ "print(\" \")\n",
+ "\n",
+ "x1 = tf.random.normal((3,3),mean = 0, stddev =1 )\n",
+ "print(x1)\n",
+ "print(\" \")\n",
+ "\n",
+ "x2 = tf.random.uniform((3,3))\n",
+ "print(x2)\n",
+ "print(\" \")"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "t-VzWiInPZhc",
+ "outputId": "7684f587-ed7c-4f1e-e360-8fe1fce686e2"
+ },
+ "execution_count": 70,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "tf.Tensor(\n",
+ "[[ 0.591363 0.12791212 0.38762185]\n",
+ " [ 0.26025018 1.7209182 -0.7802837 ]\n",
+ " [ 0.89150804 -0.9648455 0.64507854]], shape=(3, 3), dtype=float32)\n",
+ " \n",
+ "tf.Tensor(\n",
+ "[[-1.0034778 0.05435322 -1.3141975 ]\n",
+ " [-0.17819698 -1.9136705 -0.9396771 ]\n",
+ " [ 2.2143493 0.33600262 0.8174351 ]], shape=(3, 3), dtype=float32)\n",
+ " \n",
+ "tf.Tensor(\n",
+ "[[0.04812372 0.79855204 0.8067709 ]\n",
+ " [0.67069924 0.06617999 0.14941025]\n",
+ " [0.31500185 0.17441607 0.7476181 ]], shape=(3, 3), dtype=float32)\n",
+ " \n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "#### Mathematical Operations\n",
+ "\n",
+ "* Addition\n",
+ "* Subtraction\n",
+ "* Multiplication\n",
+ "* Division\n"
+ ],
+ "metadata": {
+ "id": "jCdxKVylQBmU"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "x4 = tf.random.normal((3,3))\n",
+ "print(x4)\n",
+ "print(\" \")\n",
+ "y4 = tf.random.normal((3,3))\n",
+ "print(y4)\n",
+ "print(\" \")"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "duewhYOaP5PY",
+ "outputId": "42a7412e-b455-4b6e-eba6-b314c0007fcc"
+ },
+ "execution_count": 71,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "tf.Tensor(\n",
+ "[[ 0.5908952 3.5452905 -0.34438497]\n",
+ " [-0.5237503 1.2899861 -0.50684774]\n",
+ " [ 1.2187229 0.50014 -0.6212071 ]], shape=(3, 3), dtype=float32)\n",
+ " \n",
+ "tf.Tensor(\n",
+ "[[-0.7346279 2.9705956 -0.45318994]\n",
+ " [-0.947753 0.6556651 3.018978 ]\n",
+ " [-1.5799906 -1.2278746 0.57451475]], shape=(3, 3), dtype=float32)\n",
+ " \n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "print(x4+y4)\n",
+ "print(\" \")\n",
+ "tf.add(x4,y4)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "TzMoomj8QvYF",
+ "outputId": "c276b459-cb73-451f-f5da-e922e439f74e"
+ },
+ "execution_count": 76,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "tf.Tensor(\n",
+ "[[-0.14373273 6.5158863 -0.7975749 ]\n",
+ " [-1.4715033 1.9456513 2.5121303 ]\n",
+ " [-0.3612677 -0.7277346 -0.04669237]], shape=(3, 3), dtype=float32)\n",
+ " \n"
+ ]
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 76
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "print(x4-y4)\n",
+ "print(\" \")\n",
+ "tf.subtract(x4,y4)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "5dSUDB9bQxMk",
+ "outputId": "6d236d14-31cd-4dfb-b268-29b680a6af21"
+ },
+ "execution_count": 77,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "tf.Tensor(\n",
+ "[[ 1.3255231 0.5746949 0.10880497]\n",
+ " [ 0.4240027 0.63432103 -3.525826 ]\n",
+ " [ 2.7987137 1.7280147 -1.1957219 ]], shape=(3, 3), dtype=float32)\n",
+ " \n"
+ ]
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 77
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "print(x4*y4)\n",
+ "print(\" \")\n",
+ "tf.multiply(x4,y4)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "oJrV9fmnQy5Q",
+ "outputId": "57b5cfcb-3cec-4b18-eb51-7e01ea0209e5"
+ },
+ "execution_count": 78,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "tf.Tensor(\n",
+ "[[-0.43408808 10.531624 0.1560718 ]\n",
+ " [ 0.49638593 0.8457989 -1.5301622 ]\n",
+ " [-1.9255708 -0.6141092 -0.35689265]], shape=(3, 3), dtype=float32)\n",
+ " \n"
+ ]
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 78
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "print(x4/y4)\n",
+ "print(\" \")\n",
+ "tf.divide(x4,y4)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "wZ2ZiYopQ24r",
+ "outputId": "71d0d22f-1515-45e8-ab53-37c11d6d975e"
+ },
+ "execution_count": 79,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "tf.Tensor(\n",
+ "[[-0.8043462 1.1934612 0.7599131 ]\n",
+ " [ 0.5526232 1.9674467 -0.16788718]\n",
+ " [-0.77134824 -0.40732172 -1.0812727 ]], shape=(3, 3), dtype=float32)\n",
+ " \n"
+ ]
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 79
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "#### Matrix Multiplications"
+ ],
+ "metadata": {
+ "id": "keKH4RpRRQ8X"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "x4_new = tf.random.normal((3,2))\n",
+ "y4_new = tf.random.normal((2,3))\n",
+ "\n",
+ "print(tf.matmul(x4_new,y4_new))"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "dYgFVx8KQ40-",
+ "outputId": "42de8703-84e9-4cc6-83ef-f70a71b7a2f2"
+ },
+ "execution_count": 81,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "tf.Tensor(\n",
+ "[[ 0.5675167 0.29923582 -2.018334 ]\n",
+ " [-0.5145724 1.9392778 -1.5560541 ]\n",
+ " [ 1.0566927 -2.3777525 0.73752195]], shape=(3, 3), dtype=float32)\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "x4_new @ y4_new"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "63OPzL8_SMnC",
+ "outputId": "eaf8aa78-d380-4041-d2e1-c6818e7543a2"
+ },
+ "execution_count": 84,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "execution_count": 84
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Two ways of matrix of multiplication in tensors"
+ ],
+ "metadata": {
+ "id": "arPLC1JUSSgQ"
+ }
+ }
+ ]
+}
\ No newline at end of file