ai basic1 snippets

3d_mesh.ipynb

activation.ipynb

axis.ipynb

broadcasting.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "A = np.array(\n",
    "    [[1,2,3],\n",
    "     [4,5,6],\n",
    "     [7,8,9]]) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "A:\n",
      " [[1 2 3]\n",
      " [4 5 6]\n",
      " [7 8 9]]\n",
      "\n",
      "A*2:\n",
      " [[ 2  4  6]\n",
      " [ 8 10 12]\n",
      " [14 16 18]]\n",
      "\n",
      "A+10:\n",
      " [[11 12 13]\n",
      " [14 15 16]\n",
      " [17 18 19]]\n"
     ]
    }
   ],
   "source": [
    "print(\"A:\\n\", A)\n",
    "print(\"\\nA*2:\\n\", A * 2)   # multiply by 2\n",
    "print(\"\\nA+10:\\n\", A + 10) # add 10"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "B = np.array([[10],\n",
    "              [100],\n",
    "              [1000]]) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "A:\n",
      " [[1 2 3]\n",
      " [4 5 6]\n",
      " [7 8 9]]\n",
      "\n",
      "B:\n",
      " [[  10]\n",
      " [ 100]\n",
      " [1000]]\n",
      "\n",
      "A+B:\n",
      " [[  11   12   13]\n",
      " [ 104  105  106]\n",
      " [1007 1008 1009]]\n",
      "\n",
      "A*B:\n",
      " [[  10   20   30]\n",
      " [ 400  500  600]\n",
      " [7000 8000 9000]]\n"
     ]
    }
   ],
   "source": [
    "print(\"A:\\n\", A)\n",
    "print(\"\\nB:\\n\", B)\n",
    "print(\"\\nA+B:\\n\", A+B) \n",
    "print(\"\\nA*B:\\n\", A*B)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## np.log, np.abs, np.maximum"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0.         0.69314718 1.09861229]\n",
      " [1.38629436 1.60943791 1.79175947]\n",
      " [1.94591015 2.07944154 2.19722458]]\n"
     ]
    }
   ],
   "source": [
    "print(np.log(A))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 1  4  9]\n",
      " [16 25 36]\n",
      " [49 64 81]]\n"
     ]
    }
   ],
   "source": [
    "print(np.square(A))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[1.         1.41421356 1.73205081]\n",
      " [2.         2.23606798 2.44948974]\n",
      " [2.64575131 2.82842712 3.        ]]\n"
     ]
    }
   ],
   "source": [
    "print(np.sqrt(A))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## RELU"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = np.array([[1,-2,3,-4],\n",
    "              [-9,4,5,6]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[1 0 3 0]\n",
      " [0 4 5 6]]\n"
     ]
    }
   ],
   "source": [
    "Y = np.maximum(0, X)\n",
    "print(Y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Reference: [Python的矩陣傳播機制&矩陣運算](https://www.jianshu.com/p/e26f381f82ad)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}

entropy.ipynb

mnist.ipynb

numpy_speed.ipynb

torch_speed.ipynb