neural_network/numpy_nn/activation_numpy_3.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "d863e2b2",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eb32e860",
   "metadata": {},
   "source": [
    "relu激活函数"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "eead13ab",
   "metadata": {},
   "outputs": [],
   "source": [
    "inputs = [0, -1, 3, 4, 6, 7]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "307e7d14",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 0, 3, 4, 6, 7]"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "outputs = []\n",
    "for i in inputs:\n",
    "    if i > 0:\n",
    "        outputs.append(i)\n",
    "    else:\n",
    "        outputs.append(0)\n",
    "outputs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "ef4784b3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 0, 3, 4, 6, 7]"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "outputs = []\n",
    "for i in inputs:\n",
    "    outputs.append(max(0, i))\n",
    "outputs"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.7.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}