neural_network/numpy_nn/numpy_layer_2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "92a1159e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "6306fef2",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = [1, 2, 3] #数据（3，）\n",
    "weight = [2, -1, 1] #权重\n",
    "bias = 2#偏置"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c71760e7",
   "metadata": {},
   "source": [
    "转成ndarray"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6ad946d7",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = np.array(X)\n",
    "weight = np.array(weight)\n",
    "bias = np.array(bias)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "ad1fd582",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((3,), (3,), ())"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.shape, weight.shape, bias.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1e81245b",
   "metadata": {},
   "source": [
    "向量点成"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "795bd2f0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(3, 3)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.dot(X, weight), np.dot(weight, X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "6c087a5a",
   "metadata": {},
   "outputs": [],
   "source": [
    "output = np.dot(X, weight) + bias"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "6d64a1bc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "6f7fc0e1",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = [1, 2, 3] #数据（3，）\n",
    "weight = [[2, -1, 1],\n",
    "          [2, 3, 1]] #权重\n",
    "bias = [2, 3]#偏置"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "c4bbb7a6",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = np.array(X)\n",
    "weight = np.array(weight)\n",
    "bias = np.array(bias)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "1ce4b03a",
   "metadata": {},
   "outputs": [],
   "source": [
    "output = np.dot(weight, X) + bias"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "f76ed5a0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 5, 14])"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "d83e4284",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = [[1, 2, 3],\n",
    "     [2, 3, 4],\n",
    "     [4, 5, 6]] #数据（3， 3）\n",
    "weight = [[2, -1, 1],\n",
    "          [2, 3, 1]] #权重\n",
    "bias = [[2, 3]]#偏置"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "75e715a9",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = np.array(X)\n",
    "weight = np.array(weight)\n",
    "bias = np.array(bias)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c397fd32",
   "metadata": {},
   "source": [
    "对于多个数据，还是和上面使用同样的点乘是不行的。一定要注意数据的维度。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "ab7fe33a",
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "shapes (3,3) and (2,3) not aligned: 3 (dim 1) != 2 (dim 0)",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[1;32m~\\AppData\\Local\\Temp\\ipykernel_1764\\268821979.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0moutput\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdot\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mweight\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0mbias\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32m<__array_function__ internals>\u001b[0m in \u001b[0;36mdot\u001b[1;34m(*args, **kwargs)\u001b[0m\n",
      "\u001b[1;31mValueError\u001b[0m: shapes (3,3) and (2,3) not aligned: 3 (dim 1) != 2 (dim 0)"
     ]
    }
   ],
   "source": [
    "output = np.dot(X, weight) + bias"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "844d2afe",
   "metadata": {},
   "outputs": [],
   "source": [
    "output = np.dot(X, weight.T) + bias"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "5e945d68",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 5, 14],\n",
       "       [ 7, 20],\n",
       "       [11, 32]])"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c71f101e",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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
}